Matching entries: 0
settings...
Ertin E, Stohs N, Kumar S, Raij A, al'Absi M and Shah S (2011), "AutoSense: Unobtrusively Wearable Sensor Suite for Inferring the Onset, Causality, and Consequences of Stress in the Field", In Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. New York, NY, USA , pp. 274-287. ACM.
Abstract: The effect of psychosocial stress on health has been a central focus area of public health research. However, progress has been limited due a to lack of wearable sensors that can provide robust measures of stress in the field. In this paper, we present a wireless sensor suite called AutoSense that collects and processes cardiovascular, respiratory, and thermoregularity measurements that can inform about the general stress state of test subjects in their natural environment. AutoSense overcomes several challenges in the design of wearable sensor systems for use in the field. First, it is unobtrusively wearable because it integrates six sensors in a small form factor. Second, it demonstrates a low power design; with a lifetime exceeding ten days while continuously sampling and transmitting sensor measurements. Third, sensor measurements are robust to several sources of errors and confounds inherent in field usage. Fourth, it integrates an ANT radio for low power and integrated quality of service guarantees, even in crowded environments. The AutoSense suite is complemented with a software framework on a smart phone that processes sensor measurements received from AutoSense to infer stress and other rich human behaviors. AutoSense was used in a 20+ subject real-life scientific study on stress in both the lab and field, which resulted in the first model of stress that provides 90% accuracy.
BibTeX:
@inproceedings{Ertin:2011:AUW:2070942.2070970,
  author = {Ertin, Emre and Stohs, Nathan and Kumar, Santosh and Raij, Andrew and al'Absi, Mustafa and Shah, Siddharth},
  title = {AutoSense: Unobtrusively Wearable Sensor Suite for Inferring the Onset, Causality, and Consequences of Stress in the Field},
  booktitle = {Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems},
  publisher = {ACM},
  year = {2011},
  pages = {274--287},
  url = {http://doi.acm.org/10.1145/2070942.2070970},
  doi = {10.1145/2070942.2070970}
}
Rahman MM, Ali AA, Plarre K, Al'Absi M, Ertin E and Kumar S (2011), "mconverse: Inferring conversation episodes from respiratory measurements collected in the field", In Proceedings of the 2nd Conference on Wireless Health. , pp. 10.
Abstract: Automated detection of social interactions in the natural environment has resulted in promising advances in organizational behavior, consumer behavior, and behavioral health. Progress, however, has been limited since the primary means of assessing social interactions today (i.e., audio recording) has several issues in field usage such as microphone occlusion, lack of speaker specificity, and high energy drain, in addition to significant privacy concerns. In this paper, we present mConverse, a new mobilebased system to infer conversation episodes from respiration measurements collected in the field from an unobtrusively wearable respiratory inductive plethysmograph (RIP) band worn around the user’s chest. The measurements are wirelessly transmitted to a mobile phone, where they are used in a novel machine learning model to determine whether the wearer is speaking, listening, or quiet. Our model incorporates several innovations to address issues that naturally arise in the noisy field environment such as confounding events, poor data quality due to sensor loosening and detachment, losses in the wireless channel, etc. Our basic model obtains 83% accuracy for the three class classification. We formulate a Hidden Markov Model to further improve the accuracy to 87%. Finally, we apply our model to data collected from 22 subjects who wore the sensor for 2 full days in the field to observe conversation behavior in daily life and find that people spend 25% of their day in conversations
BibTeX:
@inproceedings{rahman2011mconverse,
  author = {Rahman, Md Mahbubur and Ali, Amin Ahsan and Plarre, Kurt and Al'Absi, Mustafa and Ertin, Emre and Kumar, Santosh},
  title = {mconverse: Inferring conversation episodes from respiratory measurements collected in the field},
  booktitle = {Proceedings of the 2nd Conference on Wireless Health},
  year = {2011},
  pages = {10}
}
Misha Pavel, Wendy Nilsen, Santosh Kumar and Mani Srivastava (2013), "Mobile Health: Revolutionizing Healthcare Through Transdisciplinary Research", Computer. Los Alamitos, CA, USA Vol. 46, pp. 28-35. IEEE Computer Society.
Abstract: Mobile health (mHealth) seeks to improve individuals' health and well-being by continuously monitoring their status, rapidly diagnosing medical conditions, recognizing behaviors, and delivering just-in-time interventions, all in the user's natural mobile environment. The Web extra at http://youtu.be/o2mieSywutY is an audio interview in which Santosh Kumar, Wendy Nilsen, and Mani Srivastava discuss the path toward realizing mobile health systems.
BibTeX:
@article{10.1109/MC.2012.392,
  author = {Misha Pavel, and Wendy Nilsen, and Santosh Kumar, and Mani Srivastava,},
  title = {Mobile Health: Revolutionizing Healthcare Through Transdisciplinary Research},
  journal = {Computer},
  publisher = {IEEE Computer Society},
  year = {2013},
  volume = {46},
  pages = {28-35},
  doi = {doi.ieeecomputersociety.org/10.1109/MC.2012.392}
}
Kumar S, Nilsen WJ, Abernethy A, Atienza A, Patrick K, Pavel M, Riley WT, Shar A, Spring B, Spruijt-Metz D, Hedeker D, Honavar V, Kravitz R, Lefebvre RC, Mohr DC, Murphy SA, Quinn C, Shusterman V and Swendeman D (2013), "Mobile health technology evaluation: the mHealth evidence workshop.", American journal of preventive medicine. Netherlands Vol. 45, pp. 228-36.
Abstract: Creative use of new mobile and wearable health information and sensing technologies (mHealth) has the potential to reduce the cost of health care and improve well-being in numerous ways. These applications are being developed in a variety of domains, but rigorous research is needed to examine the potential, as well as the challenges, of utilizing mobile technologies to improve health outcomes. Currently, evidence is sparse for the efficacy of mHealth. Although these technologies may be appealing and seemingly innocuous, research is needed to assess when, where, and for whom mHealth devices, apps, and systems are efficacious. In order to outline an approach to evidence generation in the field of mHealth that would ensure research is conducted on a rigorous empirical and theoretic foundation, on August 16, 2011, researchers gathered for the mHealth Evidence Workshop at NIH. The current paper presents the results of the workshop. Although the discussions at the meeting were cross-cutting, the areas covered can be categorized broadly into three areas: (1) evaluating assessments; (2) evaluating interventions; and (3) reshaping evidence generation using mHealth. This paper brings these concepts together to describe current evaluation standards, discuss future possibilities, and set a grand goal for the emerging field of mHealth research.
BibTeX:
@article{Kumar2013,
  author = {Kumar, Santosh and Nilsen, Wendy J. and Abernethy, Amy and Atienza, Audie and Patrick, Kevin and Pavel, Misha and Riley, William T. and Shar, Albert and Spring, Bonnie and Spruijt-Metz, Donna and Hedeker, Donald and Honavar, Vasant and Kravitz, Richard and Lefebvre, R. Craig and Mohr, David C. and Murphy, Susan A. and Quinn, Charlene and Shusterman, Vladimir and Swendeman, Dallas},
  title = {Mobile health technology evaluation: the mHealth evidence workshop.},
  journal = {American journal of preventive medicine},
  year = {2013},
  volume = {45},
  pages = {228-36}
}
Wanner L and Srivastava M (2014), "ViRUS: Virtual Function Replacement Under Stress", In 6th Workshop on Power-Aware Computing and Systems (HotPower 14). Broomfield, CO USENIX Association.
Abstract: In this paper we introduce ViRUS: Virtual function Replacement Under Stress. ViRUS allows the runtime system to switch between blocks of code that perform equivalent functionality at different Quality-of- Service levels when the system is under stress — be it in the form of scarce energy resources, temperature emergencies, or various sources of environmental and process variability — with the ultimate goal of energy efficiency. We demonstrate ViRUS with a framework for transparent function replacement in shared libraries and a polymorphic version of the standard C math library in Linux. Case studies show how ViRUS can tradeoff upwards of 4% degradation in application quality for a band of upwards of 50% savings in energy consumption.
BibTeX:
@inproceedings{187114,
  author = {L. Wanner and M.B. Srivastava},
  title = {ViRUS: Virtual Function Replacement Under Stress},
  booktitle = {6th Workshop on Power-Aware Computing and Systems (HotPower 14)},
  publisher = {USENIX Association},
  year = {2014},
  url = {http://blogs.usenix.org/conference/hotpower14/workshop-program/presentation/wanner}
}
Yang L, Ting K and Srivastava M (2014), "Inferring occupancy from opportunistically available sensor data", In 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom). , pp. 60-68.
Abstract: Commercial and residential buildings are usually instrumented with meters and sensors that are deployed as part of a utility infrastructure installed by companies that provide services such as electricity, water, gas, security, phone, etc. As part of their normal operation, these service providers have direct access to information from the sensors and meters. A concern arises that the sensory information collected by the providers, although coarse-grained, can be subject to analysis that reveals private information about the users of the building. Oftentimes, multiple services are provided by the same company, in which case the potential for leakage of private information increases. Our research seeks to investigate the extent to which easily available sensory information may be used by external service providers to make occupancy-related inferences. Particularly, we focus on inferences from two different sources: motion sensors, which are installed and monitored by security companies, and smart electric meters, which are deployed by electric companies for billing and demand-response management. We explore the motion sensor scenario in a three-person single-family home and the electric meter scenario in a twelve-person university lab. Our exploration with various inference methods shows that sensory information available to service providers can enable them to make undesired occupancy related inferences, such as levels of occupancy or even the identities of current occupants, significantly better than naive prediction strategies that do not make use of sensor information.
BibTeX:
@inproceedings{6813945,
  author = {L. Yang and K. Ting and M.B. Srivastava},
  title = {Inferring occupancy from opportunistically available sensor data},
  booktitle = {2014 IEEE International Conference on Pervasive Computing and Communications (PerCom)},
  year = {2014},
  pages = {60-68},
  url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6813945}
}
Rehg J, Rozga A, Abowd G and Goodwin M (2014), "Behavioral Imaging and Autism", Pervasive Computing, IEEE. Vol. 13(2), pp. 84-87.
Abstract: Behavioral imaging encompasses the use of computational sensing and modeling techniques to measure and analyze human behavior. This article discusses a research program focused on the study of dyadic social interactions between children and their caregivers and peers. The study has resulted in a dataset containing semi-structured play interactions between children and adults. Behavioral imaging could broadly affect the quality of care for individuals with a developmental or behavioral disorder.
BibTeX:
@article{6818509,
  author = {J.M. Rehg and A. Rozga and G.D. Abowd and M.S. Goodwin},
  title = {Behavioral Imaging and Autism},
  journal = {Pervasive Computing, IEEE},
  year = {2014},
  volume = {13},
  number = {2},
  pages = {84-87},
  url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6818509}
}
Stewart K, Majurec N, Burkholder R, Ertin E and Johnson J (2014), "Waveform-diverse MIMO imaging radar target measurements", In 2014 IEEE Radar Conference. , pp. 0918-0922.
Abstract: The construction and testing of a MIMO radar for target imaging are presented. Two distinct radar systems are combined in order to form a four-channel platform with operation validated through a series of stationary target measurements. These are conducted using both time-diverse and waveform-diverse channel separation methods, and imaging results from each are compared to evaluate the performance of two varieties of pseudo-noise waveforms and the LFM chirp. Results from the first experiment successfully demonstrate the operation of the radar system but leave open a number of scientific questions for further investigation in a revised experiment. Conclusions from this second measurement are to be presented in this year's radar conference.
BibTeX:
@inproceedings{6875722,
  author = {K.B. Stewart and N. Majurec and R.J. Burkholder and E. Ertin and J.T. Johnson},
  title = {Waveform-diverse MIMO imaging radar target measurements},
  booktitle = {2014 IEEE Radar Conference},
  year = {2014},
  pages = {0918-0922},
  url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6875722&abstractAccess=no&userType=inst}
}
Pienta R, Tamersoy A, Tong H and Chau D (2014), "MAGE: Matching approximate patterns in richly-attributed graphs", In 2014 IEEE International Conference on Big Data (Big Data). , pp. 585-590.
Abstract: Given a large graph with millions of nodes and edges, say a social network where both its nodes and edges have multiple attributes (e.g., job titles, tie strengths), how to quickly find subgraphs of interest (e.g., a ring of businessmen with strong ties)? We present MAGE, a scalable, multicore subgraph matching approach that supports expressive queries over large, richly-attributed graphs. Our major contributions include: (1) MAGE supports graphs with both node and edge attributes (most existing approaches handle either one, but not both); (2) it supports expressive queries, allowing multiple attributes on an edge, wildcards as attribute values (i.e., match any permissible values), and attributes with continuous values; and (3) it is scalable, supporting graphs with several hundred million edges. We demonstrate MAGE's effectiveness and scalability via extensive experiments on large real and synthetic graphs, such as a Google+ social network with 460 million edges.
BibTeX:
@inproceedings{7004278,
  author = {R. Pienta and A. Tamersoy and H. Tong and D.H. Chau},
  title = {MAGE: Matching approximate patterns in richly-attributed graphs},
  booktitle = {2014 IEEE International Conference on Big Data (Big Data)},
  year = {2014},
  pages = {585-590},
  url = {http://www.cc.gatech.edu/ dchau/papers/14-bigdata-MAGE.pdf}
}
Abraham W, Stough W, Pina I, Linde C, Borer J, Ferrari GD, Mehran R, Stein K, Vincent A, Yadav J, Anker S and Zannad F (2014), "Trials of implantable monitoring devices in heart failure: which design is optimal?", Nature Reviews Cardiology. Vol. 11(10), pp. 576-585. Nature Publishing Group.
Abstract: Implantable monitoring devices have been developed to detect early evidence of heart failure (HF) decompensation, with the hypothesis that early detection might enable clinicians to commence therapy sooner than would otherwise be possible, and potentially to reduce the rate of hospitalization. In addition to the usual challenges inherent to device trials (such as the difficulty of double-blinding and potential for bias), studies of implantable monitoring devices present unique difficulties because they involve assessment of therapeutic end points for diagnostic devices. Problems include the lack of uniform approaches to treatment in study protocols for device alerts or out-of-range values, and the requirement of levels of evidence traditionally associated with therapeutic devices to establish effectiveness and safety. In this Review, the approaches used to deal with these issues are discussed, including the use of objective primary end points with blinded adjudication, identical duration of follow-up and number of encounters for patients in active monitoring and control groups, and treatment recommendations between groups that are consistent with international guidelines. Remote monitoring devices hold promise for reducing the rate of hospitalization among patients with HF. However, optimization of regulatory approaches and clinical trial design is needed to facilitate further evaluation of the effectiveness of combining health information technology and medical devices.
BibTeX:
@article{Abraham2014,
  author = {W.T. Abraham and W.G. Stough and I.L. Pina and C. Linde and J.S. Borer and G.M. De Ferrari and R. Mehran and K.M. Stein and A. Vincent and J.S. Yadav and S.D. Anker and F. Zannad},
  title = {Trials of implantable monitoring devices in heart failure: which design is optimal?},
  journal = {Nature Reviews Cardiology},
  publisher = {Nature Publishing Group},
  year = {2014},
  volume = {11},
  number = {10},
  pages = {576--585},
  url = {http://www.nature.com/nrcardio/journal/v11/n10/full/nrcardio.2014.114.html}
}
Abraham W, Adamson P, Packer M, Bauman J and Yadav J (2014), "Impact of Introduction of Pulmonary Artery Pressure Monitoring for Heart Failure Management:: Longitudinal Results from the Champion Trial", Journal of the American College of Cardiology. Vol. 63(12_S) Am Coll Cardio Found.
BibTeX:
@article{Abraham2014a,
  author = {W.T. Abraham and P. Adamson and M. Packer and J. Bauman and J. Yadav},
  title = {Impact of Introduction of Pulmonary Artery Pressure Monitoring for Heart Failure Management:: Longitudinal Results from the Champion Trial},
  journal = {Journal of the American College of Cardiology},
  publisher = {Am Coll Cardio Found},
  year = {2014},
  volume = {63},
  number = {12_S},
  url = {http://content.onlinejacc.org/article.aspx?articleid=1856280}
}
Abraham W, Adamson P, Stevenson L and Yadav J (2014), "Benefits of Pulmonary Artery Pressure Monitoring in Patients with NYHA Class III Heart Failure and Chronic Kidney Disease: Results from the CHAMPION Trial", Journal of Cardiac Failure. Vol. 20(8), pp. S93. Elsevier.
Abstract: Management of heart failure (HF) patients incorporates diuretic strategies to reduce congestion and prevent decompensation. Elevated cardiac filling pressures precede signs/symptoms that lead to decompensation; implantable hemodynamic monitoring (IHM) devices allow home monitoring of this signal. The CHAMPION trial found significant reductions in HF hospitalizations (HFH) in NYHA class III HF patients whose syndrome was managed using pulmonary artery pressure (PAP) from an IHM. We examined the potential benefit of PAP monitoring in patients with HF and chronic kidney disease (CKD), a difficult population to manage effectively.
BibTeX:
@article{Abraham2014b,
  author = {W.T. Abraham and P.B. Adamson and L.W. Stevenson and J. Yadav},
  title = {Benefits of Pulmonary Artery Pressure Monitoring in Patients with NYHA Class III Heart Failure and Chronic Kidney Disease: Results from the CHAMPION Trial},
  journal = {Journal of Cardiac Failure},
  publisher = {Elsevier},
  year = {2014},
  volume = {20},
  number = {8},
  pages = {S93},
  url = {http://www.onlinejcf.com/article/S1071-9164(14)00492-8/fulltext}
}
Adams C, Chen M, Guo L, Lam C, Stewart D, Correa-Fernández V, Cano M, Heppner W, Vidrine J, Li Y, Ahluwalia J, Cinciripini P and Wetter D (2014), "Mindfulness predicts lower affective volatility among African Americans during smoking cessation.", Psychology of Addictive Behavior. Vol. 28(2), pp. 580-585.
Abstract: Recent research suggests that mindfulness benefits emotion regulation and smoking cessation. However, the mechanisms by which mindfulness affects emotional and behavioral functioning are unclear. One potential mechanism, lower affective volatility, has not been empirically tested during smoking cessation. This study examined longitudinal associations among mindfulness and emotional responding over the course of smoking cessation treatment among predominantly low-socioeconomic status (SES) African American smokers, who are at high risk for relapse to smoking and tobacco-related health disparities. Participants (N = 399, 51% female, mean age = 42, 48% with annual income <$10,000) completed a baseline measure of trait mindfulness. Negative affect, positive affect, and depressive symptoms were assessed at five time points during smoking cessation treatment (up to 31 days postquit). Volatility indices were calculated to quantify within-person instability of emotional symptoms over time. Over and above demographic characteristics, nicotine dependence, and abstinence status, greater baseline trait mindfulness predicted lower volatility of negative affect and depressive symptoms surrounding the quit attempt and up to 1 month postquit, ps < 0.05. Although volatility did not mediate the association between greater mindfulness and smoking cessation, these results are the first to show that mindfulness is linked to lower affective volatility (or greater stability) of negative emotions during the course of smoking cessation. The present study suggests that mindfulness is linked to greater emotional stability and augments the study of mindfulness in diverse populations. Future studies should examine the effects of mindfulness-based interventions on volatility and whether lower volatility explains effects of mindfulness-based treatments on smoking cessation.
BibTeX:
@article{Adams2014,
  author = {C.E. Adams and M. Chen and L. Guo and C.Y. Lam and D.W. Stewart and V. Correa-Fernández and M.A. Cano and W.L. Heppner and J.I. Vidrine and Y. Li and J.S. Ahluwalia and P.M. Cinciripini and D.W. Wetter},
  title = {Mindfulness predicts lower affective volatility among African Americans during smoking cessation.},
  journal = {Psychology of Addictive Behavior},
  year = {2014},
  volume = {28},
  number = {2},
  pages = {580-585},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24955676}
}
Adamson P, Abraham W, Bourge R, Costanzo M, Hasan A, Yadav C, Henderson J, Cowart P and Stevenson L (2014), "Wireless Pulmonary Artery Pressure Monitoring Guides Management to Reduce Decompensation in Heart Failure With Preserved Ejection Fraction", Circulation: Heart Failure. , pp. CIRCHEARTFAILURE-113. Lippincott Williams &amp; Wilkins.
Abstract: Background—No treatment strategies have been demonstrated to be beneficial for the population for patients with heart failure and preserved ejection fraction.

Methods and Results—The CHAMPION Trial was a prospective, single-blinded, randomized controlled clinical trial testing the hypothesis that hemodynamically guided heart failure management decreases decompensation leading to hospitalization. Of the 550 patients enrolled in the study, 119 had LVEF ≥40% (average 50.6%), 430 patients had low LVEF (<40%, average 23.3%) and one patient had no documented LVEF. A microelectromechanical systems (MEMS) pressure sensor was permanently implanted in all participants during right heart catheterization. After implant, subjects were randomly assigned in single-blind fashion to a treatment group in whom daily uploaded pressures were used in a treatment strategy for HF management or to a control group in whom standard HF management included weight-monitoring , and pressures were uploaded but not available for investigator use. The primary efficacy endpoint of HF hospitalization rate over 6 months for preserved EF patients was 46% lower in the treatment group compared to control (IRR 0.54, C.I. 0.38-0.70, p<0.0001). After an average of 17.6 months of blinded follow-up, the hospitalization rate was 50% lower (IRR 0.50, C.I. 0.35-0.70, p<0.0001). In response to PA pressure information, more changes in diuretic and vasodilator therapies were made in the treatment group.

Conclusions—Hemodynamically-guided management of HF patients with preserved ejection fraction reduced decompensation leading to hospitalization compared to standard HF management strategies.
BibTeX:
@article{Adamson2014a,
  author = {P.B. Adamson and W.T. Abraham and R.C. Bourge and M.R. Costanzo and A. Hasan and C. Yadav and J. Henderson and P. Cowart and L.W. Stevenson},
  title = {Wireless Pulmonary Artery Pressure Monitoring Guides Management to Reduce Decompensation in Heart Failure With Preserved Ejection Fraction},
  journal = {Circulation: Heart Failure},
  publisher = {Lippincott Williams &amp; Wilkins},
  year = {2014},
  pages = {CIRCHEARTFAILURE--113},
  url = {http://circheartfailure.ahajournals.org/content/early/2014/10/06/CIRCHEARTFAILURE.113.001229.abstract}
}
Adamson P, Abraham W, Stevenson L, Neville S, Cowart P and Yadav J (2014), "Benefits of Pulmonary Artery Pressure Monitoring Extend to Reduction of All-Cause Rehospitalization", Journal of the American College of Cardiology. Vol. 63(12_S) Am Coll Cardio Found.
BibTeX:
@article{Adamson2014b,
  author = {P.B. Adamson and W.T. Abraham and L.W. Stevenson and S. Neville and P. Cowart and J. Yadav},
  title = {Benefits of Pulmonary Artery Pressure Monitoring Extend to Reduction of All-Cause Rehospitalization},
  journal = {Journal of the American College of Cardiology},
  publisher = {Am Coll Cardio Found},
  year = {2014},
  volume = {63},
  number = {12_S},
  url = {http://content.onlinejacc.org/article.aspx?articleid=1856665}
}
Adamson P, Abraham W, Bauman J and Yadav J (2014), "Impact of Wireless Pulmonary Artery Pressure Monitoring on Heart Failure Hospitalizations and All-Cause 30-Day Readmissions in Medicare-Eligible Patients With NYHA Class III Heart Failure: Results From the CHAMPION Trial", Circulation. Vol. 130(A16744)
Abstract: Heart failure (HF) is the most frequent discharge diagnosis for hospitalized Medicare beneficiaries. Readmission after a HF hospitalization (HFH) is an important metric for quality of care. Under the Hospital Readmissions Reduction Program (HRRP), hospitals with excess all-cause 30-day readmissions may be penalized for inadequate quality of care. Results from the CHAMPION trial confirmed that HF management using pulmonary artery pressure (PAP) monitoring from an implanted sensor in patients with NYHA Class III HF reduced HFH rates compared to standard management. However, the impact of this strategy on HFH rates and all-cause 30-day readmissions in Medicare-eligible patients is unknown.
BibTeX:
@article{adamson2014impact,
  author = {P.B. Adamson and W.T. Abraham and J. Bauman and J. Yadav},
  title = {Impact of Wireless Pulmonary Artery Pressure Monitoring on Heart Failure Hospitalizations and All-Cause 30-Day Readmissions in Medicare-Eligible Patients With NYHA Class III Heart Failure: Results From the CHAMPION Trial},
  journal = {Circulation},
  year = {2014},
  volume = {130},
  number = {A16744},
  url = {http://circ.ahajournals.org/content/130/Suppl_2/A16744.abstract}
}
Advani P, Reitzel L, Nguyen N, Fisher F, Savoy E, Cuevas A, Wetter D and McNeill L (2014), "Financial strain and cancer risk behaviors among African Americans.", Cancer epidemiology, biomarkers &amp;amp; prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.
Abstract: BACKGROUND: African Americans suffer disproportionately from the adverse consequences of behavioral risk factors for cancer relative to other ethnic groups. Recent studies have assessed how financial strain might uniquely contribute to engagement in modifiable behavioral risk factors for cancer, but not among African Americans. The current study examined associations between financial strain and modifiable cancer risk factors (smoking, at-risk alcohol use, overweight/obesity, insufficient physical activity, inadequate fruit and vegetable intake, and multiple risk factors) among 1,278 African American adults (age, 46.5 ± 12.6 years; 77% female) and explored potential mediators (stress and depressive symptoms) of those associations.
METHODS: Logistic regression models were used to examine associations between financial strain and cancer risk factors. Analyses were adjusted for age, sex, partner status, income, educational level, and employment status. Analyses involving overweight/obesity status additionally controlled for fruit and vegetable intake and physical activity. Nonparametric bootstrapping procedures were used to assess mediation. RESULTS: Greater financial strain was associated with greater odds of insufficient physical activity (P < 0.003) and smoking (P = 0.005) and was positively associated with the total number of cancer risk factors (P < 0.0001). There was a significant indirect effect of both stress and depressive symptoms on the relations of financial strain with physical inactivity and multiple risk factors, respectively. CONCLUSIONS: Future interventions aimed at reducing cancer disparities should focus on African Americans experiencing higher financial strain while addressing their stress and depressive symptoms. IMPACT: Longitudinal studies are needed to assess the temporal and causal relations between financial strain and modifiable behavioral cancer risk factors among African Americans
BibTeX:
@article{advani2014,
  author = {P.S. Advani and LR. Reitzel and N.T. Nguyen and F.D. Fisher and E.J. Savoy and A.G. Cuevas and D.W. Wetter and L.H. McNeill},
  title = {Financial strain and cancer risk behaviors among African Americans.},
  journal = {Cancer epidemiology, biomarkers &amp;amp; prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology},
  year = {2014},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24740200}
}
Agarwal Y, Bishop A, Chan T, Fotjik M, Gupta P, Kahng A, Lai L, Martin P, Srivastava M, Sylvester D, Wanner L and Zhang B (2014), "Redcooper: Hardware sensor enabled variability software testbed for lifetime energy constrained application", Technical Reports, Nanosystems Computer-Aided Design Laboratory, University of California, Los Angeles.
Abstract: Conventional hardware uses overdesigned margins to guardband against variability, which incurs significant amounts of power and performance overhead. If the variations can be captured and exposed to the higher levels (e.g., system/software levels), the margin can be reduced or even eliminated through opportunistic hardware/software adaptation. In this paper, we present our end-to-end implementation of an software testbed with built-in hardware sensors and adaptive software. The measurement results show that using our novel performance sensor, Design-Dependent Ring-Oscillator (DDRO), can reduce the mean delay estimation errors by up to 35% (from 2.5% to 1.5%) compared to using generic inverter-based ring-oscillator. By utilizing the sensing infrastructure on our RedCooper testbed, a demonstration shows that the hardware and software adaptation can achieve up to 2.7X total active time increase for lifetime energy constrained, as compared to sensorless system.
BibTeX:
@article{Agarwal2014,
  author = {Y. Agarwal and A. Bishop and T. Chan and M. Fotjik and P. Gupta and A. Kahng and L. Lai and P. Martin and M.B. Srivastava and D. Sylvester and L. Wanner and B. Zhang},
  title = {Redcooper: Hardware sensor enabled variability software testbed for lifetime energy constrained application},
  journal = {Technical Reports, Nanosystems Computer-Aided Design Laboratory, University of California, Los Angeles},
  year = {2014},
  url = {http://www.escholarship.org/uc/item/1c21g217}
}
al'Absi M, Nakajima M, Dokam A, Sameai A, Alsoofi M, Khalil N and Habori MA (2014), "Concurrent tobacco and khat use is associated with blunted cardiovascular stress response and enhanced negative mood: a cross-sectional investigation", Human Psychophmarmacology. Vol. 29(4), pp. 307-314.
Abstract: Objectives Khat (Catha edulis), an amphetamine-like plant, is widely used in East Africa and the Arabian Peninsula and is becoming a growing problem in other parts of the world. The concurrent use of tobacco and khat is highly prevalent and represents a public health challenge. We examined for the first time associations of the concurrent use of tobacco and khat with psychophysiological responses to acute stress in two sites in Yemen. Methods Participants (N?=?308; 135 women) included three groups: users of khat and tobacco, users of khat alone, and a control group (nonsmokers/nonusers of khat). These individuals completed a laboratory session in which blood pressures (BP), heart rate, and mood measures were assessed during rest and in response to acute stress. Results Concurrent use of khat and tobacco was associated with attenuated systolic BP, diastolic BP, and heart rate responses to laboratory stress (ps?
BibTeX:
@article{alabsi2014,
  author = {M. al'Absi and M. Nakajima and A. Dokam and A. Sameai and M. Alsoofi and N.S. Khalil and M. Al Habori},
  title = {Concurrent tobacco and khat use is associated with blunted cardiovascular stress response and enhanced negative mood: a cross-sectional investigation},
  journal = {Human Psychophmarmacology},
  year = {2014},
  volume = {29},
  number = {4},
  pages = {307-314},
  url = {http://onlinelibrary.wiley.com/doi/10.1002/hup.2403/full}
}
al'Absi M, Lemieux A and Nakajima M (2014), "Peptide YY and ghrelin predict craving and risk for relapse in abstinent smokers", Psychoneuroendocrinology. Vol. 49(0), pp. 253 - 259.
Abstract: Abstract Appetite hormones are directly involved in regulating satiety, energy expenditure, and food intake, and accumulating evidence suggests their involvement in regulating reward and craving for drugs. This study investigated the ability of peptide YY (PYY) and ghrelin during the initial 24–48&#xa0;h of a smoking cessation attempt to predict smoking relapse at 4 weeks. Multiple regression analysis indicated that increased PYY was associated with decreased reported craving and increased positive affect. Cox proportional hazard models showed that higher ghrelin levels predicted increased risk of smoking relapse (hazard ratio&#xa0;=&#xa0;2.06, 95% CI&#xa0;=&#xa0;1.30–3.27). These results indicate that circulating PYY may have buffering effects during the early stages of cessation while ghrelin may confer increased risk of smoking relapse. Further investigation of the links between these hormones and nicotine dependence is warranted.
BibTeX:
@article{alAbsi2014253,
  author = {M. al'Absi and A. Lemieux and M. Nakajima},
  title = {Peptide YY and ghrelin predict craving and risk for relapse in abstinent smokers},
  journal = {Psychoneuroendocrinology},
  year = {2014},
  volume = {49},
  number = {0},
  pages = {253 - 259},
  url = {http://www.sciencedirect.com/science/article/pii/S0306453014002947}
}
Allen S, Allen A, Tosun N, Lunos S, al'Absi M and Hatsukami D (2014), "Smoking- and menstrual-related symptomatology during short-term smoking abstinence by menstrual phase and depressive symptoms", Elsevier Addictive Behaviors. Vol. 39(5), pp. 901-906.
Abstract: Menstrual phase and depressive symptoms are known to minimize quit attempts in women. Therefore, the influence of these factors on smoking- and menstrual-related symptomatology during acute smoking cessation was investigated in a controlled cross-over lab-study. Participants (n = 147) completed two six-day testing weeks during their menstrual cycle with testing order randomly assigned (follicular vs. luteal). The testing week consisted of two days of ad libitum smoking followed by four days of biochemically verified smoking abstinence. Daily symptomatology measures were collected. Out of the 11 total symptoms investigated, six were significantly associated with menstrual phase and nine were significantly associated with level of depressive symptoms. Two significant interactions were noted indicating that there may be a stronger association between depressive symptoms with negative affect and premenstrual pain during the follicular phase compared to the luteal phase. Overall, these observations suggest that during acute smoking abstinence in premenopausal smokers, there is an association between depressive symptoms and symptomatology whereas menstrual phase appears to have less of an effect. Further study is needed to determine the effect of these observations on smoking cessation outcomes, as well as to define the mechanism of menstrual phase and depressive symptoms on smoking-related symptomatology.
BibTeX:
@article{allen2014smoking,
  author = {S.S. Allen and A.M. Allen and N. Tosun and S. Lunos and M. al'Absi and D. Hatsukami},
  title = {Smoking- and menstrual-related symptomatology during short-term smoking abstinence by menstrual phase and depressive symptoms},
  journal = {Elsevier Addictive Behaviors},
  year = {2014},
  volume = {39},
  number = {5},
  pages = {901-906},
  url = {http://www.sciencedirect.com/science/article/pii/S0306460314000318}
}
Almirall D, Nahum-Shani I, Sherwood N and Murphy S (2014), "Introduction to SMART designs for the development of adaptive interventions: with application to weight loss research", Translational Behavioral Medicine. Vol. 4(3), pp. 260-274. Springer.
Abstract: The management of many health disorders often entails a sequential, individualized approach whereby treatment is adapted and readapted over time in response to the specific needs and evolving status of the individual. Adaptive interventions provide one way to operationalize the strategies (e.g., continue, augment, switch, step-down) leading to individualized sequences of treatment. Often, a wide variety of critical questions must be answered when developing a high-quality adaptive intervention. Yet, there is often insufficient empirical evidence or theoretical basis to address these questions. The Sequential Multiple Assignment Randomized Trial (SMART)—a type of research design—was developed explicitly for the purpose of building optimal adaptive interventions by providing answers to such questions. Despite increasing popularity, SMARTs remain relatively new to intervention scientists. This manuscript provides an introduction to adaptive interventions and SMARTs. We discuss SMART design considerations, including common primary and secondary aims. For illustration, we discuss the development of an adaptive intervention for optimizing weight loss among adult individuals who are overweight.
BibTeX:
@article{almirall2014introduction,
  author = {D. Almirall and I. Nahum-Shani and N.E. Sherwood and S.A. Murphy},
  title = {Introduction to SMART designs for the development of adaptive interventions: with application to weight loss research},
  journal = {Translational Behavioral Medicine},
  publisher = {Springer},
  year = {2014},
  volume = {4},
  number = {3},
  pages = {260--274},
  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4167891/pdf/13142_2014_Article_265.pdf}
}
Ash J, Ertin E, Potter L and Zelnio E (2014), "Wide-Angle Synthetic Aperture Radar Imaging: Models and algorithms for anisotropic scattering", Signal Processing Magazine, IEEE., June, 2014. Vol. 31(4), pp. 16-26. IEEE.
Abstract: Advances in radar hardware have enabled the sensing of ever-wider synthesized apertures. In this article, radar video - a sequence of radar images indexed on subaperture - is discussed as a natural, convenient, and revealing representation to capture wide-angle scattering behavior of complex objects. We review the inverse problem of recovering wide-angle scene reflectivity from synthetic aperture radar (SAR) measurements, survey signal processing approaches for its solution, and introduce a novel Bayesian estimation method. Examples from measured and simulated scattering data are presented to illustrate scattering behavior conveniently revealed by the SAR video framework.
BibTeX:
@article{Ash2014,
  author = {J. Ash and E. Ertin and L. Potter and E. Zelnio},
  title = {Wide-Angle Synthetic Aperture Radar Imaging: Models and algorithms for anisotropic scattering},
  journal = {Signal Processing Magazine, IEEE},
  publisher = {IEEE},
  year = {2014},
  volume = {31},
  number = {4},
  pages = {16--26},
  url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6832831}
}
Balani R, Wanner L and Srivastava M (2014), "Distributed programming framework for fast iterative optimization in networked cyber-physical systems", ACM Transactions on Embedded Computing Systems (TECS). Vol. 13(2s), pp. 66. ACM.
Abstract: Large-scale coordination and control problems in cyber-physical systems are often expressed within the networked optimization model. While significant advances have taken place in optimization techniques, their widespread adoption in practical implementations has been impeded by the complexity of internode coordination and lack of programming support for the same. Currently, application developers build their own elaborate coordination mechanisms for synchronized execution and coherent access to shared resources via distributed and concurrent controller processes. However, they typically tend to be error prone and inefficient due to tight constraints on application development time and cost. This is unacceptable in many CPS applications, as it can result in expensive and often irreversible side-effects in the environment due to inaccurate or delayed reaction of the control system. This article explores the design of a distributed shared memory (DSM) architecture that abstracts the details of internode coordination. It simplifies application design by transparently managing routing, messaging, and discovery of nodes for coherent access to shared resources. Our key contribution is the design of provably correct locality-sensitive synchronization mechanisms that exploit the spatial locality inherent in actuation to drive faster and scalable application execution through opportunistic data parallel operation. As a result, applications encoded in the proposed Hotline Application Programming Framework are error free, and in many scenarios, exhibit faster reactions to environmental events over conventional implementations. Relative to our prior work, this article extends Hotline with a new locality-sensitive coordination mechanism for improved reaction times and two tunable iteration control schemes for lower message costs. Our extensive evaluation demonstrates that realistic performance and cost of applications are highly sensitive to the prevalent deployment, network, and environmental characteristics. This highlights the importance of Hotline, which provides user-configurable options to trivially tune these metrics and thus affords time to the developers for implementing, evaluating, and comparing multiple algorithms.
BibTeX:
@article{Balani2014,
  author = {R. Balani and L.F. Wanner and M.B. Srivastava},
  title = {Distributed programming framework for fast iterative optimization in networked cyber-physical systems},
  journal = {ACM Transactions on Embedded Computing Systems (TECS)},
  publisher = {ACM},
  year = {2014},
  volume = {13},
  number = {2s},
  pages = {66},
  url = {http://dl.acm.org/citation.cfm?id=2544386}
}
Baru C, Carey M, Condie T, Hristidis V, Lifka D, Wolski R, Rajan S and Roy A (2014), "Trident: Visioning A Shared Infrastructure For Data Research At Scale", Data Science Symposium. , pp. 20.
Abstract: In this talk, we identify the need for a shared infrastructure for data research at scale, and provide a vision for addressing this need. Scalable data management is a computer science endeavor that is currently enjoying widespread interest and a sizable industry investment. There is a pressing need to establish objective and scientific approaches to big data and data science research by providing a common platform for software experimentation. Such a platform could enable objective benchmarking and comparative analysis of software and algorithmic performance thereby improving the current situation where most researchers work on different computing platforms using different algorithms, different data, and different environmental settings.
BibTeX:
@article{BARU2014,
  author = {C. Baru and M. Carey and T. Condie and V. Hristidis and D. Lifka and R. Wolski and S. Rajan and A. Roy},
  title = {Trident: Visioning A Shared Infrastructure For Data Research At Scale},
  journal = {Data Science Symposium},
  year = {2014},
  pages = {20},
  url = {http://www.nist.gov/itl/iad/upload/proceedings_1-2.pdf}
}
Basole R, Park H, Kumar V, Braunsteain M, Bost J, Chau D and Kahng M (2014), "Bicentric Visualization of Pediatric Asthma Care Process Activities", Proceedings of IEEE VIS 2014 Workshop on Visualization of Electronic Health Records.
BibTeX:
@article{basolebicentric,
  author = {R.C. Basole and H. Park and V. Kumar and M.L. Braunsteain and J. Bost and D.H. Chau and M. Kahng},
  title = {Bicentric Visualization of Pediatric Asthma Care Process Activities},
  journal = {Proceedings of IEEE VIS 2014 Workshop on Visualization of Electronic Health Records},
  year = {2014},
  url = {http://www.cs.umd.edu/hcil/parisehrvis/papers/bicentric_vis.pdf}
}
Batra N, Kelly J, Parson O, Dutta H, Knottenbelt W, Rogers A, Singh A and Srivastava M (2014), "NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring", arXiv.org (preprint arXiv:1404.3878).
Abstract: Non-intrusive load monitoring, or energy disaggregation, aims to separate household energy consumption data collected from a single point of measurement into appliance-level consumption data. In recent years, the field has rapidly expanded due to increased interest as national deployments of smart meters have begun in many countries. However, empirically comparing disaggregation algorithms is currently virtually impossible. This is due to the different data sets used, the lack of reference implementations of these algorithms and the variety of accuracy metrics employed. To address this challenge, we present the Non-intrusive Load Monitoring Toolkit (NILMTK); an open source toolkit designed specifically to enable the comparison of energy disaggregation algorithms in a reproducible manner. This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets. Our toolkit includes parsers for a range of existing data sets, a collection of preprocessing algorithms, a set of statistics for describing data sets, two reference benchmark disaggregation algorithms and a suite of accuracy metrics. We demonstrate the range of reproducible analyses which are made possible by our toolkit, including the analysis of six publicly available data sets and the evaluation of both benchmark disaggregation algorithms across such data sets.
BibTeX:
@article{Batra2014a,
  author = {N. Batra and J. Kelly and O. Parson and H. Dutta and W. Knottenbelt and A. Rogers and A. Singh and M.B. Srivastava},
  title = {NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring},
  journal = {arXiv.org (preprint arXiv:1404.3878)},
  year = {2014},
  url = {http://arxiv.org/abs/1404.3878}
}
Benza R, Raina A, Abraham W, Adamson P, Lindenfeld J, Miller A, Bourge R, Bauman J and Yadav J (2014), "Pulmonary hypertension related to left heart disease: Insight from a wireless implantable hemodynamic monitor", The Journal of Heart and Lung Transplantation. (0), pp. -.
Abstract: Background Pulmonary hypertension (PH) associated with left heart disease (World Health Organization [WHO] Group II) has previously been linked with significant morbidity and mortality. However, there are currently no approved therapies or hemodynamic monitoring systems to improve outcomes in WHO Group II PH. Methods We conducted a retrospective analysis of the CHAMPION trial of an implantable hemodynamic monitor (IHM) in 550 New York Heart Association (NYHA) Functional Class III HF patients, regardless of left ventricular ejection fraction (LVEF) or heart failure (HF) etiology. We evaluated clinical variables, changes in medical therapy, HF hospitalization rates and survival in patients with and without WHO Group II PH. Results Data were obtained for 314 patients (59%) who had WHO Group II PH. Patients without PH were at significantly lower risk for mortality than PH patients (hazard ratio [HR] 0.31, 95% confidence interval [CI] 0.19 to 0.52, p &lt; 0.0001). PH patients had higher HF hospitalization rates than non-PH patients (0.77/year vs 0.37/year; HR 0.49, 95% CI 0.39 to 0.61, p &lt; 0.001). In patients with and without PH, ongoing knowledge of hemodynamic data resulted in a reduction in HF hospitalization for PH patients (HR 0.64, 95% CI 0.51 to 0.81
BibTeX:
@article{Benza2014,
  author = {R.L. Benza and A. Raina and W.T. Abraham and P.B. Adamson and J. Lindenfeld and A.B. Miller and R.C. Bourge and J. Bauman and J. Yadav},
  title = {Pulmonary hypertension related to left heart disease: Insight from a wireless implantable hemodynamic monitor},
  journal = {The Journal of Heart and Lung Transplantation},
  year = {2014},
  number = {0},
  pages = {-},
  url = {http://www.sciencedirect.com/science/article/pii/S1053249814011127}
}
Bhattacharjee T, Rehg J and Kemp C (2014), "Inferring Object Properties from Incidental Contact with a Tactile Sensing Forearm", arXiv.org (preprint arXiv:1409.4972).
Abstract: Whole-arm tactile sensing enables a robot to sense properties of contact across its entire arm. By using this large sensing area, a robot has the potential to acquire useful information from incidental contact that occurs while performing a task. Within this paper, we demonstrate that data-driven methods can be used to infer mechanical properties of objects from incidental contact with a robot's forearm. We collected data from a tactile-sensing forearm as it made contact with various objects during a simple reaching motion. We then used hidden Markov models (HMMs) to infer two object properties (rigid vs. soft and fixed vs. movable) based on low-dimensional features of time-varying tactile sensor data (maximum force, contact area, and contact motion). A key issue is the extent to which data-driven methods can generalize to robot actions that differ from those used during training. To investigate this issue, we developed an idealized mechanical model of a robot with a compliant joint making contact with an object. This model provides intuition for the classification problem. We also conducted tests in which we varied the robot arm's velocity and joint stiffness. We found that, in contrast to our previous methods [1], multivariate HMMs achieved high cross-validation accuracy and successfully generalized what they had learned to new robot motions with distinct velocities and joint stiffnesses.
BibTeX:
@article{Bhattacharjee2014,
  author = {T. Bhattacharjee and J.M. Rehg and C.C. Kemp},
  title = {Inferring Object Properties from Incidental Contact with a Tactile Sensing Forearm},
  journal = {arXiv.org (preprint arXiv:1409.4972)},
  year = {2014},
  url = {http://arxiv.org/abs/1409.4972}
}
Bidwell J, Essa I, Rozga A and Abowd G (2014), "Measuring Child Visual Attention using Markerless Head Tracking from Color and Depth Sensing Cameras", In Proceedings of the 16th International Conference on Multimodal Interaction (ICMI '14). , pp. 447-454.
Abstract: A child's failure to respond to his or her name being called is an early warning sign for autism and response to name is currently assessed as a part of standard autism screening and diagnostic tools. In this paper, we explore markerless child head tracking as an unobtrusive approach for automatically predicting child response to name. Head turns are used as a proxy for visual attention. We analyzed 50 recorded response to name sessions with the goal of predicting if children, ages 15 to 30 months, responded to name calls by turning to look at an examiner within a defined time interval. The child's head turn angles and hand annotated child name call intervals were extracted from each session. Human assisted tracking was employed using an overhead Kinect camera, and automated tracking was later employed using an additional forward facing camera as a proof-of-concept. We explore two distinct analytical approaches for predicting child responses, one relying on rule-based approached and another on random forest classification. In addition, we derive child response latency as a new measurement that could provide researchers and clinicians with finer grain quantitative information currently unavailable in the field due to human limitations. Finally we reflect on steps for adapting our system to work in less constrained natural settings.
BibTeX:
@inproceedings{Bidwell2014,
  author = {J. Bidwell and I.A. Essa and A. Rozga and G.D. Abowd},
  title = {Measuring Child Visual Attention using Markerless Head Tracking from Color and Depth Sensing Cameras},
  booktitle = {Proceedings of the 16th International Conference on Multimodal Interaction (ICMI '14)},
  year = {2014},
  pages = {447--454},
  url = {http://dl.acm.org/citation.cfm?id=2663235}
}
Bisdikian C, Gibson C, Chakraborty S, Srivastava M, Sensoy M and Norman T (2014), "Inference management, trust and obfuscation principles for quality of information in emerging pervasive environments", Pervasive and Mobile Computing. Vol. 11, pp. 168-187. Elsevier.
BibTeX:
@article{Bisdikian2014,
  author = {C. Bisdikian and C. Gibson and S. Chakraborty and M.B. Srivastava and M. Sensoy and T.J. Norman},
  title = {Inference management, trust and obfuscation principles for quality of information in emerging pervasive environments},
  journal = {Pervasive and Mobile Computing},
  publisher = {Elsevier},
  year = {2014},
  volume = {11},
  pages = {168--187},
  url = {http://www.sciencedirect.com/science/article/pii/S1574119213001120}
}
Brennan P, Valdez R, Alexander G, Arora S, Bernstam E, Edmunds M, Kirienko N, Martin R, Sim I, Skiba D and Rosenbloom T (2014), "Patient-centered care, collaboration, communication, and coordination: a report from AMIA's 2013 Policy Meeting", Journal of the American Medical Informatics Association. , pp. amiajnl-2014. BMJ Publishing Group Ltd.
Abstract: n alignment with a major shift toward patient-centered care as the model for improving care in our health system, informatics is transforming patient–provider relationships and overall care delivery. AMIA's 2013 Health Policy Invitational was focused on examining existing challenges surrounding full engagement of the patient and crafting a research agenda and policy framework encouraging the use of informatics solutions to achieve this goal. The group tackled this challenge from educational, technical, and research perspectives. Recommendations include the need for consumer education regarding rights to data access, the need for consumers to access their health information in real time, and further research on effective methods to engage patients. This paper summarizes the meeting as well as the research agenda and policy recommendations prioritized among the invited experts and stakeholders.
BibTeX:
@article{Brennan2014,
  author = {P.F. Brennan and R. Valdez and G. Alexander and S. Arora and E.V. Bernstam and M. Edmunds and N. Kirienko and R.D. Martin and I. Sim and D. Skiba and T. Rosenbloom},
  title = {Patient-centered care, collaboration, communication, and coordination: a report from AMIA's 2013 Policy Meeting},
  journal = {Journal of the American Medical Informatics Association},
  publisher = {BMJ Publishing Group Ltd},
  year = {2014},
  pages = {amiajnl--2014},
  url = {http://jamia.oxfordjournals.org/content/early/2014/11/07/amiajnl-2014-003176}
}
Bu Y, Borkar V, Jia J, Carey M and Condie T (2014), "Pregelix: Big (ger) graph analytics on a dataflow engine", arXiv preprint arXiv:1407.0455.
Abstract: There is a growing need for distributed graph processing systems that are capable of gracefully scaling to very large graph datasets. Unfortunately, this challenge has not been easily met due to the intense memory pressure imposed by process-centric, message passing
designs that many graph processing systems follow. Pregelix is a new open source distributed graph processing system that is based on an iterative dataflow design that is better tuned to handle both in-memory and out-of-core workloads. As such, Pregelix
offers improved performance characteristics and scaling properties over current open source systems (e.g., we have seen up to 15× speedup compared to Apache Giraph and up to 35× speedup compared to distributed GraphLab), and more effective use of available machine resources to support Big(ger) Graph Analytics.
BibTeX:
@article{Bu2014,
  author = {Y. Bu and V. Borkar and J. Jia and M.J. Carey and T. Condie},
  title = {Pregelix: Big (ger) graph analytics on a dataflow engine},
  journal = {arXiv preprint arXiv:1407.0455},
  year = {2014},
  url = {http://www.vldb.org/pvldb/vol8/p161-bu.pdf}
}
Businelle M, Ma P, Kendzor D, Reitzel L, Chen M, Lam C, Bernstein I and Wetter D (2014), "Predicting quit attempts among homeless smokers seeking cessation treatment: an ecological momentary assessment study.", Nicotine &amp; Tobacco Research.. Thesis at: Department of Health Disparities Research, University of Texas MD Anderson Cancer Center, Houston, TX.. Vol. 16(10), pp. 1371-1378.
Abstract: Homeless adults are more likely to smoke tobacco and are less likely to successfully quit smoking than smokers in the general population, despite comparable numbers of cessation attempts and desire to quit. To date, studies that have examined smoking cessation in homeless samples have used traditional lab/clinic-based assessment methodologies. Real-time assessment of key variables may provide new insights into the process of quitting among homeless smokers.The purpose of the current study was to identify predictors of a quit attempt using real-time assessment methodology during the 6 days prior to a scheduled quit attempt among homeless adults seeking care at a shelter-based smoking cessation clinic. Parameters for multiple variables (i.e., motivation for quitting, smoking expectancies, quit self-efficacy, smoking urges, negative affect, positive affect, restlessness, hostility, and stress) were calculated and were used as predictors of biochemically verified quit date abstinence (i.e., ?13hr abstinent) using logistic regression analyses.Participants (n = 57) were predominantly male (59.6%), non-White (68.4%), and smoked an average of 18 cigarettes per day. A total of 1,132 ecological momentary assessments (83% completion rate) were collected at random times (i.e., up to 4 assessments/day) during the 6 days prior to a scheduled quit attempt. Results indicated that declining (negative slope) negative affect, restlessness, and stress predicted quit date abstinence. Additionally, increasing positive coping expectancies across the prequit week predicted quit date abstinence.Study findings highlight multiple variables that may be targeted during the precessation period to increase smoking cessation attempts in this difficult to treat population of smokers.
BibTeX:
@article{Businelle2014,
  author = {M.S. Businelle and P. Ma and D.E. Kendzor and L.R. Reitzel and M. Chen and C.Y. Lam and I. Bernstein and D.W. Wetter},
  title = {Predicting quit attempts among homeless smokers seeking cessation treatment: an ecological momentary assessment study.},
  journal = {Nicotine &amp; Tobacco Research},
  school = {Department of Health Disparities Research, University of Texas MD Anderson Cancer Center, Houston, TX.},
  year = {2014},
  volume = {16},
  number = {10},
  pages = {1371--1378},
  url = {http://dx.doi.org/10.1093/ntr/ntu088}
}
Cano M, Lam C, Chen M, Adams C, Correa-Fernández V, Stewart D, McClure J, Cinciripini P and Wetter D (2014), "Positive smoking outcome expectancies mediate the association between negative affect and smoking urge among women during a quit attempt.", Experiential and Clinical Psychopharmacology. Vol. 22(4), pp. 322-40.
Abstract: Ecological momentary assessment was used to examine associations between negative affect, positive smoking outcome expectancies, and smoking urge during the first 7 days of a smoking quit attempt. Participants were 302 female smokers who enrolled in an individually tailored smoking cessation treatment study. Multilevel mediation analysis was used to examine the temporal relationship among the following: (a) the effects of negative affect and positive smoking outcome expectancies at 1 assessment point (e.g., time j) on smoking urge at the subsequent time point (e.g., time j + 1) in Model 1; and, (b) the effects of negative affect and smoking urge at time j on positive smoking outcome expectancies at time j + 1 in Model 2. The results from Model 1 showed a statistically significant effect of negative affect at time j on smoking urge at time j + 1, and this effect was mediated by positive smoking outcome expectancies at time j, both within- and between-participants. In Model 2, the within-participant indirect effect of negative affect at time j on positive smoking outcome expectancies at time j + 1 through smoking urge at time j was nonsignificant. However, a statistically significant indirect between-participants effect was found in Model 2. The findings support the hypothesis that urge and positive smoking outcome expectancies increase as a function of negative affect, and suggest a stronger effect of expectancies on urge as opposed to the effect of urge on expectancies.
BibTeX:
@article{cano2014positive,
  author = {M.Á. Cano and C.Y. Lam and M. Chen and C.E. Adams and V. Correa-Fernández and D.W. Stewart and J.B. McClure and P.M. Cinciripini and D.W. Wetter},
  title = {Positive smoking outcome expectancies mediate the association between negative affect and smoking urge among women during a quit attempt.},
  journal = {Experiential and Clinical Psychopharmacology},
  year = {2014},
  volume = {22},
  number = {4},
  pages = {322-40},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24796849}
}
Carlson J, Jankowska M, Meseck K, Godbole S, Natarajan L, Raab F, Demchak B, Patrick K and Kerr J (2014), "Validity of PALMS GPS Scoring of Active and Passive Travel Compared to SenseCam.", Medicine &amp; Science in Sports &amp; Exercise.
Abstract: Purpose: The objective of this study is to assess validity of the personal activity location measurement system (PALMS) for deriving time spent walking/running, bicycling, and in vehicle, using SenseCam as the comparison.
Methods: AQ1 Forty adult cyclists wore a Qstarz BT-Q1000XT GPS data logger and SenseCam (camera worn around the neck capturing multiple images every minute) for a mean time of 4 d. PALMS used distance and speed between global positioning system (GPS) points to classify whether each minute was part of a trip (yes/no), and if so, the trip mode (walking/running, bicycling, or in vehicle). SenseCam images were annotated to create the same classifications (i.e., trip yes/no and mode). Contingency tables (2  2) and confusion matrices were calculated at the minute level for PALMS versus SenseCam classifications. Mixed-effects linear regression models estimated agreement (mean differences and intraclass correlation coefficients) between PALMS and SenseCam with regard to minutes/day in each mode.
Results: Minute-level sensitivity, specificity, and negative predictive value were Q88%, and positive predictive value was Q75% for non–mode-specific trip detection. Seventy-two percent to 80% of outdoor walking/running minutes, 73% of bicycling minutes, and 74%–76% of in-vehicle minutes were correctly classified by PALMS. For minutes/day, PALMS had a mean bias (i.e., amount of over or under estimation) of 2.4–3.1 min (11%–15%) for walking/running, 2.3–2.9 min (7%–9%) for bicycling, and 4.3–5 min (15%–17%) for vehicle time. Intraclass correlation coefficients were Q0.80 for all modes.
Conclusions: PALMS has validity for processing GPS data to objectively measure time spent walking/running, bicycling, and in vehicle in population studies. Assessing travel patterns is one of many valuable applications of GPS in physical activity research that can improve our understanding of the determinants and health outcomes of active transportation as well as its effect on physical activity.
BibTeX:
@article{Carlson2014,
  author = {J.A. Carlson and M.M. Jankowska and K. Meseck and S. Godbole and L. Natarajan and F. Raab and B. Demchak and K. Patrick and J. Kerr},
  title = {Validity of PALMS GPS Scoring of Active and Passive Travel Compared to SenseCam.},
  journal = {Medicine &amp; Science in Sports &amp; Exercise},
  year = {2014},
  url = {http://www.researchgate.net/publication/263814943_Validity_of_PALMS_GPS_Scoring_of_Active_and_Passive_Travel_Compared_to_SenseCam}
}
Chakraborty S, Shen C, Raghavan KR, Shoukry Y, Millar M and Srivastava M (2014), "ipShield: A Framework for Enforcing Context-aware Privacy", In Proceedings of the 11th USENIX Conference on Networked Systems Design and Implementation. Berkeley, CA, USA , pp. 143-156. USENIX Association.
Abstract: Smart phones are used to collect and share personal data with untrustworthy third-party apps, often leading to data misuse and privacy violations. Unfortunately, state-of-the-art privacy mechanisms on Android provide inadequate access control and do not address the vulnerabilities that arise due to unmediated access to so-called innocuous sensors on these phones. We present ipShield, a framework that provides users with greater control over their resources at runtime. ipShield performs monitoring of every sensor accessed by an app and uses this information to perform privacy risk assessment. The risks are conveyed to the user as a list of possible inferences that can be drawn using the shared sensor data. Based on user-configured lists of allowed and private inferences, a recommendation consisting of binary privacy actions on individual sensors is generated. Finally, users are provided with options to override the recommended actions and manually configure context-aware fine-grained privacy rules. We implemented ipShield by modifying the AOSP on a Nexus 4 phone. Our evaluation indicates that running ipShield incurs negligible CPU and memory overhead and only a small reduction in battery life.
BibTeX:
@inproceedings{Chakraborty:2014:IFE:2616448.2616463,
  author = {Chakraborty, Supriyo and Shen, Chenguang and Raghavan, Kasturi Rangan and Shoukry, Yasser and Millar, Matt and Srivastava, Mani},
  title = {ipShield: A Framework for Enforcing Context-aware Privacy},
  booktitle = {Proceedings of the 11th USENIX Conference on Networked Systems Design and Implementation},
  publisher = {USENIX Association},
  year = {2014},
  pages = {143--156},
  url = {http://dl.acm.org/citation.cfm?id=2616448.2616463}
}
Chakraborty B and Murphy S (2014), "Dynamic treatment regimes", Annual Review of Statistics and Its Application. Vol. 1, pp. 447-464. NIH Public Access.
Abstract: A dynamic treatment regime consists of a sequence of decision rules, one per stage of intervention, that dictate how to individualize treatments to patients based on evolving treatment and covariate history. These regimes are particularly useful for managing chronic disorders, and fit well into the larger paradigm of personalized medicine. They provide one way to operationalize a clinical decision support system. Statistics plays a key role in the construction of evidence-based dynamic treatment regimes – informing best study design as well as efficient estimation and valid inference. Due to the many novel methodological challenges it offers, this area has been growing in popularity among statisticians in recent years. In this article, we review the key developments in this exciting field of research. In particular, we discuss the sequential multiple assignment randomized trial designs, estimation techniques like Q-learning and marginal structural models, and several inference techniques designed to address the associated non-standard asymptotics. We reference software, whenever available. We also outline some important future directions.
BibTeX:
@article{chakraborty2014dynamic,
  author = {B. Chakraborty and S.A. Murphy},
  title = {Dynamic treatment regimes},
  journal = {Annual Review of Statistics and Its Application},
  publisher = {NIH Public Access},
  year = {2014},
  volume = {1},
  pages = {447-464},
  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4231831/}
}
Chau D (2014), "HCI meets data mining: principles and tools for big data analytics", In 32nd annual ACM Conference on Human Factors in Computing Systems (CHI 2014). , pp. 1039-1040.
BibTeX:
@inproceedings{Chau2014,
  author = {D.H. Chau},
  title = {HCI meets data mining: principles and tools for big data analytics},
  booktitle = {32nd annual ACM Conference on Human Factors in Computing Systems (CHI 2014)},
  year = {2014},
  pages = {1039--1040},
  url = {http://www.cs.cmu.edu/ dchau/thesis/polo_thesis.pdf}
}
Chen Y, Lin Z, Pienta R, Kahng M and Chau D (2014), "Towards scalable graph computation on mobile devices", In 2014 IEEE International Conference on Big Data (Big Data),. , pp. 29-35.
Abstract: Mobile devices have become increasingly central to our everyday activities, due to their portability, multi-touch capabilities, and ever-improving computational power. Such attractive
features have spurred research interest in leveraging mobile devices for computation. We explore a novel approach that aims to use a single mobile device to perform scalable
graph computation on large graphs that do not fit in the device’s limited main memory, opening up the possibility of performing on-device analysis of large datasets, without relying
on the cloud. Based on the familiar memory mapping capability provided by today’s mobile operating systems, our approach to scale up computation is powerful and intentionally kept simple to maximize its applicability across the iOS and Android platforms. Our experiments demonstrate that an iPad mini can perform fast computation on large real graphs with as many as 272 million edges (Google+ social graph), at a speed that is only a few times
slower than a 13” Macbook Pro. Through creating a real world iOS app with this technique, we demonstrate the strong potential application for scalable graph computation on a single mobile device using our approach.
BibTeX:
@inproceedings{Chen2014,
  author = {Y. Chen and Z. Lin and R. Pienta and M. Kahng and D.H. Chau},
  title = {Towards scalable graph computation on mobile devices},
  booktitle = {2014 IEEE International Conference on Big Data (Big Data),},
  year = {2014},
  pages = {29--35},
  url = {http://www.cc.gatech.edu/ dchau/papers/14-bigdata-mobile-mmap.pdf}
}
Ciptadi A, Goodwin M and Rehg J (2014), "Movement Pattern Histogram for Action Recognition and Retrieval", In 2014 European Conference on Computer Vision (ECCV 2014). , pp. 695-710. Springer International Publishing.
Abstract: We present a novel action representation based on encoding the global temporal movement of an action. We represent an action as a set of movement pattern histograms that encode the global temporal dynamics of an action. Our key observation is that temporal dynamics of an action are robust to variations in appearance and viewpoint changes, making it useful for action recognition and retrieval. We pose the problem of computing similarity between action representations as a maximum matching problem in a bipartite graph. We demonstrate
the effectiveness of our method for cross-view action recognition on the IXMAS dataset. We also show how our representation complements existing bag-of-features representations on the UCF50 dataset. Finally we show the power of our representation for action retrieval on a new real-world dataset containing repetitive motor movements emitted by children with autism in an unconstrained classroom setting.
BibTeX:
@incollection{Ciptadi2014,
  author = {A. Ciptadi and M.S. Goodwin and J.M. Rehg},
  title = {Movement Pattern Histogram for Action Recognition and Retrieval},
  booktitle = {2014 European Conference on Computer Vision (ECCV 2014)},
  publisher = {Springer International Publishing},
  year = {2014},
  pages = {695--710},
  url = {http://www.cc.gatech.edu/ aciptadi/ciptadi-eccv2014.pdf}
}
Collins L, Nahum-Shani I and Almirall D (2014), "Optimization of behavioral dynamic treatment regimens based on the sequential, multiple assignment, randomized trial (SMART)", Clinical Trials. Vol. 11(4), pp. 426-434. SAGE Publications.
Abstract: A behavioral intervention is a program aimed at modifying behavior for the purpose of treating or preventing disease, promoting health, and/or enhancing well-being. Many behavioral interventions are dynamic treatment regimens, that is, sequential, individualized multicomponent interventions in which the intensity and/or type of treatment is varied in response to the needs and progress of the individual participant. The multiphase optimization strategy (MOST) is a comprehensive framework for development, optimization, and evaluation of behavioral interventions, including dynamic treatment regimens. The objective of optimization is to make dynamic treatment regimens more effective, efficient, scalable, and sustainable. An important tool for optimization of dynamic treatment regimens is the sequential, multiple assignment, randomized trial (SMART). The purpose of this article is to discuss how to develop optimized dynamic treatment regimens within the MOST framework. Methods and results The article discusses the preparation, optimization, and evaluation phases of MOST. It is shown how MOST can be used to develop a dynamic treatment regimen to meet a prespecified optimization criterion. The SMART is an efficient experimental design for gathering the information needed to optimize a dynamic treatment regimen within MOST. One signature feature of the SMART is that randomization takes place at more than one point in time. Conclusion MOST and SMART can be used to develop optimized dynamic treatment regimens that will have a greater public health impact.
BibTeX:
@article{Collins2014,
  author = {L.M. Collins and I. Nahum-Shani and D. Almirall},
  title = {Optimization of behavioral dynamic treatment regimens based on the sequential, multiple assignment, randomized trial (SMART)},
  journal = {Clinical Trials},
  publisher = {SAGE Publications},
  year = {2014},
  volume = {11},
  number = {4},
  pages = {426-434},
  url = {http://ctj.sagepub.com/content/11/4/426.long}
}
Conroy D, Yang C and Maher J (2014), "Behavior Change Techniques in Top-Ranked Mobile Apps for Physical Activity", American journal of preventive medicine. Vol. 46(6), pp. 649-652. Elsevier.
Abstract: Background: Mobile applications (apps) have potential for helping people increase their physical activity, but little is known about the behavior change techniques marketed in these apps.
Purpose: The aim of this study was to characterize the behavior change techniques represented in online descriptions of top-ranked apps for physical activity.
Methods: Top-ranked apps (n¼167) were identified on August 28, 2013, and coded using the
Coventry, Aberdeen and London–Revised (CALO-RE) taxonomy of behavior change techniques during the following month. Analyses were conducted during 2013.
Results: Most descriptions of apps incorporated fewer than four behavior change techniques. The most common techniques involved providing instruction on how to perform exercises, modeling how to perform exercises, providing feedback on performance, goal-setting for physical activity, and planning social support/change. A latent class analysis revealed the existence of two types of apps, educational and motivational, based on their configurations of behavior change techniques.
Conclusions: Behavior change techniques are not widely marketed in contemporary physical
activity apps. Based on the available descriptions and functions of the observed techniques in
contemporary health behavior theories, people may need multiple apps to initiate and maintain behavior change. This audit provides a starting point for scientists, developers, clinicians, and consumers to evaluate and enhance apps in this market.
BibTeX:
@article{Conroy2014,
  author = {D.E. Conroy and C. Yang and J.P. Maher},
  title = {Behavior Change Techniques in Top-Ranked Mobile Apps for Physical Activity},
  journal = {American journal of preventive medicine},
  publisher = {Elsevier},
  year = {2014},
  volume = {46},
  number = {6},
  pages = {649--652},
  url = {http://www.ajpmonline.org/pb/assets/raw/Health%20Advance/journals/amepre/AMEPRE_4004_Embargo.pdf}
}
Dallery J, Riley W and Nahum-Shani I (2014), "Research designs to develop and evaluate technology-based health behavior interventions", Behavioral Health Care and Technology: Using Science-Based Innovations to Transform Practice., In Behavioral Healthcare and Technology. , pp. 168. Oxford University Press.
BibTeX:
@incollection{Dallery2014,
  author = {J. Dallery and W.T. Riley and I. Nahum-Shani},
  editor = {L. Marsch and S. Lord and J. Dallery},
  title = {Research designs to develop and evaluate technology-based health behavior interventions},
  booktitle = {Behavioral Healthcare and Technology},
  journal = {Behavioral Health Care and Technology: Using Science-Based Innovations to Transform Practice},
  publisher = {Oxford University Press},
  year = {2014},
  pages = {168}
}
DePasse J, Sawyer A, Chen C, Jethwani K and Sim I (2014), "Academic Medical Centers as Digital Health Catalysts", Elsevier Healthcare. Vol. 2(3), pp. 173-176.
Abstract: Emerging digital technologies offer enormous potential to improve quality, reduce cost, and increase patient-centeredness in healthcare. Academic Medical Centers (AMCs) play a key role in advancing medical care through cutting-edge medical research, yet traditional models for invention, validation and commercialization at AMCs have been designed around biomedical initiatives, and are less well suited for new digital health technologies. Recently, two large bi-coastal Academic Medical Centers, the University of California, San Francisco (UCSF) through the Center for Digital Health Innovation (CDHI) and Partners Healthcare through the Center for Connected Health (CCH) have launched centers focused on digital health innovation. These centers show great promise but are also subject to significant financial, organizational, and visionary challenges. We explore these AMC initiatives, which share the following characteristics: a focus on academic research methodology; integration of digital technology in educational programming; evolving models to support “clinician innovators”; strategic academic–industry collaboration and emergence of novel revenue models.
BibTeX:
@article{DePasse2014173,
  author = {J.W. DePasse and A. Sawyer and C.E. Chen and K. Jethwani and I. Sim},
  title = {Academic Medical Centers as Digital Health Catalysts},
  journal = {Elsevier Healthcare},
  year = {2014},
  volume = {2},
  number = {3},
  pages = {173-176},
  url = {http://www.sciencedirect.com/science/article/pii/S2213076414000554}
}
Elmalaki S, Gottscho M, Gupta P and Srivastava M (2014), "A case for battery charging-aware power management and deferrable task scheduling in smartphones", In Proceedings of the 6th USENIX conference on Power-Aware Computing and Systems. Broomfield, CO , pp. 4-4.
Abstract: Prior battery-aware systems research has focused on discharge power management in order to maximize the usable battery lifetime of a device. In order to achieve the vision of perpetual mobile device operation, we propose that software also needs to carefully consider the process of battery charging. This is because the power consumed by the system when plugged in can influence the rate of battery charging, and hence, the availability of the system to the user. We characterize the charging process of a Nexus 4 smartphone and analyze the charging behaviors of anonymous Nexus 4 users using the Device Analyzer dataset. We find that there is potential for software schedulers to increase device availability by distributing tasks across the charging period. We estimate that approximately 53% of the users we examined could benefit from up to 18.9% improvement in net energy gained by the battery while charging. Accordingly, we propose new threads of research in charging-aware power management and deferrable task scheduling that could improve overall availability for a significant portion of smartphone users.
BibTeX:
@inproceedings{Elmalaki2014,
  author = {S. Elmalaki and M. Gottscho and P. Gupta and M.B. Srivastava},
  title = {A case for battery charging-aware power management and deferrable task scheduling in smartphones},
  booktitle = {Proceedings of the 6th USENIX conference on Power-Aware Computing and Systems},
  year = {2014},
  pages = {4--4},
  url = {https://www.usenix.org/conference/hotpower14/workshop-program/presentation/elmalaki}
}
Ertin E (2014), "Three-Dimensional Imaging of Vehicles from Sparse Apertures in Urban Environment", Compressive Sensing for Urban Radar., In Compressive Sensing for Urban Radar. , pp. 361. CRC Press.
Abstract: Three-dimensional synthetic aperture radar (SAR) imaging of vehicles in urban setting are made possible by new data collection capabilities, in which airborne radar systems interrogate a large scene persistently and over a large range of aspect angles. Wide-angle 3-D reconstructions of vehicles can be useful in applications such as automatic target recognition (ATR) and fingerprinting. The backscatter data collected by the airborne platform at each pulse can be interpreted as 1-D lines of the 3-D Fourier transform of the scene, and the aggregation of radar returns over the flight path defines a conical manifold of data in the scenes 3-D Fourier domain. Generating high-resolution 3-D images using traditional Fourier processing methods requires that radar data be collected over a densely sampled set of points in both azimuth and elevation angle. This method of imaging requires very large collection times and storage requirements and may be prohibitively costly in practice. There is thus moti- vation to consider more sparsely sampled data collection strategies, where only a small fraction of the data required to perform traditional high-resolution imaging is collected. In this chapter, we review several techniques that have been proposed for 3-D reconstruction data collected from sparsely apertures, as well as discuss new approaches based on dictionary learning of target primitives. Particular emphasis is given sparsity regularized least squares approaches to wide-angle 3-D radar reconstruction for arbitrary, sparse apertures. We provide comprehensive set of comparative results using data from the GOTCHA data collection campaign.
BibTeX:
@incollection{Ertin2014,
  author = {E. Ertin},
  title = {Three-Dimensional Imaging of Vehicles from Sparse Apertures in Urban Environment},
  booktitle = {Compressive Sensing for Urban Radar},
  journal = {Compressive Sensing for Urban Radar},
  publisher = {CRC Press},
  year = {2014},
  pages = {361},
  url = {http://www2.ece.ohio-state.edu/ ertine/Ertin2014b.pdf}
}
Estrin D (2014), "small data, where n= me", Communications of the ACM. Vol. 57(4), pp. 32-34. ACM.
BibTeX:
@article{Estrin2014,
  author = {D. Estrin},
  title = {small data, where n= me},
  journal = {Communications of the ACM},
  publisher = {ACM},
  year = {2014},
  volume = {57},
  number = {4},
  pages = {32--34},
  url = {http://cacm.acm.org/magazines/2014/4/173218-small-data-where-n-me/fulltext}
}
Fitzsimmons P, Maher J, Doerksen S, Elavsky S, Rebar A and Conroy D (2014), "A daily process analysis of physical activity, sedentary behavior, and perceived cognitive abilities", Psychology of Sport and Exercise. Vol. 15(5), pp. 498-504. Elsevier.
Abstract: Objectives
This study evaluated the role of both physical activity and sedentary behavior in daily perceptions of cognitive abilities and whether these relations exist within-person, between-person, or both.

Design
Non-experimental, intensive longitudinal research using ecological momentary assessments.

Method
College students wore accelerometers and provided end-of-day reports on physical activity, sedentary behavior, and perceived cognitive abilities for 14 days.

Results
Across self-reports and objective measures of behavior, daily deviations in physical activity were positively associated with perceived cognitive abilities. Daily deviations in self-reported, but not objectively-assessed, sedentary behavior also were negatively associated with perceived cognitive abilities. Contrary to previous research, overall levels of physical activity and sedentary behaviors were not associated with perceived cognitive abilities.

Conclusions
These findings indicate that physical activity has a within- rather than between-person association with perceived cognitive abilities although between-person associations effects may require longer monitoring periods to manifest. Further research is needed to establish the direction of causality and resolve whether the nature (rather than quantity) of sedentary activities influences cognition.
BibTeX:
@article{Fitzsimmons2014,
  author = {P.T. Fitzsimmons and J.P. Maher and S.E. Doerksen and S. Elavsky and A.L. Rebar and D.E. Conroy},
  title = {A daily process analysis of physical activity, sedentary behavior, and perceived cognitive abilities},
  journal = {Psychology of Sport and Exercise},
  publisher = {Elsevier},
  year = {2014},
  volume = {15},
  number = {5},
  pages = {498--504},
  url = {http://www.sciencedirect.com/science/article/pii/S1469029214000557}
}
Hernandez J, Riobo J, Rozga A, Abowd G and Picard R (2014), "Using electrodermal activity to recognize ease of engagement in children during social interactions", In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014). , pp. 307-317.
Abstract: The recent emergence of comfortable wearable sensors has focused almost entirely on monitoring physical activity, ignoring opportunities to monitor more subtle phenomena,
such as the quality of social interactions. We argue that it is compelling to address whether physiological sensors can shed light on quality of social interactive behavior. This work leverages the use of a wearable electrodermal activity (EDA) sensor to recognize ease of engagement of children during a social interaction with an adult. In particular, we monitored 51 child-adult dyads in a semistructured play interaction and used Support Vector Machines to automatically identify children who had been rated by the adult as more or less difficult to engage. We report on the classification value of several features extracted from the child's EDA responses, as well as several other features capturing the physiological synchrony
between the child and the adult.
BibTeX:
@inproceedings{Hernandez2014,
  author = {J. Hernandez and J. Riobo and A. Rozga and G.D. Abowd and R.W. Picard},
  title = {Using electrodermal activity to recognize ease of engagement in children during social interactions},
  booktitle = {Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2014)},
  year = {2014},
  pages = {307--317},
  url = {http://dl.acm.org/citation.cfm?id=2636065}
}
Heron K, Smyth S, Conroy D, Sciamanna C and Rovniak L (2014), "The Development And Evaluation Of A Mobile Real-Time Physical Activity Intervention", In Annals of Behavioral Medicine. Vol. 47, pp. S53-S53. Springer, 233 Spring St., New York, NY 10013 USA.
BibTeX:
@incollection{Heron2014,
  author = {K. Heron and S. Smyth and D.E. Conroy and C. Sciamanna and L. Rovniak},
  title = {The Development And Evaluation Of A Mobile Real-Time Physical Activity Intervention},
  booktitle = {Annals of Behavioral Medicine},
  publisher = {Springer, 233 Spring St., New York, NY 10013 USA},
  year = {2014},
  volume = {47},
  pages = {S53--S53}
}
Hnat T (2014), "Macroprogramming: Lowering the Entry Barrier for Wireless Embedded Network Systems", Wireless Sensor Networks. Vol. 8354, pp. 166-181. Springer.
Abstract: Accurate energy expenditure monitoring will be an essential part of medical diagnosis in the future, enabling individually-tailored just-in-time interventions. However, there are currently no real-time monitors that are practical for continuous daily use. In this paper, we introduce the K-Sense energy expenditure monitor that uses inertial measurement units (IMUs) mounted to an individual’s wrist and ankle with elastic bands to determine angular velocity and position. The system utilizes kinematics to determine the amount of energy required for each limb to achieve its current movement. Our empirical evaluation includes over 3,000,000 individual data samples across 12 individuals and the results indicate that the system can estimate total energy expenditure with a 92 percent accuracy on average.
BibTeX:
@article{Hnata,
  author = {T.W. Hnat},
  title = {Macroprogramming: Lowering the Entry Barrier for Wireless Embedded Network Systems},
  journal = {Wireless Sensor Networks},
  publisher = {Springer},
  year = {2014},
  volume = {8354},
  pages = {166-181},
  url = {http://link.springer.com/chapter/10.1007/978-3-319-04651-8_11}
}
Ho B and Srivastava M (2014), "Poster: M-Seven: monitoring smoking event by considering time sequence information via iPhone M7 API", In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14). , pp. 372-372.
Abstract: Smartphones are equipped with various sensors that provide rich context information. By leveraging these sensors, several interesting and practical applications have emerged.
Accelerometer data has been used, for example, to detect transportation, exercise activities, etc. A typical approach is to classify activity directly based on features extracted
from raw sensing data. Cheng et. al. implemented a different approach by using two-stage classification: the system first detects several sub-behaviors, and uses the combination
of attributes to infer higher-level behaviors. Built upon this approach, we focus on exploring the time sequence of activities, which is an underexplored, yet natural and information-rich indicator. In this work, we explore this time sequence concept through detection of smoking events.
BibTeX:
@inproceedings{Ho2014,
  author = {B. Ho and M.B. Srivastava},
  title = {Poster: M-Seven: monitoring smoking event by considering time sequence information via iPhone M7 API},
  booktitle = {Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14)},
  year = {2014},
  pages = {372--372},
  url = {http://dl.acm.org/citation.cfm?id=2594368.2601451}
}
Hossain S, Ali A, Rahman M, Ertin E, Epstein D, Kennedy A, Preston K, Umbricht A, Chen Y and Kumar S (2014), "Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity.", Proceedings of the 13th ACM/IEE Conference on Information Processing in Sensor Networks.. Thesis at: Dept of Computer Science and Engg., Washington University in St. Louise.. Vol. 2014, pp. 71-82.
Abstract: A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the natural free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably in the natural field environment. In this paper, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detecting drug use events in the field is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collect 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We develop a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We develop efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then apply our model on the recovery segments from these windows. Our model achieves 100% true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data.
BibTeX:
@article{Hossain2014a,
  author = {S.M. Hossain and A.A. Ali and M.M. Rahman and E. Ertin and D. Epstein and A. Kennedy and K. Preston and A. Umbricht and Y. Chen and S. Kumar},
  title = {Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity.},
  journal = {Proceedings of the 13th ACM/IEE Conference on Information Processing in Sensor Networks},
  school = {Dept of Computer Science and Engg., Washington University in St. Louise.},
  year = {2014},
  volume = {2014},
  pages = {71--82},
  url = {http://dl.acm.org/ft_gateway.cfm?id=2602348&amp;ftid=1444466&amp;dwn=1&amp;CFID=494348324&amp;CFTOKEN=58863845}
}
Hu P, Zhang P and Ganesan D (2014), "Leveraging interleaved signal edges for concurrent backscatter", In Proceedings of the 1st ACM workshop on Hot topics in wireless. , pp. 13-18.
Abstract: One of the central challenges in backscatter is how to enable concurrent transmissions. Most backscatter protocols operate in a sequential TDMA-like manner due to the fact that most nodes cannot overhear each other’s transmissions, which is detrimental for throughout and energy consumption. Recent e↵orts to separate concurrent signals by inverting a system of linear equations is also problematic due to varying channel coe"cients caused by system and environmental dynamics. In this paper, we introduce BST, a novel physical layer for backscatter communication that enables concurrent transmission by leveraging intra-bit multiplexing of OOK signals from multiple tags. The key idea underlying BST is that the reader can sample at considerably higher rates than the tags, hence it can extract time-domain signal edges that result from interleaved transmissions of several tags. Our preliminary experiment results show that BST can achieve 5⇥ the throughput of Buzz and 10⇥ the throughput of TDMA-based solutions, such as EPC Gen 2.
BibTeX:
@inproceedings{Hu2014,
  author = {P. Hu and P. Zhang and D. Ganesan},
  title = {Leveraging interleaved signal edges for concurrent backscatter},
  booktitle = {Proceedings of the 1st ACM workshop on Hot topics in wireless},
  year = {2014},
  pages = {13--18},
  url = {http://dl.acm.org/citation.cfm?id=2643617}
}
Jakicic J, Sox H, Blair S, Bensink M, Johnson W, King A, Lee I, Nahum-Shani I, Sallis J, Sallis R, Craft L, Whitehead J and Ainsworth B (2014), "Comparative Effectiveness Research: A Roadmap for Physical Activity and Lifestyle.", Medicine &amp; Science in Sports &amp; Exercise.. Thesis at: 1University of Pittsburgh, Pittsburgh, PA; 2Dartmouth College, Hanover, NH; 3University of South Carolina, Columbia, SC; 4Fred Hutchinson Cancer Research Center, Seattle, WA; 5Arizona State University.
Abstract: Comparative Effectiveness Research (CER) is designed to support informed decision making at both the individual, population, and policy levels. The American College of Sports Medicine and partners convened a conference with the focus of building an agenda for CER within the context of physical activity and non-pharmacological lifestyle approaches in the prevention and treatment of chronic disease. This report summarizes the conference content and consensus recommendations that culminated in a CER Roadmap for Physical Activity and Lifestyle approaches to reducing the risk of chronic disease.This conference focused on presentations and discussion around the following topic areas: 1) defining CER, 2) identifying the current funding climate to support CER, 3) summarizing methods for conducting CER, and 4) identifying CER opportunities for physical activity.This conference resulted in consensus recommendations to adopt a CER Roadmap for Physical Activity and Lifestyle approaches to reducing the risk of chronic disease. In general, this roadmap provides a systematic framework by which CER for physical activity can move from a planning phase, to a phase of engagement in CER related to lifestyle factors with particular emphasis on physical activity, to a societal change phase that results in changes in policy, practice, and health.It is recommended that physical activity researchers and healthcare providers use the roadmap developed from this conference as a method to systematically engage in and apply CER to the promotion of physical activity as a key lifestyle behavior that can be effective at impacting a variety of health-related outcomes.
BibTeX:
@article{Jakicic2014,
  author = {J.M. Jakicic and H. Sox and S.N. Blair and M. Bensink and W.G. Johnson and A.C. King and I. Lee and I. Nahum-Shani and J.F. Sallis and R.E. Sallis and L. Craft and J.R. Whitehead and B.E. Ainsworth},
  title = {Comparative Effectiveness Research: A Roadmap for Physical Activity and Lifestyle.},
  journal = {Medicine &amp; Science in Sports &amp; Exercise},
  school = {1University of Pittsburgh, Pittsburgh, PA; 2Dartmouth College, Hanover, NH; 3University of South Carolina, Columbia, SC; 4Fred Hutchinson Cancer Research Center, Seattle, WA; 5Arizona State University},
  year = {2014},
  url = {http://dx.doi.org/10.1249/MSS.0000000000000590}
}
Kang U, Akoglu L and Chau D (2014), "Big Graph Mining for the Web and Social Media: Algorithms, Anomaly Detection, and Applications", In Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York, New York, USA , pp. 677-678. ACM.
Abstract: Graphs are everywhere: social networks, computer net- works, mobile call networks, the World Wide Web, protein interaction networks, and many more. The lower cost of disk storage, the success of social networking websites and Web 2.0 applications, and the high availability of data sources lead to graphs being generated at unprecedented size. They are now measured in terabytes or even petabytes, with more than billions of nodes and edges. Finding patterns on large graphs have a lot of applica- tions including cyber security on the Web, social media min- ing (Facebook, Twitter), and fraud detection, among others. This tutorial will cover topics related to finding patterns and anomalies and sensemaking in large-scale graphs with appli- cations to real-world problems in social media and the Web. Specifically, we aim to answer the following questions: How can we scale up graph mining algorithms for massive graphs with billions of edges? How can we find anomalies in such large-scale graphs? How can we make sense of disk-resident large graphs, what and how can we do visual analytics? How can we use the algorithms and anomaly detection techniques to solve challenging real-world problems that play key role in social media and the Web? Our tutorial consists of three main parts. We start with scalable graph mining algorithms for billion-scale graphs, in- cluding structure analysis, eigensolvers, storage and index- ing, and graph layout and graph compression. Next we de- scribe anomaly detection techniques for large scale graphs with applications on social media. Finally, we discuss vi- sual analytics techniques which leverage these algorithms and anomaly detection techniques in the previous parts.
BibTeX:
@inproceedings{Kang:2014:BGM:2556195.2556198,
  author = {U. Kang and L. Akoglu and D.H. Chau},
  title = {Big Graph Mining for the Web and Social Media: Algorithms, Anomaly Detection, and Applications},
  booktitle = {Proceedings of the 7th ACM International Conference on Web Search and Data Mining},
  publisher = {ACM},
  year = {2014},
  pages = {677--678},
  url = {http://doi.acm.org/10.1145/2556195.2556198}
}
Kang J, Ciecierski C, Malin E, Carroll A, Gidea M, Craft L, Spring B and Hitsman B (2014), "A latent class analysis of cancer risk behaviors among U.S. college students", Elsevier Preventive Medicine. Vol. 64, pp. 121-126.
Abstract: Objective The purpose of this study is to understand how cancer risk behaviors cluster in U.S. college students and vary by race and ethnicity. Methods Using the fall 2010 wave of the National College Health Assessment (NCHA), we conducted a latent class analysis (LCA) to evaluate the clustering of cancer risk behaviors/conditions: tobacco use, physical inactivity, unhealthy diet, alcohol binge drinking, and overweight/obesity. The identified clusters were then examined separately by students' self-reported race and ethnicity. Results Among 30,093 college students surveyed, results show a high prevalence of unhealthy diet as defined by insufficient fruit and vegetable intake (> 95%) and physical inactivity (> 60%). The LCA identified behavioral clustering for the entire sample and distinct clustering among Black and American Indian students. Conclusions Cancer risk behaviors/conditions appear to cluster among college students differentially by race. Understanding how risk behaviors cluster in young adults can lend insight to racial disparities in cancer through adulthood. Health behavior interventions focused on modifying multiple risk behaviors and tailored to students' racial group could potentially have a much larger effect on cancer prevention than those targeting any single behavior.
BibTeX:
@article{Kang2014a,
  author = {J. Kang and C.C. Ciecierski and E.L. Malin and A.J. Carroll and M. Gidea and L.L. Craft and B. Spring and B. Hitsman},
  title = {A latent class analysis of cancer risk behaviors among U.S. college students},
  journal = {Elsevier Preventive Medicine},
  year = {2014},
  volume = {64},
  pages = {121-126},
  url = {http://www.sciencedirect.com/science/article/pii/S0091743514001170}
}
Kilbourne A, Almirall D, Eisenberg D, Waxmonsky J, Goodrich D, Fortney J, Kirchner J, Solberg L, Main D, Bauer M, Kyle J, Murphy S, Nord J and Thomas M (2014), "Protocol: Adaptive Implementation of Effective Programs Trial (ADEPT): cluster randomized SMART trial comparing a standard versus enhanced implementation strategy to improve outcomes of a mood disorders program", Implementation Science. Vol. 9(1), pp. 132. BioMed Central Ltd.
Abstract: Background: Despite the availability of psychosocial evidence-based practices (EBPs), treatment and outcomes for persons with mental disorders remain suboptimal. Replicating Effective Programs (REP), an effective implementation strategy, still resulted in less than half of sites using an EBP. The primary aim of this cluster randomized trial is to determine, among sites not initially responding to REP, the effect of adaptive implementation strategies that begin with an External Facilitator (EF) or with an External Facilitator plus an Internal Facilitator (IF) on improved EBP use and patient outcomes in 12 months. Methods/Design: This study employs a sequential multiple assignment randomized trial (SMART) design to build an adaptive implementation strategy. The EBP to be implemented is life goals (LG) for patients with mood disorders across 80 community-based outpatient clinics (N = 1,600 patients) from different U.S. regions. Sites not initially responding to REP (defined as <50% patients receiving ≥3 EBP sessions) will be randomized to receive additional support from an EF or both EF/IF. Additionally, sites randomized to EF and still not responsive will be randomized to continue with EF alone or to receive EF/IF. The EF provides technical expertise in adapting LG in
routine practice, whereas the on-site IF has direct reporting relationships to site leadership to support LG use in routine practice. The primary outcome is mental health-related quality of life; secondary outcomes include receipt of LG sessions, mood symptoms, implementation costs, and organizational change. Diiscussion: This study design will determine whether an off-site EF alone versus the addition of an on-site IF improves EBP uptake and patient outcomes among sites that do not respond initially to REP. It will also examine the value of delaying the provision of EF/IF for sites that continue to not respond despite EF.
BibTeX:
@article{Kilbourne2014,
  author = {A.M. Kilbourne and D. Almirall and D. Eisenberg and J. Waxmonsky and D.E. Goodrich and J.C. Fortney and J.E. Kirchner and L.I. Solberg and D. Main and M.S. Bauer and J. Kyle and S.A. Murphy and J.M. Nord and M.R. Thomas},
  title = {Protocol: Adaptive Implementation of Effective Programs Trial (ADEPT): cluster randomized SMART trial comparing a standard versus enhanced implementation strategy to improve outcomes of a mood disorders program},
  journal = {Implementation Science},
  publisher = {BioMed Central Ltd},
  year = {2014},
  volume = {9},
  number = {1},
  pages = {132},
  url = {http://www.implementationscience.com/content/pdf/s13012-014-0132-x.pdf}
}
Krahnke J, Abraham W, Adamson P, Bourge R, Bauman J, Ginn G, Martinez F, Criner G and Group CTS (2014), "Heart Failure and respiratory hospitalizations are reduced in heart failure subjects with chronic obstructive pulmonary disease using an implantable pulmonary artery pressure monitoring device", Journal of cardiac failure. Vol. 21(3), pp. 240-9. Churchill Livingstone.
BibTeX:
@article{Krahnke2014,
  author = {J.S. Krahnke and W.T. Abraham and P.B. Adamson and R.C. Bourge and J. Bauman and G. Ginn and F.J. Martinez and G.J. Criner and CHAMPION Trial Study Group},
  title = {Heart Failure and respiratory hospitalizations are reduced in heart failure subjects with chronic obstructive pulmonary disease using an implantable pulmonary artery pressure monitoring device},
  journal = {Journal of cardiac failure},
  publisher = {Churchill Livingstone},
  year = {2014},
  volume = {21},
  number = {3},
  pages = {240-9},
  url = {http://www.sciencedirect.com/science/article/pii/S1071916414013505}
}
Kumar V, Park H, Basole R, Braunstein M, Kahng M, Chau D, Tamersoy A, Hirsh D, Serban N, Bost J, Lesnick B, Schissel B and Thompson M (2014), "Exploring Clinical Care Processes Using Visual and Data Analytics: Challenges and Opportunities", Knowledge Discovery and Data Mining (KDD): Workshop on Data Science for Social Good.
BibTeX:
@article{Kumar2014b,
  author = {V. Kumar and H. Park and R.C. Basole and M. Braunstein and M. Kahng and D.H. Chau and A. Tamersoy and D.A. Hirsh and N. Serban and J. Bost and B. Lesnick and B. Schissel and M. Thompson},
  title = {Exploring Clinical Care Processes Using Visual and Data Analytics: Challenges and Opportunities},
  journal = {Knowledge Discovery and Data Mining (KDD): Workshop on Data Science for Social Good},
  year = {2014},
  url = {http://dssg.uchicago.edu/kddworkshop/papers/kumar.pdf}
}
Kundu A, Li Y, Dellaert F, Li F and Rehg J (2014), "Joint Semantic Segmentation and 3D Reconstruction from Monocular Video", In Proceedings of the 2014 European Conference on Computer Vision (ECCV ). , pp. 703-718. Springer International Publishing.
Abstract: We present an approach for joint inference of 3D scene structure and semantic labeling for monocular video. Starting with monocular image stream, our framework produces a 3D volumetric semantic + occupancy map, which is much more useful than a series of 2D semantic label images or a sparse point cloud produced by traditional semantic segmentation and Structure from Motion(SfM) pipelines respectively. We derive a Conditional Random Field (CRF) model defined in the 3D space, that jointly infers the semantic category and occupancy for each voxel. Such a joint inference in the 3D CRF paves the way for more informed priors and constraints, which is otherwise not possible if solved separately in
their traditional frameworks. We make use of class specific semantic cues that constrain the 3D structure in areas, where multiview constraints are weak. Our model comprises of higher order factors, which helps when the depth is unobservable. We also make use of class specific semantic cues to reduce either the degree of such higher order factors, or to approximately model them with unaries if possible. We demonstrate improved 3D structure
and temporally consistent semantic segmentation for difficult, large scale, forward moving monocular image sequences.
BibTeX:
@incollection{Kundu2014,
  author = {A. Kundu and Y. Li and F. Dellaert and F. Li and J.M. Rehg},
  title = {Joint Semantic Segmentation and 3D Reconstruction from Monocular Video},
  booktitle = {Proceedings of the 2014 European Conference on Computer Vision (ECCV )},
  publisher = {Springer International Publishing},
  year = {2014},
  pages = {703--718},
  url = {http://www.cc.gatech.edu/ dellaert/pubs/Kundu14eccv.pdf

http://link.springer.com/chapter/10.1007/978-3-319-10599-4_45} }
Laber E, LIzotte D, Qian M, Pelman W and Murphy S (2014), "Dynamic treatment regimes: Technical challenges and applications", Electronic Journal of Statistics. Vol. 8(1), pp. 1225-1272.
Abstract: Dynamic treatment regimes are of growing interest across the clinical sciences because these regimes provide one way to operationalize and thus inform sequential personalized clinical decision making. Formally, a dynamic treatment regime is a sequence of decision rules, one per stage of clinical intervention. Each decision rule maps up-to-date patient information to a recommended treatment. We briefly review a variety of approaches for using data to construct the decision rules. We then review a critical inferential challenge that results from nonregularity, which often arises in this area. In particular, nonregularity arises in inference for parameters in the optimal dynamic treatment regime; the asymptotic, limiting, distribution of estimators are sensitive to local perturbations. We propose and evaluate a locally consistent Adaptive Confidence Interval (ACI) for the parameters of the optimal dynamic treatment regime. We use data from the Adaptive Pharmacological and Behavioral Treatments for Children with ADHD Trial as an illustrative example. We conclude by highlighting and discussing emerging theoretical problems in this area.
BibTeX:
@article{laber2014,
  author = {E. Laber and D.J. LIzotte and M. Qian and W.E. Pelman and S.A. Murphy},
  title = {Dynamic treatment regimes: Technical challenges and applications},
  journal = {Electronic Journal of Statistics},
  year = {2014},
  volume = {8},
  number = {1},
  pages = {1225--1272},
  url = {http://projecteuclid.org/euclid.ejs/1408540283}
}
Lagoa C, Bekiroglu K, Lanza S and Murphy S (2014), "Designing adaptive intensive interventions using methods from engineering.", Journal of Consulting and Clinical Psychology. Vol. 82(5), pp. 868. American Psychological Association.
Abstract: OBJECTIVE:
Adaptive intensive interventions are introduced, and new methods from the field of control engineering for use in their design are illustrated.
METHOD:
A detailed step-by-step explanation of how control engineering methods can be used with intensive longitudinal data to design an adaptive intensive intervention is provided. The methods are evaluated via simulation.
RESULTS:
Simulation results illustrate how the designed adaptive intensive intervention can result in improved outcomes with less treatment by providing treatment only when it is needed. Furthermore, the methods are robust to model misspecification as well as the influence of unobserved causes.
CONCLUSIONS:
These new methods can be used to design adaptive interventions that are effective yet reduce participant burden.
BibTeX:
@article{Lagoa2014,
  author = {C.M. Lagoa and K. Bekiroglu and S.T. Lanza and S.A. Murphy},
  title = {Designing adaptive intensive interventions using methods from engineering.},
  journal = {Journal of Consulting and Clinical Psychology},
  publisher = {American Psychological Association},
  year = {2014},
  volume = {82},
  number = {5},
  pages = {868},
  url = {http://psycnet.apa.org/journals/ccp/82/5/868/}
}
Lam C, Businelle M, Aigner C, McClure J, Cofta-Woerpel L, Cinciripini P and Wetter D (2014), "Individual and Combined Effects of Multiple High-Risk Triggers on Postcessation Smoking Urge and Lapse", Nicotine and Tobacco Research. Vol. 16(5), pp. 569-575.
Abstract: Introduction: Negative affect, alcohol consumption, and presence of others smoking have consistently been implicated as risk factors for smoking lapse and relapse. What is not known, however, is how these factors work together to affect smoking outcomes. This paper uses ecological momentary assessment (EMA) collected during the first 7 days of a smoking cessation attempt to test the individual and combined effects of high-risk triggers on smoking urge and lapse. Methods: Participants were 300 female smokers who enrolled in a study that tested an individually tailored smoking cessation treatment. Participants completed EMA, which recorded negative affect, alcohol consumption, presence of others smoking, smoking urge, and smoking lapse, for 7 days starting on their quit date. Results: Alcohol consumption, presence of others smoking, and negative affect were, independently and in combination, associated with increase in smoking urge and lapse. The results also found that the relationship between presence of others smoking and lapse and the relationship between negative affect and lapse were moderated by smoking urge. Conclusions: The current study found significant individual effects of alcohol consumption, presence of other smoking, and negative affect on smoking urge and lapse. Combing the triggers increased smoking urge and the risk for lapse to varying degrees, and the presence of all 3 triggers resulted in the highest urge and lapse risk.
BibTeX:
@article{Lam2014,
  author = {C.Y. Lam and M.S. Businelle and C.J. Aigner and J.B. McClure and L. Cofta-Woerpel and P.M. Cinciripini and D.W. Wetter},
  title = {Individual and Combined Effects of Multiple High-Risk Triggers on Postcessation Smoking Urge and Lapse},
  journal = {Nicotine and Tobacco Research},
  year = {2014},
  volume = {16},
  number = {5},
  pages = {569-575},
  url = {http://ntr.oxfordjournals.org/content/16/5/569.short}
}
Lin Z, Kahng M, Sabrin K, Chau D, Lee H and Kang U (2014), "MMap: Fast billion-scale graph computation on a PC via memory mapping", In 2014 IEEE International Conference on Big Data. , pp. 159-164.
Abstract: Graph computation approaches such as GraphChi and TurboGraph recently demonstrated that a single PC can perform efficient computation on billion-node graphs. To achieve high speed and scalability, they often need sophisticated data structures and memory management strategies. We propose a minimalist approach that forgoes such requirements, by leveraging the fundamental memory mapping (MMap) capability found on operating systems. We contribute: (1) a new insight that MMap is a viable technique for creating fast and scalable graph algorithms that surpasses some of the best techniques; (2) the design and implementation of popular graph algorithms for billion-scale graphs with little code, thanks to memory mapping; (3) extensive experiments on real graphs, including the 6.6 billion edge YahooWeb graph, and show that this new approach is significantly faster or comparable to the highly-optimized methods (e.g., 9.5X faster than GraphChi for computing PageRank on 1.47B edge Twitter graph). We believe our work provides a new direction in the design and development of scalable algorithms. Our packaged code is available at http://poloclub.gatech.edu/mmap/.
BibTeX:
@inproceedings{Lin2014,
  author = {Z. Lin and M. Kahng and K.M. Sabrin and D.H. Chau and H. Lee and U. Kang},
  title = {MMap: Fast billion-scale graph computation on a PC via memory mapping},
  booktitle = {2014 IEEE International Conference on Big Data},
  year = {2014},
  pages = {159--164},
  url = {http://www.cc.gatech.edu/ dchau/papers/14-bigdata-mmap.pdf}
}
Lopez D, Fernandez M, Cano M, Mendez C, Tsai C, Wetter D and Strom S (2014), "Association of acculturation, nativity, and years living in the United States with biobanking among individuals of Mexican descent.", Cancer epidemiology, biomarkers &amp; prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.
Abstract: BACKGROUND: Biobanking is the collection of human biospecimens (tissues, blood, and body fluids) and their associated clinical and outcome data. Hispanics are less likely to provide biologic specimens for biobanking. The purpose of this study was to investigate the association of acculturation, nativity status, and years living in the United States with participation in biobanking among individuals of Mexican descent. METHODS: Participants were 19,212 adults of Mexican descent enrolled in an ongoing population-based cohort in Houston, TX. Participants were offered the opportunity to provide a blood, urine, or saliva sample for biobanking. Acculturation was assessed with the bidimensional acculturation scale for Hispanics and scores were categorized into "low acculturation," "bicultural," and "high-acculturation." RESULTS: After multivariable adjustment, we found an increased likelihood of participation in biobanking among individuals classified as "bicultural" as compared with "highly acculturated" individuals [OR, 1.58; 95% confidence intervals (CI), 1.10-2.26]. The associations of nativity status and years living in the United States with biobanking were not statistically significant. After stratifying by gender, the associations of acculturation, nativity status, and years living in the United States with biobanking were not statistically significant. CONCLUSION: Although individuals of Mexican descent who were "bicultural" were more likely to participate in biobanking than individuals who were "highly acculturated," the difference in rates of participation among acculturation categories was small. The high participation rate in biospecimen collection is likely due to extensive community-engaged research efforts. Future studies are warranted to understand individuals' participation in biobanking. IMPACT: Community-engaged research efforts may increase Hispanics' participation in biobanking.
BibTeX:
@article{Lopez2014,
  author = {D.S. Lopez and M.E. Fernandez and M.A. Cano and C. Mendez and C.L. Tsai and D.W. Wetter and S.S. Strom},
  title = {Association of acculturation, nativity, and years living in the United States with biobanking among individuals of Mexican descent.},
  journal = {Cancer epidemiology, biomarkers &amp; prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology},
  year = {2014},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24609849}
}
Maher J, Doerksen S, Elavsky S and Conroy D (2014), "Daily satisfaction with life is regulated by both physical activity and sedentary behavior.", Journal of Sport &amp; Exercise Psychology. Vol. 36(2), pp. 166-178.
Abstract: Recent research revealed that on days when college students engage in more physical activity than is typical for them, they also experience greater satisfaction with life (SWL). That work relied on self-reported physical activity and did not differentiate between low levels of physical activity and sedentary behavior. This study was designed to (1) determine if the association between self-reported physical activity and SWL would exist when physical activity was monitored objectively and (2) examine the between- and within-person associations among physical activity, sedentary behavior, and SWL. During a 14-day ecological momentary assessment study, college students (N = 128) wore an accelerometer to objectively measure physical activity and sedentary behavior, and they self-reported their physical activity, sedentary behavior, and SWL at the end of each day. Physical activity and sedentary behavior had additive, within-person associations with SWL across self-reported and objective-measures of behavior. Strategies to promote daily well-being should encourage college students to incorporate greater amounts of physical activity as well as limit their sedentary behavior.
BibTeX:
@article{Maher2014,
  author = {J.P. Maher and S.E. Doerksen and S. Elavsky and D.E. Conroy},
  title = {Daily satisfaction with life is regulated by both physical activity and sedentary behavior.},
  journal = {Journal of Sport &amp; Exercise Psychology},
  year = {2014},
  volume = {36},
  number = {2},
  pages = {166--178},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24686953}
}
Malhotra K, Chau D, Sun J, Hadjipanayis C and Navath S (2014), "Temporal Event Sequence Mining for Glioblastoma Survival Prediction", ACM SIGKDD '14 Workshop on Health Informatics (HI-KDD 2014).
Abstract: One of the many challenges in the field of medicine is to make the best decisions about optimal treatment plans for patients. Medical practitioners often have differing opinions about the best treatment among multiple available options. While standard protocols are in place for the first and second lines of treatment for most diseases, a lot of variation exists in the treatment plans subsequently chosen. As a representative disease we study Glioblastoma Multiforme (GBM) which is a rare form of brain tumor. The goal of our study is to predict patients surviving for greater than the median survival period for GBM and discover in addition to clinical and genomic factors, certain treatment patterns which influence longevity. We use publicly available data for 300 patients spanning a period of 2 years from The Cancer Genome Atlas Portal, which has actual de-identified patient data from multiple institutions. Information about each patient comprises a set of features from the clinical and the genomic domain. We also use sequential mining algorithms to extract treatment patterns and use the patterns themselves as additional features. A model predicting whether a patient would survive for more than a year is developed using logistic regression and the most predictive features influencing the survival period of GBM patients include mRNA expression levels of certain genes and medications given in a particular sequence. The model achieved an AUC of 0.85 with an accuracy of 86.4% .The study is a preliminary step in a long term plan of developing personalized treatment plans with GBM patients as an initial model that can later be extended to other diseases.
BibTeX:
@article{malhotra2014,
  author = {K. Malhotra and D.H. Chau and J. Sun and C. Hadjipanayis and S.B. Navath},
  title = {Temporal Event Sequence Mining for Glioblastoma Survival Prediction},
  journal = {ACM SIGKDD '14 Workshop on Health Informatics (HI-KDD 2014)},
  year = {2014},
  url = {http://cci.drexel.edu/HI-KDD2014/morning_1.pdf}
}
Martin P, Ho B, Grupen N, Muñoz S and Srivastava M (2014), "An iBeacon Primer for Indoor Localization: Demo Abstract", In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings. Memphis, Tennessee , pp. 190-191. ACM.
Abstract: Providing an accurate, low cost estimate of sub-room indoor positioning remains an active area of research with applications including reactive indoor spaces, dynamic temperature control, wireless health, and augmented reality, to name a few. Recently proposed indoor localization solutions have required anywhere from zero additional infrastructure to customized RF hardware and have provided room-level to centimeter-level accuracy, typically in that respective order. One emerging technology that is proving a pragmatic solution for scalable, accurate localization is that of Bluetooth Low Energy beaconing, spearheaded by Apple's recently introduced iBeacon protocol. In this demo, we present a suite of localization tools developed around the iBeacon protocol, providing an in-depth look at Bluetooth Low Energy's viability as an indoor positioning technology. Our system shows an average position estimation error of 0.53 meters.
BibTeX:
@inproceedings{Martin:2014:IPI:2674061.2675028,
  author = {P. Martin and B. Ho and N. Grupen and S. Muñoz and M.B. Srivastava},
  title = {An iBeacon Primer for Indoor Localization: Demo Abstract},
  booktitle = {Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings},
  publisher = {ACM},
  year = {2014},
  pages = {190--191},
  url = {http://doi.acm.org/10.1145/2674061.2675028}
}
Martin P, Shoukry Y, Swaminathan P, Ouyang R and Srivastava M (2014), "Social spring: encounter-based path refinement for indoor tracking systems", In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings (ACM BuildSys 2014). , pp. 156-159.
Abstract: Indoor localization is poised to catalyze the development of smarter buildings and the creation of reactive indoor spaces, allowing for user-optimized energy expenditure and a more intimate user experience. This paper presents Social Spring, an architecture and
corresponding software suite for refining indoor path estimation algorithms. Given an underlying indoor localization scheme, Social Spring attempts to reduce path estimation errors by leveraging encounters between users in real time. The driving concept
behind Social Spring is that paths are treated as strings of nodes connected edgewise in a graph, while encounters are treated as additional edges in that graph. Each node attempts to minimize a local potential function dictated by a network of springs, the minimum of which is designed such that nodes converge to a lower energy equivalently lower error) state. We further provide simulations and preliminary tests on real indoor localization datasets in order
to lend credence to Social Spring’s effectiveness over a range of environmental factors, demonstrating between 10% and 30% error reduction.
BibTeX:
@inproceedings{Martin2014a,
  author = {P. Martin and Y. Shoukry and P. Swaminathan and R.W. Ouyang and M.B. Srivastava},
  title = {Social spring: encounter-based path refinement for indoor tracking systems},
  booktitle = {Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings (ACM BuildSys 2014)},
  year = {2014},
  pages = {156--159},
  url = {http://dl.acm.org/citation.cfm?id=2674061.2674065}
}
Mauriello L, Evers K, Nilsen W and Patrick K (2014), "The Use Of mHealth With Special Populations: Theory, Research And Practice", In Annals of Behavioral Medicine. Vol. 47, pp. S149-S149.
BibTeX:
@incollection{Mauriello2014,
  author = {L. Mauriello and K. Evers and W. Nilsen and K. Patrick},
  title = {The Use Of mHealth With Special Populations: Theory, Research And Practice},
  booktitle = {Annals of Behavioral Medicine},
  year = {2014},
  volume = {47},
  pages = {S149--S149}
}
Mayberry A, Hu P, Marlin B, Salthouse C and Ganesan D (2014), "iShadow: Design of a Wearable, Real-time Mobile Gaze Tracker", In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14). Bretton Woods, New Hampshire, USA , pp. 82-94. ACM.
Abstract: Continuous, real-time tracking of eye gaze is valuable in a variety of scenarios including hands-free interaction with the physical world, detection of unsafe behaviors, leveraging visual context for advertising, life logging, and others. While eye tracking is commonly used in clinical trials and user studies, it has not bridged the gap to everyday consumer use. The challenge is that a real-time eye tracker is a power-hungry and computation-intensive device which requires continuous sensing of the eye using an imager running at many tens of frames per second, and continuous processing of the image stream using sophisticated gaze estimation algorithms. Our key contribution is the design of an eye tracker that dramatically reduces the sensing and computation needs for eye tracking, thereby achieving orders of magnitude reductions in power consumption and form-factor. The key idea is that eye images are extremely redundant, therefore we can estimate gaze by using a small subset of carefully chosen pixels per frame. We instantiate this idea in a prototype hardware platform equipped with a low-power image sensor that provides random access to pixel values, a low-power ARM Cortex M3 microcontroller, and a bluetooth radio to communicate with a mobile phone. The sparse pixel-based gaze estimation algorithm is a multi-layer neural network learned using a state-of-the-art sparsity-inducing regularization function that minimizes the gaze prediction error while simultaneously minimizing the number of pixels used. Our results show that we can operate at roughly 70mW of power, while continuously estimating eye gaze at the rate of 30 Hz with errors of roughly 3 degrees.
BibTeX:
@inproceedings{Mayberry:2014:IDW:2594368.2594388,
  author = {A. Mayberry and P. Hu and B. Marlin and C. Salthouse and D. Ganesan},
  title = {iShadow: Design of a Wearable, Real-time Mobile Gaze Tracker},
  booktitle = {Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14)},
  publisher = {ACM},
  year = {2014},
  pages = {82--94},
  url = {http://doi.acm.org/10.1145/2594368.2594388}
}
Mun M, Kim D, Shilton K, Estrin D, Hansen M and Govindan R (2014), "PDVLoc: A Personal Data Vault for Controlled Location Data Sharing", ACM Transactions on Sensor Networks. New York, NY, USA Vol. 10(4), pp. 58:1-58:29. ACM.
Abstract: Location-Based Mobile Service (LBMS) is one of the most popular smartphone services. LBMS enables people to more easily connect with each other and analyze the aspects of their lives. However, sharing location data can leak people's privacy. We present PDVLoc, a controlled location data-sharing framework based on selectively sharing data through a Personal Data Vault (PDV). A PDV is a privacy architecture in which individuals retain ownership of their data. Data are routinely filtered before being shared with content-service providers, and users or data custodian services can participate in making controlled data-sharing decisions. Introducing PDVLoc gives users flexible and granular access control over their location data. We have implemented a prototype of PDVLoc and evaluated it using real location-sharing social networking applications, Google Latitude and Foursquare. Our user study of 19 participants over 20 days shows that most users find that PDVLoc is useful to manage and control their location data, and are willing to continue using PDVLoc.
BibTeX:
@article{Mun:2014:PPD:2633905.2523820,
  author = {M.Y. Mun and D.H. Kim and K. Shilton and D. Estrin and M. Hansen and R. Govindan},
  title = {PDVLoc: A Personal Data Vault for Controlled Location Data Sharing},
  journal = {ACM Transactions on Sensor Networks},
  publisher = {ACM},
  year = {2014},
  volume = {10},
  number = {4},
  pages = {58:1--58:29},
  url = {http://doi.acm.org/10.1145/2523820}
}
Murphy D, Harrell L, Fintzy R, Belin T, Gutierrez A, Vitero S and Shetty V (2014), "A Comparison of Methamphetamine Users to a Matched NHANES Cohort: Propensity Score Analyses for Oral Health Care and Dental Service Need", The Journal of Behavioral Health Services &amp; Research. , pp. 1-15. Springer US.
Abstract: Sequential multiple assignment randomized trials (SMARTs) are increasingly being used to inform clinical and intervention science. In a SMART, each patient is repeatedly randomized over time. Each randomization occurs at a critical decision point in the treatment course. These critical decision points often correspond to milestones in the disease process or other changes in a patient's health status. Thus, the timing and number of randomizations may vary across patients and depend on evolving patient-specific information. This presents unique challenges when analyzing data from a SMART in the presence of missing data. This paper presents the first comprehensive discussion of missing data issues typical of SMART studies: we describe five specific challenges and propose a flexible imputation strategy to facilitate valid statistical estimation and inference using incomplete data from a SMART. To illustrate these contributions, we consider data from the Clinical Antipsychotic Trial of Intervention and Effectiveness, one of the most well-known SMARTs to date. Copyright © 2014 John Wiley & Sons, Ltd.
BibTeX:
@article{Murphy2014,
  author = {D.A. Murphy and L. Harrell and R. Fintzy and T.R. Belin and A. Gutierrez and S.J. Vitero and V. Shetty},
  title = {A Comparison of Methamphetamine Users to a Matched NHANES Cohort: Propensity Score Analyses for Oral Health Care and Dental Service Need},
  journal = {The Journal of Behavioral Health Services &amp; Research},
  publisher = {Springer US},
  year = {2014},
  pages = {1-15},
  url = {http://dx.doi.org/10.1007/s11414-014-9449-0}
}
Nahum-Shani I, Henderson M, Lim S and Vinokur A (2014), "Supervisor support: does supervisor support buffer or exacerbate the adverse effects of supervisor undermining?", Journal of Applied Psychology. Vol. 99(3), pp. 484-503.
Abstract: Empirical investigations concerning the interplay between supervisor support and supervisor undermining behaviors and their effects on employees yielded contradictory findings, with some studies suggesting that support buffers the adverse effects of undermining, and others suggesting that support exacerbates these adverse effects. Seeking to explain such contradictory findings, we integrate uncertainty-management perspectives with coping theory to posit that relational uncertainty is inherent in the mixture of supervisor support and undermining. Hence, whether supervisor support buffers or exacerbates the adverse effects of supervisor undermining on employee health and well-being depends on factors pertaining to employee ability to resolve and manage such relational uncertainty. Specifically, we hypothesize a buffering effect for employees with high self-esteem and high quality of work life, and an exacerbating effect for employees with low self-esteem and low quality of work life. Analyses of 2-wave data collected from a probability stratified sample of U.S. Air Force personnel supported our predictions. Two supplementary studies of the U.S. military replicated our core findings and demonstrated its practical significance.
BibTeX:
@article{nahumshani2014a,
  author = {I. Nahum-Shani and M.M. Henderson and S. Lim and A.D. Vinokur},
  title = {Supervisor support: does supervisor support buffer or exacerbate the adverse effects of supervisor undermining?},
  journal = {Journal of Applied Psychology},
  year = {2014},
  volume = {99},
  number = {3},
  pages = {484-503},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24490969}
}
Nakajima M and al'Absi M (2014), "Nicotine withdrawal and stress-induced changes in pain sensitivity: a cross-sectional investigation between abstinent smokers and nonsmokers", Psychophysiology. Vol. 51(10), pp. 1015-22.
Abstract: Chronic smoking has been linked with alterations in endogenous pain regulation. These alterations may be pronounced when individuals quit smoking because nicotine withdrawal produces a variety of psychological and physiological symptoms. Smokers interested in quitting (n?=?98) and nonsmokers (n?=?37) completed a laboratory session including cold pressor test (CPT) and heat thermal pain. Smokers set a quit date and completed the session after 48?h of abstinence. Participants completed the pain assessments once after rest and once after stress. Cardiovascular and nicotine withdrawal measures were collected. Smokers showed blunted cardiovascular responses to stress relative to nonsmokers. Only nonsmokers had greater pain tolerance to CPT after stress than after rest. Lower systolic blood pressure was related to lower pain tolerance. These findings suggest that smoking withdrawal is associated with blunted stress response and increased pain sensitivity.
BibTeX:
@article{nakajima2014,
  author = {M. Nakajima and M. al'Absi},
  title = {Nicotine withdrawal and stress-induced changes in pain sensitivity: a cross-sectional investigation between abstinent smokers and nonsmokers},
  journal = {Psychophysiology},
  year = {2014},
  volume = {51},
  number = {10},
  pages = {1015-22},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24934193}
}
Natarajan A, Gaiser E, Angarita G, Malison R, Ganesan D and Marlin B (2014), "Conditional Random Fields for Morphological Analysis of Wireless ECG Signals", In Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Newport Beach, California , pp. 370-379. ACM.
BibTeX:
@inproceedings{Natarajan2014,
  author = {A. Natarajan and E. Gaiser and G. Angarita and R. Malison and D. Ganesan and B. Marlin},
  title = {Conditional Random Fields for Morphological Analysis of Wireless ECG Signals},
  booktitle = {Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics},
  publisher = {ACM},
  year = {2014},
  pages = {370--379},
  url = {http://doi.acm.org/10.1145/2649387.2649414}
}
Ouyang R, Srivastava M, Toniolo A and Norman T (2014), "Truth Discovery in Crowdsourced Detection of Spatial Events", In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. , pp. 461-470.
Abstract: The ubiquity of smartphones has led to the emergence of mobile crowdsourcing tasks such as the detection of spatial events when smartphone users move around in their daily lives. However, the credibility of those detected events can be negatively impacted by unreliable participants with low-quality data. Consequently, a major challenge in quality control is to discover true events from diverse and noisy participants’ reports. This truth discovery problem is uniquely distinct from its online counterpart in that it involves uncertainties in both participants’ mobility and reliability. Decoupling these two types of uncertainties through location tracking will raise severe privacy and energy issues, whereas simply ignoring
missing reports or treating them as negative reports will significantly degrade the accuracy of the discovered truth. In this paper, we propose a new method to tackle this truth discovery problem through principled probabilistic modeling. In particular, we integrate the modeling of location popularity, location visit indicators, truth of events and three-way participant reliability in a unified framework. The proposed model is thus capable of efficiently handling various types of uncertainties and automatically discovering truth without any supervision or the need of location tracking. Experimental results demonstrate that our proposed method outperforms existing state-of-the-art truth discovery approaches in the mobile crowdsourcing environment.
BibTeX:
@inproceedings{Ouyang2014,
  author = {R.W. Ouyang and M.B. Srivastava and A. Toniolo and T.J. Norman},
  title = {Truth Discovery in Crowdsourced Detection of Spatial Events},
  booktitle = {Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management},
  year = {2014},
  pages = {461--470},
  url = {http://dl.acm.org/citation.cfm?id=2662003}
}
Parate A, Chiu M, Chadowitz C, Ganesan D and Kalogerakis E (2014), "RisQ: Recognizing Smoking Gestures with Inertial Sensors on a Wristband", In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14). Bretton Woods, New Hampshire, USA , pp. 149-161. ACM.
Abstract: Smoking-induced diseases are known to be the leading cause of death in the United States. In this work, we design RisQ, a mobile solution that leverages a wristband containing a 9-axis inertial measurement unit to capture changes in the orientation of a person's arm, and a machine learning pipeline that processes this data to accurately detect smoking gestures and sessions in real-time. Our key innovations are four-fold: a) an arm trajectory-based method that extracts candidate hand-to-mouth gestures, b) a set of trajectory-based features to distinguish smoking gestures from confounding gestures including eating and drinking, c) a probabilistic model that analyzes sequences of hand-to-mouth gestures and infers which gestures are part of individual smoking sessions, and d) a method that leverages multiple IMUs placed on a person's body together with 3D animation of a person's arm to reduce burden of self-reports for labeled data collection. Our experiments show that our gesture recognition algorithm can detect smoking gestures with high accuracy (95.7%), precision (91%) and recall (81%). We also report a user study that demonstrates that we can accurately detect the number of smoking sessions with very few false positives over the period of a day, and that we can reliably extract the beginning and end of smoking session periods.
BibTeX:
@inproceedings{Parate:2014:RRS:2594368.2594379,
  author = {A. Parate and M. Chiu and C. Chadowitz and D. Ganesan and E. Kalogerakis},
  title = {RisQ: Recognizing Smoking Gestures with Inertial Sensors on a Wristband},
  booktitle = {Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '14)},
  publisher = {ACM},
  year = {2014},
  pages = {149--161},
  url = {http://doi.acm.org/10.1145/2594368.2594379}
}
Park D, Kapusta A, Kim Y, Rehg J and Kemp C (2014), "Learning to reach into the unknown: Selecting initial conditions when reaching in clutter", In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014). , pp. 630-637.
Abstract: Often in highly-cluttered environments, a robot can observe the exterior of the environment with ease, but cannot directly view nor easily infer its detailed internal structure (e.g., dense foliage or a full refrigerator shelf). We present a data-driven approach that greatly improves a robot’s success at reaching to a goal location in the unknown interior of an environment based on observable external properties, such as the category of the clutter and the locations of openings into the clutter (i.e., apertures). We focus on the problem of selecting a good initial configuration for a manipulator when reaching with a greedy controller. We use density estimation to model the probability of a successful reach given an initial condition and then perform constrained optimization to find an initial condition with the highest estimated probability of success. We evaluate our approach with two simulated robots reaching in clutter, and provide a demonstration with a real PR2 robot reaching to locations through random apertures. In our evaluations, our approach significantly outperformed two alternative approaches when making two consecutive reach attempts to goals in distinct categories of unknown clutter. Notably, our approach only uses sparse readily-apparent features.
BibTeX:
@inproceedings{Park2014,
  author = {D. Park and A. Kapusta and Y.K. Kim and J.M. Rehg and C.C. Kemp},
  title = {Learning to reach into the unknown: Selecting initial conditions when reaching in clutter},
  booktitle = {2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014)},
  year = {2014},
  pages = {630--637},
  url = {http://www.hsi.gatech.edu/hrl/pdf/iros2014_lic.pdf}
}
Pellegrini C, Hoffman S, Collins L and Spring B (2014), "Optimization of remotely delivered intensive lifestyle treatment for obesity using the Multiphase Optimization Strategy: Opt-IN study protocol.", Contemporary Clinical Trials. Vol. 38(2), pp. 251-9.
Abstract: BACKGROUND: Obesity-attributable medical expenditures remain high, and interventions that are both effective and cost-effective have not been adequately developed. The Opt-IN study is a theory-guided trial using the Multiphase Optimization Strategy (MOST) to develop an optimized, scalable version of a technology-supported weight loss intervention. OBJECTIVE: Opt-IN aims to identify which of 5 treatment components or component levels contribute most meaningfully and cost-efficiently to the improvement of weight loss over a 6 month period. STUDY DESIGN: Five hundred and sixty obese adults (BMI 30-40 kg/m(2)) between 18 and 60 years old will be randomized to one of 16 conditions in a fractional factorial design involving five intervention components: treatment intensity (12 vs. 24 coaching calls), reports sent to primary care physician (No vs. Yes), text messaging (No vs. Yes), meal replacement recommendations (No vs. Yes), and training of a participant's self-selected support buddy (No vs. Yes). During the 6-month intervention, participants will monitor weight, diet, and physical activity on the Opt-IN smartphone application downloaded to their personal phone. Weight will be assessed at baseline, 3, and 6 months. SIGNIFICANCE: The Opt-IN trial is the first study to use the MOST framework to develop a weight loss treatment that will be optimized to yield the best weight loss outcome attainable for $500 or less.
BibTeX:
@article{pellegrini2014b,
  author = {C.A. Pellegrini and S.A. Hoffman and L.M. Collins and B. Spring},
  title = {Optimization of remotely delivered intensive lifestyle treatment for obesity using the Multiphase Optimization Strategy: Opt-IN study protocol.},
  journal = {Contemporary Clinical Trials},
  year = {2014},
  volume = {38},
  number = {2},
  pages = {251-9},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24846621}
}
Pleister A, Hasan A, Abraham W, James K and Khayat R (2014), "Changes in Thoracic Impedance Measured via the Azygos Vein with the remed=etextregistered System Indicate Worsening Heart Failure", Journal of Cardiac Failure., August, 2014. Vol. 20(8), pp. S111-S112. Elsevier.
Abstract: Central sleep apnea occurs in approximately one third of patients with heart failure and is associated with an increased risk of recurrent hospitalizations. A new therapeutic approach, the remedē® System, has demonstrated improved sleep indices and quality of life. The device measures transthoracic impedance (TI) between an implantable pulse generator (IPG) implanted in the pectoral region and an electrode on a lead in one of three unique locations: the pericardiophrenic vein, the brachiocephalic vein or the azygos vein.
BibTeX:
@article{Pleister2014,
  author = {A. Pleister and A. Hasan and W.T. Abraham and K. James and R. Khayat},
  title = {Changes in Thoracic Impedance Measured via the Azygos Vein with the remed=etextregistered System Indicate Worsening Heart Failure},
  journal = {Journal of Cardiac Failure},
  publisher = {Elsevier},
  year = {2014},
  volume = {20},
  number = {8},
  pages = {S111--S112},
  url = {http://www.onlinejcf.com/article/S1071-9164(14)00546-6/abstract}
}
Potretzke S, Nakajima M, Cragin T and al' Absi M (2014), "Changes in circulating leptin levels during acute stress and associations with craving in abstinent smokers: a preliminary investigation", Psychoneuroendocrinology. Vol. 47, pp. 232-40.
Abstract: Recent research suggests a role for the appetite hormone leptin in cigarette smoking. This study examined patterns of change in leptin in response to stress and associations with craving during the initial phase of a quit attempt. Thirty-six smokers (average age±SEM, 33.4±2.4) interested in smoking cessation set a quit day and were required to be abstinent for 24h. After, they completed a laboratory session including public speaking and cognitive challenges, and attended 4 weekly post-cessation assessments. Blood samples and self-report measures were collected throughout the laboratory session. The results indicated that leptin levels significantly increased following exposure to acute stress. We also found positive correlations between leptin and craving for cigarettes. No differences were observed in leptin levels between smokers who maintained abstinence for 4 weeks and those who relapsed during this period. These findings suggest that leptin levels may change in response to stress and that leptin could be a useful marker of craving for smoking.
BibTeX:
@article{Potretzke2014,
  author = {S. Potretzke and M. Nakajima and T. Cragin and M. al' Absi},
  title = {Changes in circulating leptin levels during acute stress and associations with craving in abstinent smokers: a preliminary investigation},
  journal = {Psychoneuroendocrinology},
  year = {2014},
  volume = {47},
  pages = {232-40},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24954303}
}
Rahman M, Bari R, Ali A, Sharmin M, Raij A, Hovsepian K, Hossain S, Ertin E, Kennedy A, Epstein D, Preston K, Jobes M, Beck J, Kedia S, Ward K, al’Absi M and Kumar S (2014), "Are we there yet?: feasibility of continuous stress assessment via wireless physiological sensors", In Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. , pp. 479-488.
BibTeX:
@inproceedings{Rahman2014,
  author = {M.M Rahman and R. Bari and A.A. Ali and M. Sharmin and A. Raij and K. Hovsepian and S.M. Hossain and E. Ertin and A. Kennedy and D.H. Epstein and K.L. Preston and M. Jobes and J.G. Beck and S. Kedia and K.D. Ward and M. al’Absi and S. Kumar},
  title = {Are we there yet?: feasibility of continuous stress assessment via wireless physiological sensors},
  booktitle = {Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics},
  year = {2014},
  pages = {479--488},
  url = {http://dl.acm.org/citation.cfm?id=2649433}
}
Carbunar M, Ballesteros B, Burri J, Chau D and Rahman D (2014), "Turning the Tide: Curbing Deceptive Yelp Behaviors", Prodeedings of SIAM International Conference on Data Mining (SDM).
Abstract: The popularity and influence of reviews, make sites like Yelp ideal targets for malicious behaviors. We present Marco, a novel system that exploits the unique combination of social, spatial and temporal signals gleaned from Yelp, to detect venues whose ratings are impacted by fraudulent reviews. Marco increases the cost and complexity of attacks, by imposing a tradeoff on fraudsters, between their ability to impact venue ratings and their ability to remain undetected. We contribute a new dataset to the community, which consists of both ground truth and gold standard data. We show that Marco significantly outperforms state-of-the-art approaches, by achieving 94% accuracy in classifying reviews as fraudulent or genuine, and 95.8% accuracy in classifying venues as deceptive or legitimate. Marco successfully flagged 244 deceptive venues from our large dataset with 7,435 venues, 270,121 reviews and 195,417 users. Among the San Francisco car repair and moving companies that we analyzed, almost 10% exhibit fraudulent behaviors.
BibTeX:
@article{Rahman2014b,
  author = {M. Carbunar and B. Ballesteros and J. Burri and D.H. Chau and D. Rahman},
  title = {Turning the Tide: Curbing Deceptive Yelp Behaviors},
  journal = {Prodeedings of SIAM International Conference on Data Mining (SDM)},
  year = {2014},
  url = {http://users.cis.fiu.edu/ carbunar/deceptive.pdf}
}
Raina A, Bourge R, Abraham W, Adamson P, Bauman J, Yadav J and Benza R (2014), "Use of a Wireless Implantable Hemodynamic Monitor Leads to Reductions in Heart Failure Hospitalizations Among WHO Group II Pulmonary Hypertension Patients", The Journal of Heart and Lung Transplantation. Vol. 33(4), pp. S92-S92. Elsevier.
Abstract: Morbidity and mortality in heart failure (HF) remain high despite contemporary therapy, especially in patients with concomitant pulmonary hypertension (PH). RHC is used to risk stratify patients with HF and to determine the etiology and severity of PH. However, implantable hemodynamic monitors (IHM) can provide ongoing hemodynamic data which affords the opportunity for optimal medical management of HF patients with PH.
BibTeX:
@article{Raina2014,
  author = {A. Raina and R.C. Bourge and W.T. Abraham and P.B. Adamson and J. Bauman and J. Yadav and R.L. Benza},
  title = {Use of a Wireless Implantable Hemodynamic Monitor Leads to Reductions in Heart Failure Hospitalizations Among WHO Group II Pulmonary Hypertension Patients},
  journal = {The Journal of Heart and Lung Transplantation},
  publisher = {Elsevier},
  year = {2014},
  volume = {33},
  number = {4},
  pages = {S92--S92},
  url = {http://www.jhltonline.org/article/S1053-2498(14)00296-4/abstract}
}
Ratcliff C, Lam C, Arun B, Valero V and Cohen L (2014), "Ecological momentary assessment of sleep, symptoms, and mood during chemotherapy for breast cancer.", Psychooncology.. Thesis at: Department of Clinical Psychology, University of Houston, 126 Heyne Building, Houston, TX, 77204, USA.. Vol. 23(11), pp. 1220-1228.
Abstract: This study examined the association of sleep before and during a chemotherapy (CT) cycle for breast cancer with symptoms and mood during a CT cycle.Twenty women undergoing CT for breast cancer completed the Pittsburgh Sleep Quality Index (PSQI) 1 h prior to a CT infusion. For 3 weeks following infusion, participants estimated sleep efficiency, minutes to sleep (sleep latency), number of nocturnal awakenings (sleep fragmentation (SF)), and sleep quality (SQ) each morning and rated symptoms (nausea, fatigue, numbness, and difficulty thinking) and mood three times daily (morning, afternoon, and evening) via ecological momentary assessments using automated handheld computers.The results showed that disturbed sleep (PSQI score?>?5) prior to CT infusion was associated with greater fatigue, and more negative and anxious mood throughout the 3-week CT cycle, and good pre-CT infusion sleep (PSQI score?
BibTeX:
@article{Ratcliff2014,
  author = {C.G. Ratcliff and C.Y. Lam and B. Arun and V. Valero and L. Cohen},
  title = {Ecological momentary assessment of sleep, symptoms, and mood during chemotherapy for breast cancer.},
  journal = {Psychooncology},
  school = {Department of Clinical Psychology, University of Houston, 126 Heyne Building, Houston, TX, 77204, USA.},
  year = {2014},
  volume = {23},
  number = {11},
  pages = {1220--1228},
  url = {http://dx.doi.org/10.1002/pon.3525}
}
Rebar A, Elavsky S, Maher J, Doerksen S and Conroy D (2014), "Habits predict physical activity on days when intentions are weak.", Journal of Sport &amp; Exercise Psychology. Vol. 36(2), pp. 157-165.
Abstract: Physical activity is regulated by controlled processes, such as intentions, and automatic processes, such as habits. Intentions relate to physical activity more strongly for people with weak habits than for people with strong habits, but people's intentions vary day by day. Physical activity may be regulated by habits unless daily physical activity intentions are strong. University students (N = 128) self-reported their physical activity habit strength and subsequently self-reported daily physical activity intentions and wore an accelerometer for 14 days. On days when people had intentions that were weaker than typical for them, habit strength was positively related to physical activity, but on days when people had typical or stronger intentions than was typical for them, habit strength was unrelated to daily physical activity. Efforts to promote physical activity may need to account for habits and the dynamics of intentions.
BibTeX:
@article{Rebar2014,
  author = {A.L. Rebar and S. Elavsky and J.P. Maher and S.E. Doerksen and D.E. Conroy},
  title = {Habits predict physical activity on days when intentions are weak.},
  journal = {Journal of Sport &amp; Exercise Psychology},
  year = {2014},
  volume = {36},
  number = {2},
  pages = {157--165},
  url = {http://www.researchgate.net/profile/Amanda_Rebar/publication/261256626_Habits_predict_physical_activity_on_days_when_intentions_are_weak/links/53f444ae0cf2155be354f8e2.pdf}
}
Rebar A, Maher J, Doerksen S, Elavsky S and Conroy D (2014), "Intention-behavior gap is wider for walking and moderate physical activity than for vigorous physical activity in university students.", Journal of Science and Medicine in Sport.. Thesis at: Center for Behavior and Health - Institute for Public Health and Medicine, Northwestern University, USA..
Abstract: The theory of planned behavior proposes that physical activity is the result of intentions; however little is known about whether the relation between intentions and behavior differs between vigorous, moderate physical activity, and walking. For university students, vigorous physical activity is oftentimes enacted as a goal-directed behavior; whereas walking is oftentimes a means to achieving a goal other than physical activity (e.g., transportation).The study was a one-week prospective study.Undergraduate students (N=164) reported intentions for walking, moderate physical activity, and vigorous physical activity and self-reported these behaviors one week later.Hierarchical linear modeling revealed that intentions were more strongly related to vigorous physical activity than to moderate physical activity or walking.Intention-enhancing interventions may effectively promote vigorous physical activity, but other motivational processes may be more appropriate to target in interventions of walking and moderate physical activity.
BibTeX:
@article{Rebar2014a,
  author = {A.L. Rebar and J.P. Maher and S.E. Doerksen and S. Elavsky and D.E. Conroy},
  title = {Intention-behavior gap is wider for walking and moderate physical activity than for vigorous physical activity in university students.},
  journal = {Journal of Science and Medicine in Sport},
  school = {Center for Behavior and Health - Institute for Public Health and Medicine, Northwestern University, USA.},
  year = {2014},
  url = {http://dx.doi.org/10.1016/j.jsams.2014.11.392}
}
Rejeski W, Spring B, Domanchuk K, Tao H, Tian L, Zhao L and McDermott M (2014), "A group-mediated, home-based physical activity intervention for patients with peripheral artery disease: effects on social and psychological function", Journal of Translational Medicine.
Abstract: BACKGROUND: PAD is a disabling, chronic condition of the lower extremities that affects approximately 8 million people in the United States. The purpose of this study was to determine whether an innovative home-based walking exercise program for patients with peripheral artery disease (PAD) improves self-efficacy for walking, desire for physical competence, satisfaction for physical functioning, social functioning, and acceptance of PAD related pain and discomfort. METHODS: The design was a 6-month randomized controlled clinical trial of 194 patients with PAD. Participants were randomized to 1 of 2 parallel groups: a home-based group-mediated cognitive behavioral walking intervention or an attention control condition. RESULTS: Of the 194 participants randomized, 178 completed the baseline and 6-month follow-up visit. The mean age was 70.66 (±9.44) and was equally represented by men and women. Close to half of the cohort was African American. Following 6-months of treatment, the intervention group experienced greater improvement on self-efficacy (p = .0008), satisfaction with functioning (p = .0003), pain acceptance (p = .0002), and social functioning (p = .0008) than the control group; the effects were consistent across a number of potential moderating variables. Change in these outcomes was essentially independent of change in 6-minute walk performance.
BibTeX:
@article{rejeski2014,
  author = {W.J. Rejeski and B. Spring and K. Domanchuk and H. Tao and L. Tian and L. Zhao and M.Z.M. McDermott},
  title = {A group-mediated, home-based physical activity intervention for patients with peripheral artery disease: effects on social and psychological function},
  journal = {Journal of Translational Medicine},
  year = {2014},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24467875}
}
Roche M, Pincus A, Rebar A, Conroy D and Ram N (2014), "Enriching psychological assessment using a person-specific analysis of interpersonal processes in daily life", Assessment. , pp. 1073191114540320. SAGE Publications.
Abstract: We present a series of methods and approaches for clinicians interested in tracking their individual patients over time and in the natural settings of their daily lives. The application of person-specific analyses to intensive repeated measurement data can assess some aspects of persons that are distinct from the valuable results obtained from single-occasion assessments. Guided by interpersonal theory, we assess a psychotherapy patient’s interpersonal processes as they unfold in his daily life. We highlight specific contexts that change these processes, use an informant report to examine discrepancies in his reported interpersonal processes, and examine how his interpersonal processes differ as a function of varying levels of self-esteem and anger. We advocate for this approach to complement existing psychological assessments and provide a scoring program to facilitate initial implementation.
BibTeX:
@article{Roche2014,
  author = {M.J. Roche and A.L. Pincus and A.L. Rebar and D.E. Conroy and N. Ram},
  title = {Enriching psychological assessment using a person-specific analysis of interpersonal processes in daily life},
  journal = {Assessment},
  publisher = {SAGE Publications},
  year = {2014},
  pages = {1073191114540320},
  url = {http://asm.sagepub.com/content/21/5/515.full.pdf+html}
}
Saravanan P, Clarke S, Chau D and Zha H (2014), "LatentGesture: active user authentication through background touch analysis", In Proceedings of the Second International Symposium of Chinese CHI. , pp. 110-113.
Abstract: We propose a new approach for authenticating users of mobile devices that is based on analyzing the user’s touch interaction with common user interface (UI) elements, e.g., buttons, checkboxes and sliders. Unlike one-off authentication techniques such as passwords or gestures, our technique works continuously in the background while the user uses the mobile device. To evaluate our approach’s effectiveness, we conducted a lab study with 20 participants, where we recorded their interaction traces on a mobile phone and a tablet (e.g., touch pressure, locations), while they filled out electronic forms populated with UI widgets. Using classification methods based on SVM and Random Forests, we achieved an average of 97.9% accuracy with a mobile phone and 96.79% accuracy with a tablet for single user classification, demonstrating that our technique has strong potential for real-world use. We believe our research can help strengthen personal device security and safeguard against unintended or unauthorized uses, such as small children in a household making unauthorized online transactions on their parents’ devices, or an impostor accessing the bank account belonging to the victim of a stolen device.
BibTeX:
@inproceedings{Saravanan2014,
  author = {P. Saravanan and S. Clarke and D.H. Chau and H. Zha},
  title = {LatentGesture: active user authentication through background touch analysis},
  booktitle = {Proceedings of the Second International Symposium of Chinese CHI},
  year = {2014},
  pages = {110--113},
  url = {http://dl.acm.org/citation.cfm?doid=2592235.2592252}
}
Sarker H, Sharmin M, Ali A, Rahman M, Bari R, Hossain S and Kuma S (2014), "Assessing the Availability of Users to Engage in Just-in-time Intervention in the Natural Environment", In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Seattle, Washington , pp. 909-920. ACM.
Abstract: Wearable wireless sensors for health monitoring are enabling the design and delivery of just-in-time interventions (JITI). Critical to the success of JITI is to time its delivery so that the user is available to be engaged. We take a first step in modeling users' availability by analyzing 2,064 hours of physiological sensor data and 2,717 self-reports collected from 30 participants in a week-long field study. We use delay in responding to a prompt to objectively measure availability. We compute 99 features and identify 30 as most discriminating to train a machine learning model for predicting availability. We find that location, affect, activity type, stress, time, and day of the week, play significant roles in predicting availability. We find that users are least available at work and during driving, and most available when walking outside. Our model finally achieves an accuracy of 74.7% in 10-fold cross-validation and 77.9% with leave-one-subject-out.
BibTeX:
@inproceedings{Sarker:2014:AAU:2632048.2636082,
  author = {H. Sarker and M. Sharmin and A.A. Ali and M.M. Rahman and R. Bari and S.M. Hossain and S. Kuma},
  title = {Assessing the Availability of Users to Engage in Just-in-time Intervention in the Natural Environment},
  booktitle = {Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2014},
  pages = {909--920},
  url = {https://md2k.org/images/papers/jitai/nihms667251_sarker.pdf},
  doi = {10.1145/2632048.2636082}
}
Shortreed S, Laber E, Stroup T, Pineau J and Murphy S (2014), "A multiple imputation strategy for sequential multiple assignment randomized trials", Statistics in Medicine. Vol. 33(24), pp. 4202-14.
Abstract: Sequential multiple assignment randomized trials (SMARTs) are increasingly being used to inform clinical and intervention science. In a SMART, each patient is repeatedly randomized over time. Each randomization occurs at a critical decision point in the treatment course. These critical decision points often correspond to milestones in the disease process or other changes in a patient's health status. Thus, the timing and number of randomizations may vary across patients and depend on evolving patient-specific information. This presents unique challenges when analyzing data from a SMART in the presence of missing data. This paper presents the first comprehensive discussion of missing data issues typical of SMART studies: we describe five specific challenges and propose a flexible imputation strategy to facilitate valid statistical estimation and inference using incomplete data from a SMART. To illustrate these contributions, we consider data from the Clinical Antipsychotic Trial of Intervention and Effectiveness, one of the most well-known SMARTs to date.
BibTeX:
@article{Shortreed2014,
  author = {S.M. Shortreed and E. Laber and T.S. Stroup and J. Pineau and S.A. Murphy},
  title = {A multiple imputation strategy for sequential multiple assignment randomized trials},
  journal = {Statistics in Medicine},
  year = {2014},
  volume = {33},
  number = {24},
  pages = {4202-14},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24919867}
}
Sim I, Tu S, Carini S, Lehmann H, Pollock B, Peleg M and Wittkowski K (2014), "The Ontology of Clinical Research (OCRe): an informatics foundation for the science of clinical research.", Journal of Biomedical Informatics.. Thesis at: Department of Research Design and Biostatistics, The Rockefeller University, New York, NY, United States.. Vol. 52, pp. 78-91.
Abstract: To date, the scientific process for generating, interpreting, and applying knowledge has received less informatics attention than operational processes for conducting clinical studies. The activities of these scientific processes - the science of clinical research - are centered on the study protocol, which is the abstract representation of the scientific design of a clinical study. The Ontology of Clinical Research (OCRe) is an OWL 2 model of the entities and relationships of study design protocols for the purpose of computationally supporting the design and analysis of human studies. OCRe's modeling is independent of any specific study design or clinical domain. It includes a study design typology and a specialized module called ERGO Annotation for capturing the meaning of eligibility criteria. In this paper, we describe the key informatics use cases of each phase of a study's scientific lifecycle, present OCRe and the principles behind its modeling, and describe applications of OCRe and associated technologies to a range of clinical research use cases. OCRe captures the central semantics that underlies the scientific processes of clinical research and can serve as an informatics foundation for supporting the entire range of knowledge activities that constitute the science of clinical research.
BibTeX:
@article{Sim2014,
  author = {I. Sim and S.W. Tu and S. Carini and H.P. Lehmann and B.H. Pollock and M. Peleg and K.M. Wittkowski},
  title = {The Ontology of Clinical Research (OCRe): an informatics foundation for the science of clinical research.},
  journal = {Journal of Biomedical Informatics},
  school = {Department of Research Design and Biostatistics, The Rockefeller University, New York, NY, United States.},
  year = {2014},
  volume = {52},
  pages = {78--91},
  url = {http://dx.doi.org/10.1016/j.jbi.2013.11.002}
}
Small R, Whellan D, Boyle A, Sarkar S, Koehler J, Warman E and Abraham W (2014), "Implantable device diagnostics on day of discharge identify heart failure patients at increased risk for early readmission for heart failure", European journal of heart failure. Vol. 16(4), pp. 419-425. Wiley Online Library.
Abstract: AIMS: We hypothesized that diagnostic data in implantable devices evaluated on the day of discharge from a heart failure hospitalization (HFH) can identify patients at risk for HF readmission (HFR) within 30 days. METHODS AND RESULTS: In this retrospective analysis of four studies enrolling patients with CRT devices, we identified patients with a HFH, device data on the day of discharge, and 30-day post-discharge clinical follow-up. Four diagnostic criteria were evaluated on the discharge day: (i) intrathoracic impedance>8 ? below reference impedance; (ii) AF burden>6 h; (iii) CRT pacing<90%; and (iv) night heart rate>80 b.p.m. Patients were considered to have higher risk for HFR if ?2 criteria were met, average risk if 1 criterion was met, and lower risk if no criteria were met. A Cox proportional hazards model was used to compare the groups. The data cohort consisted of a total of 265 HFHs in 175 patients, of which 36 (14%) were followed by HFR. On the discharge day, ?2 criteria were met in 43 (16% of 265 HFHs), only 1 criterion was met in 92 (35%), and none of the four criteria were met in 130 HFHs (49%); HFR rates were 28, 16, and 7%, respectively. HFH with ?2 criteria met was five times more likely to have HFR compared with HFH with no criteria met (adjusted hazard ratio 5.0; 95% confidence interval 1.9–13.5
BibTeX:
@article{Small2014,
  author = {R.S. Small and D.J. Whellan and A. Boyle and S. Sarkar and J. Koehler and E.N. Warman and W.T. Abraham},
  title = {Implantable device diagnostics on day of discharge identify heart failure patients at increased risk for early readmission for heart failure},
  journal = {European journal of heart failure},
  publisher = {Wiley Online Library},
  year = {2014},
  volume = {16},
  number = {4},
  pages = {419--425},
  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24464745/}
}
Spring B, Moller A, Colangelo L, Siddique J, Roehrig M, Daviglus M, Polak J, Reis J, Sidney S and Liu K (2014), "Healthy lifestyle change and subclinical atherosclerosis in young adults: Coronary Artery Risk Development in Young Adults (CARDIA) study", Circulation. Vol. 130, pp. 10-17.
Abstract: BACKGROUND: The benefits of healthy habits are well established, but it is unclear whether making health behavior changes as an adult can still alter coronary artery disease risk. METHODS AND RESULTS: The Coronary Artery Risk Development in Young Adults (CARDIA) prospective cohort study (n=3538) assessed 5 healthy lifestyle factors (HLFs) among young adults aged 18 to 30 years (year 0 baseline) and 20 years later (year 20): not overweight/obese, low alcohol intake, healthy diet, physically active, nonsmoker. We tested whether change from year 0 to 20 in a continuous composite HLF score (HLF change; range, -5 to +5) is associated with subclinical atherosclerosis (coronary artery calcification and carotid intima-media thickness) at year 20, after adjustment for demographics, medications, and baseline HLFs. By year 20, 25.3% of the sample improved (HLF change ?+1); 40.4% deteriorated (had fewer HLFs); 34.4% stayed the same; and 19.2% had coronary artery calcification (>0). Each increase in HLFs was associated with reduced odds of detectable coronary artery calcification (odds ratio=0.85; 95% confidence interval, 0.74-0.98) and lower intima-media thickness (carotid bulb ?=-0.024
BibTeX:
@article{Spring2014,
  author = {B. Spring and A.C. Moller and L.A. Colangelo and J. Siddique and M. Roehrig and M.L. Daviglus and J.F. Polak and J.P. Reis and S. Sidney and K. Liu},
  title = {Healthy lifestyle change and subclinical atherosclerosis in young adults: Coronary Artery Risk Development in Young Adults (CARDIA) study},
  journal = {Circulation},
  year = {2014},
  volume = {130},
  pages = {10-17},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/24982115}
}
Srivastava M (2014), "In Sensors We Trust--A Realistic Possibility?", In 2014 IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS). , pp. 1-1.
Abstract: Sensors of diverse capabilities and modalities, carried by us or deeply embedded in the physical world, have invaded our personal, social, work, and urban spaces. Our relationship with these sensors is a complicated one. On the one hand, these sensors collect rich data that are shared and disseminated, often initiated by us, with a broad array of service providers, interest groups, friends, and family. Embedded in this data is information that can be used to algorithmically construct a virtual biography of our activities, revealing intimate behaviors and lifestyle patterns. On the other hand, we and the services we use, increasingly depend directly and indirectly on information originating from these sensors for making a variety of decisions, both routine and critical, in our lives. The quality of these decisions and our confidence in them depend directly on the quality of the sensory information and our trust in the sources. Sophisticated adversaries, benefiting from the same technology advances as the sensing systems, can manipulate sensory sources and analyze data in subtle ways to extract sensitive knowledge, cause erroneous inferences, and subvert decisions. The consequences of these compromises will only amplify as our society increasingly complex human-cyber-physical systems with increased reliance on sensory information and real-time decision cycles.Drawing upon examples of this two-faceted relationship with sensors in applications such as mobile health and sustainable buildings, this talk will discuss the challenges inherent in designing a sensor information flow and processing architecture that is sensitive to the concerns of both producers and consumer. For the pervasive sensing infrastructure to be trusted by both, it must be robust to active adversaries who are deceptively extracting private information, manipulating beliefs and subverting decisions. While completely solving these challenges would require a new science of resilient, secure and trustwor- hy networked sensing and decision systems that would combine hitherto disciplines of distributed embedded systems, network science, control theory, security, behavioral science, and game theory, this talk will provide some initial ideas. These include an approach to enabling privacy-utility trade-offs that balance the tension between risk of information sharing to the producer and the value of information sharing to the consumer, and method to secure systems against physical manipulation of sensed information.
BibTeX:
@inproceedings{Srivastava2014,
  author = {M.B. Srivastava},
  title = {In Sensors We Trust--A Realistic Possibility?},
  booktitle = {2014 IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS)},
  year = {2014},
  pages = {1--1},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=6846138&amp;isnumber=6846129}
}
Stewart D, Cano M, Correa-Fernández V, Spears C, Li Y, Waters A, Wetter D and Vidrine J (2014), "Lower health literacy predicts smoking relapse among racially/ethnically diverse smokers with low socioeconomic status", BMC Public Health. Vol. 14
Abstract: Background Nearly half of U.S. adults have difficulties with health literacy (HL), which is defined as the ability to adequately obtain, process, and understand basic health information. Lower HL is associated with negative health behaviors and poor health outcomes. Racial/ethnic minorities and those with low socioeconomic status (SES) are disproportionately affected by poor HL. They also have higher smoking prevalence and more difficulty quitting smoking. Thus, lower HL may be uniquely associated with poorer cessation outcomes in this population. Methods This study investigated the association between HL and smoking cessation outcomes among 200, low-SES, racially/ethnically diverse smokers enrolled in smoking cessation treatment. Logistic regression analyses adjusted for demographics (i.e., age, gender, race/ethnicity, relationship status), SES-related characteristics (i.e., education, income), and nicotine dependence were conducted to investigate associations between HL and smoking relapse at the end of treatment (3 weeks post quit day). Results Results indicated that smokers with lower HL (score of
BibTeX:
@article{Stewart2014,
  author = {D.W. Stewart and M.A. Cano and V. Correa-Fernández and C.A. Spears and Y. Li and A.J. Waters and D.W. Wetter and J.I. Vidrine},
  title = {Lower health literacy predicts smoking relapse among racially/ethnically diverse smokers with low socioeconomic status},
  journal = {BMC Public Health},
  year = {2014},
  volume = {14},
  url = {http://www.biomedcentral.com/1471-2458/14/716}
}
Stolper C, Kahng M, Lin Z, Foerster F, Goel A, Stasko J and Chau D (2014), "GLO-STIX: Graph-Level Operations for Specifying Techniques and Interactive eXploration", IEEE VIS 2014. IEEE.
Abstract: The field of graph visualization has produced a wealth of visualization techniques for accomplishing a variety of analysis tasks. Therefore analysts often rely on a suite of different techniques, and visual graph analysis application builders strive to provide this breadth of techniques. To provide a holistic model for specifying network visualization techniques (as opposed to considering each technique in isolation) we present the Graph-Level Operations (GLO) model. We describe a method for identifying GLOs and apply it to identify five classes of GLOs, which can be flexibly combined to re-create six canonical graph visualization techniques. We discuss advantages of the GLO model, including potentially discovering new, effective network visualization techniques and easing the engineering challenges of building multi-technique graph visualization applications. Finally, we implement the GLOs that we identified into the GLO-STIX prototype system that enables an analyst to interactively explore a graph by applying GLOs.
BibTeX:
@article{Stolper2014,
  author = {C.D. Stolper and M. Kahng and Z. Lin and F. Foerster and A. Goel and J. Stasko and D.H. Chau},
  title = {GLO-STIX: Graph-Level Operations for Specifying Techniques and Interactive eXploration},
  journal = {IEEE VIS 2014},
  publisher = {IEEE},
  year = {2014},
  url = {http://www.cc.gatech.edu/ dchau/papers/14-infovis-glo-stix.pdf}
}
Stolper C, Foerster F, Kahng M, Lin Z, Goel A, Stasko J and Chau D (2014), "GLOs: graph-level operations for exploratory network visualization", In 2014 ACM CHI Conference on Human Factors in Computing Systems (CHI 2014). , pp. 1375-1380.
Abstract: There is a wealth of visualization techniques available for graph and network visualization. However, each of these techniques was designed for a specific task. Many graph visualization techniques and the transitions between them can be specified using a set of operations on the visualization elements such as positioning or resizing nodes, showing or hiding edges, or showing or hiding axes. We term these operations Graph-Level Operations or GLOs. Our goal is to identify and provide a comprehensive set of these operations in order to better support the broadest range of graph and network analysis tasks. Here we present early results of our work, including a preliminary set of operations and an example application of GLOs in transitioning between familiar graph visualization techniques.
BibTeX:
@inproceedings{Stolper2014a,
  author = {C.D. Stolper and F. Foerster and M. Kahng and Z. Lin and A. Goel and J. Stasko and D.H. Chau},
  title = {GLOs: graph-level operations for exploratory network visualization},
  booktitle = {2014 ACM CHI Conference on Human Factors in Computing Systems (CHI 2014)},
  year = {2014},
  pages = {1375--1380},
  url = {http://www.cc.gatech.edu/ dchau/glo/glo_chi2014.pdf}
}
Swendeman D, Ramanathan N, Comulada W, Rotheram-Borus M and Estrin D (2014), "Efficacy Of Daily Self-Monitoring Of Health Behaviors And Quality Of Life By Mobile Phone: Mixed-Methods Results From Two Studies With Diverse Populations", In Annals of Behavioral Medicine. Vol. 47, pp. S263-S263.
BibTeX:
@incollection{Swendeman2014,
  author = {D. Swendeman and N. Ramanathan and W.S. Comulada and M.J. Rotheram-Borus and D. Estrin},
  title = {Efficacy Of Daily Self-Monitoring Of Health Behaviors And Quality Of Life By Mobile Phone: Mixed-Methods Results From Two Studies With Diverse Populations},
  booktitle = {Annals of Behavioral Medicine},
  year = {2014},
  volume = {47},
  pages = {S263--S263}
}
Swendeman D, Comulada W, Ramanathan N, Lazar M and Estrin D (2014), "Reliability and Validity of Daily Self-Monitoring by Smartphone Application for Health-Related Quality-of-Life, Antiretroviral Adherence, Substance Use, and Sexual Behaviors Among People Living with HIV", AIDS and Behavior. Vol. 19(2), pp. 330-340. Springer US.
Abstract: This paper examines inter-method reliability and validity of daily self-reports by smartphone application compared to 14-day recall web-surveys repeated over 6 weeks with people living with HIV (PLH). A participatory sensing framework guided participant-centered design prioritizing external validity of methods for potential applications in both research and self-management interventions. Inter-method reliability correlations were consistent with prior research for physical and mental health quality-of-life (r = 0.26–0.61), antiretroviral adherence (r = 0.70–0.73), and substance use (r = 0.65–0.92) but not for detailed sexual encounter surveys (r = 0.15–0.61). Concordant and discordant pairwise comparisons show potential trends in reporting biases, for example, lower recall reports of unprotected sex or alcohol use, and rounding up errors for frequent events. Event-based reporting likely compensated for modest response rates to daily time-based prompts, particularly for sexual and drug use behaviors that may not occur daily. Recommendations are discussed for future continuous assessment designs and analyses.
BibTeX:
@article{Swendeman2015,
  author = {D. Swendeman and W.S. Comulada and N. Ramanathan and M. Lazar and D. Estrin},
  title = {Reliability and Validity of Daily Self-Monitoring by Smartphone Application for Health-Related Quality-of-Life, Antiretroviral Adherence, Substance Use, and Sexual Behaviors Among People Living with HIV},
  journal = {AIDS and Behavior},
  publisher = {Springer US},
  year = {2014},
  volume = {19},
  number = {2},
  pages = {330-340},
  url = {http://dx.doi.org/10.1007/s10461-014-0923-8}
}
Tamersoy A, Roundy K and Chau D (2014), "Guilt by Association: Large Scale Malware Detection by Mining File-relation Graphs", In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, New York, USA , pp. 1524-1533. ACM.
Abstract: The increasing sophistication of malicious software calls for new defensive techniques that are harder to evade, and are capable of protecting users against novel threats. We present AESOP, a scalable algorithm that identifies malicious executable files by applying Aesop's moral that "a man is known by the company he keeps." We use a large dataset voluntarily contributed by the members of Norton Community Watch, consisting of partial lists of the files that exist on their machines, to identify close relationships between files that often appear together on machines. AESOP leverages locality-sensitive hashing to measure the strength of these inter-file relationships to construct a graph, on which it performs large scale inference by propagating information from the labeled files (as benign or malicious) to the preponderance of unlabeled files. AESOP attained early labeling of 99% of benign files and 79% of malicious files, over a week before they are labeled by the state-of-the-art techniques, with a 0.9961 true positive rate at flagging malware, at 0.0001 false positive rate.
BibTeX:
@inproceedings{Tamersoy:2014:GAL:2623330.2623342,
  author = {A. Tamersoy and K. Roundy and D.H. Chau},
  title = {Guilt by Association: Large Scale Malware Detection by Mining File-relation Graphs},
  booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  publisher = {ACM},
  year = {2014},
  pages = {1524--1533},
  url = {http://doi.acm.org/10.1145/2623330.2623342}
}
Tamersoy A, Khalil E, Xie B, Lenkey S, Routledge B, Chau D and Navathe S (2014), "Large-scale insider trading analysis: patterns and discoveries", Social Network Analysis and Mining. Vol. 4(1) Springer Vienna.
Abstract: How do company insiders trade? Do their trading behaviors differ based on their roles (e.g., chief executive officer vs. chief financial officer)? Do those behaviors change over time (e.g., impacted by the 2008 market crash)? Can we identify insiders who have similar trading behaviors? And what does that tell us? This work presents the first academic, large-scale exploratory study of insider filings and related data, based on the complete Form 4 fillings from the U.S. Securities and Exchange Commission. We analyze 12 million transactions by 370 thousand insiders spanning 1986–2012, the largest reported in academia. We explore the temporal and network-based aspects of the trading behaviors of insiders, and make surprising and counterintuitive discoveries. We study how the trading behaviors of insiders differ based on their roles in their companies, the types of their transactions, their companies’ sectors, and their relationships with other insiders. Our work raises exciting research questions and opens up many opportunities for future studies. Most importantly, we believe our work could form the basis of novel tools for financial regulators and policymakers to detect illegal insider trading, help them understand the dynamics of the trades, and enable them to adapt their detection strategies toward these dynamics.
BibTeX:
@article{Tamersoy2014,
  author = {A. Tamersoy and E. Khalil and B. Xie and S.L. Lenkey and B.R. Routledge and D.H. Chau and S.B. Navathe},
  title = {Large-scale insider trading analysis: patterns and discoveries},
  journal = {Social Network Analysis and Mining},
  publisher = {Springer Vienna},
  year = {2014},
  volume = {4},
  number = {1},
  url = {http://dx.doi.org/10.1007/s13278-014-0201-9}
}
Kumar S, al'Absi M, Beck J, Ertin E and Scott M (2014), "Behavioral Monitoring and Assessment via Mobile Sensing Technologies", In Leveraging Technology to Transform Behavioral Healthcare. , pp. 27-39. Oxford Press.
BibTeX:
@incollection{UMemphisCS2014-503,
  author = {S. Kumar and M. al'Absi and J.G. Beck and E. Ertin and M. Scott},
  editor = {L. Marsch and S. Lord and J. Dallery},
  title = {Behavioral Monitoring and Assessment via Mobile Sensing Technologies},
  booktitle = {Leveraging Technology to Transform Behavioral Healthcare},
  publisher = {Oxford Press},
  year = {2014},
  pages = {27-39}
}
Vhaduri S, Ali A, Sharmin M, Hovsepian K and Kumar S (2014), "Estimating Drivers' Stress from GPS Traces", In Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI '14). Seattle, WA, USA , pp. 20:1-20:8. ACM.
Abstract: Driving is known to be a daily stressor. Measurement of driver's stress in real-time can enable better stress management by increasing self-awareness. Recent advances in sensing technology has made it feasible to continuously assess driver's stress in real-time, but it requires equipping the driver with these sensors and/or instrumenting the car. In this paper, we present "GStress", a model to estimate driver's stress using only smartphone GPS traces. The GStress model is developed and evaluated from data collected in a mobile health user study where 10 participants wore physiological sensors for 7 days (for an average of 10.45 hours/day) in their natural environment. Each participant engaged in 10 or more driving episodes, resulting in a total of 37 hours of driving data. We find that major driving events such as stops, turns, and braking increase stress of the driver. We quantify their impact on stress and thus construct our GStress model by training a Generalized Linear Mixed Model (GLMM) on our data. We evaluate the applicability of GStress in predicting stress from GPS traces, and obtain a correlation of 0.72. By obviating any burden on the driver or the car, we believe, GStress can make driver's stress assessment ubiquitous.
BibTeX:
@inproceedings{Vhaduri:2014:EDS:2667317.2667335,
  author = {S. Vhaduri and A.A. Ali and M. Sharmin and K. Hovsepian and S. Kumar},
  title = {Estimating Drivers' Stress from GPS Traces},
  booktitle = {Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI '14)},
  publisher = {ACM},
  year = {2014},
  pages = {20:1--20:8},
  url = {http://doi.acm.org/10.1145/2667317.2667335}
}
Watkins K, Regan S, Nguyen N, Businelle M, Kendzor D, Lam C, Balis D, Cuevas A, Cao Y and Reitzel L (2014), "Advancing cessation research by integrating EMA and geospatial methodologies: associations between tobacco retail outlets and real-time smoking urges during a quit attempt", Nicotine Tob Res.. Vol. 16(Supplement 2), pp. S93-S101.
Abstract: INTRODUCTION: Residential tobacco retail outlet (TRO) density and proximity have been associated with smoking behaviors. More research is needed to understand the mechanisms underlying these relations and their potential relevance outside of the residential setting. This study integrates ecological momentary assessment (EMA) and geo-location tracking to explore real-time associations between exposure to TROs and smoking urges among 47 economically disadvantaged smokers in a cessation trial (59.6% female; 36.2% White). METHODS: EMA data were collected for 1 week postquit via smartphone, which recorded smoking urge strength ? 4 random times daily along with real-time participant location data. For each assessment, the participants' proximity to the closest TRO and the density of TROs surrounding the participant were calculated. Linear mixed model regressions examined associations between TRO variables and smoking urges and whether relations varied based on participants' distance from their home. Covariates included sociodemographics, prequit tobacco dependence, treatment group, and daily smoking status. RESULTS: Main effects were nonsignificant; however, the interaction between TRO proximity and distance from home was considered significant (p = .056). Specifically, closer proximity to TROs was associated with stronger smoking urges ? 1 mile of home (p = .001) but not >1 mile from home (p = .307). Significant associations were attributable to assessments completed at participants' home addresses. All density analyses were nonsignificant. CONCLUSIONS: Technological challenges encountered in this study resulted in a significant amount of missing data, highlighting the preliminary nature of these findings and limiting the inferences that can be drawn. However, results suggest that closer residential proximity to tobacco outlets may trigger stronger urges to smoke among economically disadvantaged smokers trying to quit, perhaps due to enhanced cigarette availability and accessibility. Therefore, limiting tobacco sales in close proximity to residential areas may complement existing tobacco control efforts and facilitate cessation.
BibTeX:
@article{Watkins2014,
  author = {K.L. Watkins and S.D. Regan and N. Nguyen and M.S. Businelle and D.E. Kendzor and C.Y. Lam and D. Balis and A.G. Cuevas and Y. Cao and L.R. Reitzel},
  title = {Advancing cessation research by integrating EMA and geospatial methodologies: associations between tobacco retail outlets and real-time smoking urges during a quit attempt},
  journal = {Nicotine Tob Res.},
  year = {2014},
  volume = {16},
  number = {Supplement 2},
  pages = {S93-S101},
  url = {http://ntr.oxfordjournals.org/content/16/Suppl_2/S93}
}
Yamaguchi M, Katagata H, Tezuka Y, Niwa D and Shetty V (2014), "Automated-immunosensor with centrifugal fluid valves for salivary cortisol measurement", Sensing and Bio-Sensing Research. Vol. 1(0), pp. 15 - 20.
Abstract: Abstract Point-of-care measurement of the stress hormone cortisol will greatly facilitate the timely diagnosis and management of stress-related disorders. We describe an automated salivary cortisol immunosensor, incorporating centrifugal fluid valves and a disposable disc-chip that allows for truncated reporting of cortisol levels (&lt;15&#xa0;min). The performance characteristics of the immunosensor are optimized through select blocking agents to prevent the non-specific adsorption of proteins; immunoglobulin G (IgG) polymer for the pad and milk protein for the reservoirs and the flow channels. Incorporated centrifugal fluid valves allow for rapid and repeat washings to remove impurities from the saliva samples. An optical reader and laptop computer automate the immunoassay processes and provide easily accessible digital readouts of salivary cortisol measurements. Linear regression analysis of the calibration curve for the cortisol immunosensor showed 0.92 of coefficient of multiple determination, R2, and 38.7% of coefficient of variation, CV, for a range of salivary cortisol concentrations between 0.4 and 11.3&#xa0;ng/mL. The receiver operating characteristic (ROC) curve analysis of human saliva samples indicate potential utility for discriminating stress disorders and underscore potential application of the biosensor in stress disorders. The performance of our salivary cortisol immunosensor approaches laboratory based tests and allows noninvasive, quantitative, and automated analysis of human salivary cortisol levels with reporting times compatible with point-of-care applications.
BibTeX:
@article{Yamaguchi201415,
  author = {M. Yamaguchi and H. Katagata and Y. Tezuka and D. Niwa and V. Shetty},
  title = {Automated-immunosensor with centrifugal fluid valves for salivary cortisol measurement},
  journal = {Sensing and Bio-Sensing Research},
  year = {2014},
  volume = {1},
  number = {0},
  pages = {15 - 20},
  url = {http://www.sciencedirect.com/science/article/pii/S2214180414000099}
}
Yonekura T, Takeda K, Shetty V and Yamaguchi M (2014), "Relationship between salivary cortisol and depression in adolescent survivors of a major natural disaster", The Journal of Physiological Sciences. , pp. 1-7. Springer.
Abstract: The purpose of this study was to determine the utility of salivary cortisol levels for screening mental states such as depression in adolescents following a natural disaster. We examined the relationship of salivary cortisol levels in adolescent survivors of the 2011 Tohoku Earthquake with the depression subscale of the 28-item General Health Questionnaire (GHQ). Subjects were 63 adolescent survivors (age = 14.29 years ± 0.51) who were administered the GHQ and provided saliva samples thrice daily (morning, afternoon and evening) over the course of 3 days. Based on the GHQ-depression subscores, subjects were divided into low and high depression groups. About 22 % of the subjects were classified into the high symptom group. When data collected over 3 days were used, a significant difference was observed between the two groups in the salivary cortisol levels at the evening time point as well the ratio of the morning/evening levels (p < 0.05). Analyzed by means of receiver-operating characteristic curves, the morning/evening ratios showed a good power in discriminating between subjects with and without depressive symptoms. Our study suggests that repeated measurement of salivary cortisol levels over 3 days has utility in screening for depressive states in adolescents following a natural disaster.
BibTeX:
@article{Yonekura2014,
  author = {T. Yonekura and K. Takeda and V. Shetty and M. Yamaguchi},
  title = {Relationship between salivary cortisol and depression in adolescent survivors of a major natural disaster},
  journal = {The Journal of Physiological Sciences},
  publisher = {Springer},
  year = {2014},
  pages = {1--7},
  url = {http://link.springer.com/content/pdf/10.1007%2Fs12576-014-0315-x.pdf}
}
Zaman K, Yli-Piipari S and Hnat T (2014), "Kinematic-based Sedentary and Light-intensity Activity Detection for Wearable Medical Applications", In Proceedings of the 1st Workshop on Mobile Medical Applications. Memphis, Tennessee , pp. 28-33. ACM.
Abstract: A sedentary lifestyle is becoming common for many individuals throughout the United States; however, this comes with a health cost of various preventable diseases such as cardiovascular disease, colon cancer, metabolic syndrome, and diabetes. Many times, individuals are completely unaware of how his or her health has deteriorated because of the slow progression or the demands of a job. We seek to bring attention to these problems by identifying specific sedentary activities and propose that just-in-time interventions could be used to help individuals overcome some of these problems. Our solution involves wearable sensors and utilizes a kinematic-based activity recognition systems to identify sedentary and light-intensity activities. Our system is evaluated with a series of laboratory experiments that include data from 34 individuals and a total of over 1400 minutes of activity. Results indicate that our system has a classification accuracy of up to 95.4 percent across all activities.
BibTeX:
@inproceedings{Zaman:2014:KSL:2676431.2676433,
  author = {K.I. Zaman and S.R. Yli-Piipari and T.W. Hnat},
  title = {Kinematic-based Sedentary and Light-intensity Activity Detection for Wearable Medical Applications},
  booktitle = {Proceedings of the 1st Workshop on Mobile Medical Applications},
  publisher = {ACM},
  year = {2014},
  pages = {28--33},
  url = {http://doi.acm.org/10.1145/2676431.2676433}
}
Zaman K, White A, Yli-Piipari S and Hnat T (2014), "K-Sense: Towards a Kinematic Approach for Measuring Human Energy Expenditure", In Wireless Sensor Networks. Vol. 8354, pp. 166-181. Springer International Publishing.
Abstract: Accurate energy expenditure monitoring will be an essential part of medical diagnosis in the future, enabling individually-tailored just-in-time interventions. However, there are currently no real-time monitors that are practical for continuous daily use. In this paper, we introduce the K-Sense energy expenditure monitor that uses inertial measurement units (IMUs) mounted to an individual’s wrist and ankle with elastic bands to determine angular velocity and position. The system utilizes kinematics to determine the amount of energy required for each limb to achieve its current movement. Our empirical evaluation includes over 3,000,000 individual data samples across 12 individuals and the results indicate that the system can estimate total energy expenditure with a 92 percent accuracy on average.
BibTeX:
@incollection{Zaman2014,
  author = {K.I. Zaman and A. White and S.R. Yli-Piipari and T.W. Hnat},
  editor = {B. Krishnamachari and A.L. Murphy and N. Trigoni},
  title = {K-Sense: Towards a Kinematic Approach for Measuring Human Energy Expenditure},
  booktitle = {Wireless Sensor Networks},
  publisher = {Springer International Publishing},
  year = {2014},
  volume = {8354},
  pages = {166-181},
  url = {http://dx.doi.org/10.1007/978-3-319-04651-8_11}
}
Zhang P, Hu P, Pasikanti V and Ganesan D (2014), "EkhoNet: high speed ultra low-power backscatter for next generation sensors", In Proceedings of the 20th Annual International Conference on Mobile Computing and Networking (MobiCom '14). , pp. 557-568.
BibTeX:
@inproceedings{Zhang2014,
  author = {P. Zhang and P. Hu and V. Pasikanti and D. Ganesan},
  title = {EkhoNet: high speed ultra low-power backscatter for next generation sensors},
  booktitle = {Proceedings of the 20th Annual International Conference on Mobile Computing and Networking (MobiCom '14)},
  year = {2014},
  pages = {557--568},
  url = {http://dl.acm.org/citation.cfm?id=2639138

http://people.cs.umass.edu/ dganesan/papers/Mobicom14-EkhoNet.pdf
} }
Zheng Z, Lu Z, Sinha P and Kumar S (2014), "Ensuring Predictable Contact Opportunity for Scalable Vehicular Internet Access On the Go", IEEE/ACM Trans. Netw.. IEEE.
Abstract: With increasing popularity of media enabled handhelds and their integration with the in-vehicle entertainment systems, the need for high data-rate services for mobile users on the go is evident. This ever-increasing demand of data is constantly surpassing what cellular networks can economically support. Large-scale Wireless LANs (WLANs) can provide such a service, but they are expensive to deploy and maintain. Open WLAN access-points, on the other hand, need no new deployments, but can offer only opportunistic services, lacking any performance guarantees. In contrast, a carefully planned sparse deployment of roadside WiFi provides an economically scalable infrastructure with quality of service assurance to mobile users. In this paper, we present a new metric, called Contact Opportunity, to closely model the quality of data service that a mobile user might experience when driving through the system. We then present efficient deployment algorithms for minimizing the cost for ensuring a required level of contact opportunity. We further extend this concept and the deployment techniques to a more intuitive metric – the average throughput – by taking various dynamic elements into account. Simulations over a real road network and experimental results show that our approach achieves significantly better cost vs. throughput tradeoff in both the worst case and average case compared with some commonly used deployment algorithms.
BibTeX:
@article{Zheng2014,
  author = {Z. Zheng and Z. Lu and P. Sinha and S. Kumar},
  title = {Ensuring Predictable Contact Opportunity for Scalable Vehicular Internet Access On the Go},
  journal = {IEEE/ACM Trans. Netw.},
  publisher = {IEEE},
  year = {2014},
  url = {http://arxiv.org/pdf/1401.0781v1}
}
Teng D and Ertin E (2015), "Learning to Aggregate Information for Sequential Inferences", ArXiv e-prints.
Abstract: We consider the problem of training a binary sequential classifier un-der an error rate constraint. It is well known that for known densities, accumulating the likelihood ratio statistics is time optimal under a fixed error rate constraint. For the case of unknown densities, we formulate the learning for sequential detection problem as a constrained density ratio estimation problem. Specifically, we show that the problem can be posed as a convex optimization problem using a Reproducing Kernel Hilbert Space representation for the log-density ratio function. The proposed bi-nary sequential classifier is tested on synthetic data set and UC Irvine human activity recognition data set, together with previous approaches for density ratio estimation. Our empirical results show that the classifier trained through the proposed technique achieves smaller average sampling cost than previous classifiers proposed in the literature for the same error rate.
BibTeX:
@article{2015arXiv150807964T,
  author = {Teng, D. and Ertin, E.},
  title = {Learning to Aggregate Information for Sequential Inferences},
  journal = {ArXiv e-prints},
  year = {2015},
  url = {https://md2k.org/images/papers/methods/Learning-to-Aggregate_Ertin16.pdf}
}
Abraham WT, Lindenfeld J, Reddy V, Hasenfuss G, Kuck K, Boscardin J, Gibbons R and Burkhoff D (2015), "A Randomized Controlled Trial to Evaluate the Safety and Efficacy of Cardiac Contractility Modulation in Patients With Moderately Reduced Left Ventricular Ejection Fraction and a Narrow QRS Duration: Study Rationale and Design", Journal of Cardiac Failure. Vol. 21(1), pp. 16 - 23.
Abstract: Abstract Cardiac contractility modulation (CCM) signals are nonexcitatory electrical signals delivered during the cardiac absolute refractory period that enhance the strength of cardiac muscular contraction. The FIX-HF-5 study was a prospective randomized study comparing CCM plus optimal medical therapy (OMT) to OMT alone that included 428 New York Heart Association (NYHA) functional class III or IV heart failure patients with ejection fraction (EF) ≤45% according to core laboratory assessment. The study met its primary safety end point, but did not reach its primary efficacy end point: a responders analysis of changes in ventilatory anaerobic threshold (VAT). However, in a prespecified subgroup analysis, significant improvements in primary and secondary end points, including the responder VAT end point, were observed in patients with EFs ranging from 25% to 45%, who constituted about one-half of the study subjects. We therefore designed a new study to prospectively confirm the efficacy of CCM in this population. A hierarchic bayesian statistical analysis plan was developed to take advantage of the data already available from the first study. In addition, based on technical difficulties encountered in reliably quantifying VAT and the relatively large amount of nonquantifiable studies, the primary efficacy end point was changed to peak VO2, with significant measures incorporated to minimize the influence of placebo effect. In this paper, we provide the details and rationale of the FIX-HF-5C study design to study CCM plus OMT compared with OMT alone in subjects with normal QRS duration, NYHA functional class III or IV, and EF 25% to 45%. This study is registered on www.clinicaltrials.gov with identifier no. NCT01381172.
BibTeX:
@article{Abraham201516,
  author = {W. T. Abraham and J. Lindenfeld and V.Y. Reddy and G. Hasenfuss and K. Kuck and J. Boscardin and R. Gibbons and D. Burkhoff},
  title = {A Randomized Controlled Trial to Evaluate the Safety and Efficacy of Cardiac Contractility Modulation in Patients With Moderately Reduced Left Ventricular Ejection Fraction and a Narrow QRS Duration: Study Rationale and Design},
  journal = {Journal of Cardiac Failure},
  year = {2015},
  volume = {21},
  number = {1},
  pages = {16 - 23},
  url = {http://www.sciencedirect.com/science/article/pii/S1071916414012214}
}
Pienta R, Lin Z, Kahng M, Vreeken J, Talukdar PP, Abello J, Parameswaran G and Chau. DH (2015), "AdaptiveNav: Adaptive Discovery of Interesting and Surprising Nodes in Large Graphs", In IEEE VIS.
BibTeX:
@inproceedings{AdaptiveNav,
  author = {Robert Pienta and Zhiyuan Lin and Minsuk Kahng and Jilles Vreeken and Partha P. Talukdar and James Abello and Ganesh Parameswaran and Duen Horng Chau.},
  title = {AdaptiveNav: Adaptive Discovery of Interesting and Surprising Nodes in Large Graphs},
  booktitle = {IEEE VIS},
  year = {2015}
}
Al-Bakri A, Jawad M, Salameh P, al'Absi M and Kassim S (2015), "Opportunistic insights into occupational health hazards associated with waterpipe tobacco smoking premises in the United kingdom.", Asian Pac J Cancer Prev.. Thesis at: Queen Mary, University of London, Barts and The London School of Medicine and Dentistry, Institute of Dentistry, London, UK E-mail : s.kassim@qmul.ac.uk.. Vol. 16(2), pp. 621-626.
Abstract: Smokefree laws aim to protect employees and the public from the dangers of secondhand smoke. Waterpipe premises have significantly increased in number in the last decade, with anecdotal reports of poor compliance with the smokefree law. The literature is bereft of information pertaining to waterpipe premise employees. This study aimed to opportunistically gather knowledge about the occupational health hazards associated with working in waterpipe premises in London, England.Employees from seven convenience-sampled, smokefree-compliant waterpipe premises in London were observed for occupational activities. Opportunistic carbon monoxide (CO) measurements were made among those with whom a rapport had developed. Observations were thematically coded and analysed.Occupational hazards mainly included environmental smoke exposure. Waterpipe-serving employees were required to draw several puffs soon after igniting the coals, thereby providing quality assurance of the product. Median CO levels were 27.5ppm (range 21-55ppm) among these employees. Self-reported employee health was poor, with some suggestion that working patterns and smoke exposure was a contributory factor.The smokefree law in England does not appear to protect waterpipe premise employees from high levels of CO. Continued concerns surrounding chronic smoke exposure may contribute to poor self-reported physical and mental wellbeing.
BibTeX:
@article{Al-Bakri2015,
  author = {A. Al-Bakri and M. Jawad and P. Salameh and M. al'Absi and S. Kassim},
  title = {Opportunistic insights into occupational health hazards associated with waterpipe tobacco smoking premises in the United kingdom.},
  journal = {Asian Pac J Cancer Prev},
  school = {Queen Mary, University of London, Barts and The London School of Medicine and Dentistry, Institute of Dentistry, London, UK E-mail : s.kassim@qmul.ac.uk.},
  year = {2015},
  volume = {16},
  number = {2},
  pages = {621--626},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/25684497}
}
Allen A, al'Absi M, Lando H and Allen S (2015), "Allopregnanolone association with psychophysiological and cognitive functions during acute smoking abstinence in premenopausal women.", Experimental and Clinical Psychopharmacology.. Thesis at: Community Health.. Vol. 23(1), pp. 22-28.
Abstract: Nicotine response may predict susceptibility to smoking relapse. Allopregnanolone, a neuroactive steroid metabolized from progesterone, has been shown to be associated with several symptoms of nicotine response. We sought to explore the association between allopregnanolone and response to nicotine during acute smoking abstinence in premenopausal women. Participants completed 2 nicotine-response laboratory sessions, 1 in their follicular (low allopregnanolone) and 1 in their luteal (high allopregnanolone) menstrual phase, on the fourth day of biochemically confirmed smoking abstinence. During the laboratory sessions, participants self-administered a nicotine nasal spray and completed a timed series of cardiovascular, cognitive, and subjective assessments of response to nicotine. The relationships of allopregnanolone with baseline values and change scores of outcome measures were assessed using covariance pattern modeling. Study participants (N = 77) had a mean age of 29.9 (SD = 6.8) years and smoked an average of 12.2 (SD = 4.9) cigarettes per day. Allopregnanolone concentration measured before nicotine administration was positively associated with systolic (? = 0.85
BibTeX:
@article{Allen2015,
  author = {A.M. Allen and M. al'Absi and H. Lando and S.S. Allen},
  title = {Allopregnanolone association with psychophysiological and cognitive functions during acute smoking abstinence in premenopausal women.},
  journal = {Experimental and Clinical Psychopharmacology},
  school = {Community Health.},
  year = {2015},
  volume = {23},
  number = {1},
  pages = {22--28},
  url = {http://dx.doi.org/10.1037/a0038747}
}
Allen A, Lunos S, Heishman S, al'Absi M, Hatsukami D and Allen S (2015), "Subjective response to nicotine by menstrual phase.", Addictive Behavior.. Thesis at: Community Health, Medical School, University of Minnesota, Minneapolis, MN 55414, USA.. Vol. 43, pp. 50-53.
Abstract: The luteal menstrual phase might be a favorable time for smoking cessation when non-nicotine interventions (e.g. counseling, bupropion) are used, whereas the follicular menstrual phase appears favorable when nicotine interventions are used. Thus, there may be an interaction between menstrual phase and response to nicotine. We sought to examine the role of menstrual phase on response to nicotine during acute smoking abstinence.In this controlled cross-over trial, women completed two identical experimental sessions (follicular [F] vs. luteal [L] phase) after four days of biochemically-verified smoking abstinence. During the sessions, nicotine nasal spray was administered, and participants provided a series of subjective assessments.Participants (n=140) were 29.7±6.6years old and smoked 12.6±5.8 cigarettes per day. Compared to the F phase, the L phase was associated with a greater increase in stimulation (7.2±2.2 vs. 14.4±2.3
BibTeX:
@article{Allen2015a,
  author = {A.M. Allen and S. Lunos and S.J. Heishman and M. al'Absi and D. Hatsukami and S.S. Allen},
  title = {Subjective response to nicotine by menstrual phase.},
  journal = {Addictive Behavior},
  school = {Community Health, Medical School, University of Minnesota, Minneapolis, MN 55414, USA.},
  year = {2015},
  volume = {43},
  pages = {50--53},
  url = {http://dx.doi.org/10.1016/j.addbeh.2014.12.008}
}
Amat-Santos I, Bergeron S, Bernier M, Allende R, Ribeiro H, Urena M, Pibarot P, Verheye S, Keren G, Yaacoby M, Nitzan Y, Abraham W and Rodés-Cabau J (2015), "Left atrial decompression through unidirectional left-to-right interatrial shunt for the treatment of left heart failure: first-in-man experience with the V-Wave device.", EuroIntervention.. Thesis at: Lung Institute, Quebec City, Quebec, Canada.. Vol. 10(9), pp. 1127-1131.
Abstract: Elevated filling pressures of the left atrium (LA) are associated with poorer outcomes in patients with chronic heart failure. The V-Wave is a new percutaneously implanted device intended to decrease the LA pressure by the shunting of blood from the LA to the right atrium. This report describes the first-in-man experience with the V-Wave device.A 70-year-old man with a history of heart failure of ischaemic origin, left ventricular dysfunction (LVEF: 35%, pulmonary wedge: 19 mmHg), no right heart dysfunction, NYHA Class III and orthopnoea despite optimal treatment, was accepted for V-Wave device implantation. The device consists of an ePTFE encapsulated nitinol frame that is implanted at the level of the interatrial septum and contains a trileaflet pericardium tissue valve sutured inside which allows a unidirectional LA to right atrium shunt. The procedure was performed through a transfemoral venous approach under fluoroscopic and TEE guidance. The device was successfully implanted and the patient was discharged 24 hours after the procedure with no complications. At three-month follow-up a left-to-right shunt through the device was confirmed by TEE. The patient was in NYHA Class II, without orthopnoea, the Kansas City Cardiomyopathy index was 77.6 (from 39.1 at baseline) and NT-proBNP was 322 ng/mL (from 502 ng/mL at baseline). The QP/QS was 1.17 and the pulmonary wedge was 8 mmHg, with no changes in pulmonary pressure or right ventricular function.Left atrial decompression through a unidirectional left-to-right interatrial shunt represents a new concept for the treatment of patients with left ventricular failure. The present report shows the feasibility of applying this new therapy with the successful and uneventful implantation of the V-Wave device, which was associated with significant improvement in functional, quality of life and haemodynamic parameters at 90 days.
BibTeX:
@article{Amat-Santos2015,
  author = {I.J. Amat-Santos and S. Bergeron and M. Bernier and R. Allende and H.B. Ribeiro and M. Urena and P. Pibarot and S. Verheye and G. Keren and M. Yaacoby and Y. Nitzan and W.T. Abraham and J. Rodés-Cabau},
  title = {Left atrial decompression through unidirectional left-to-right interatrial shunt for the treatment of left heart failure: first-in-man experience with the V-Wave device.},
  journal = {EuroIntervention},
  school = {Lung Institute, Quebec City, Quebec, Canada.},
  year = {2015},
  volume = {10},
  number = {9},
  pages = {1127--1131},
  url = {http://www.pcronline.com/eurointervention/ahead_of_print/201405-07/}
}
Angarita GA, Natarajan A, Gaiser E, Parate A, Marlin B, Gueorguieva R, Ganesan D and Malison R (2015), "A remote wireless sensor network/electrocardiographic approach to discriminating cocaine use", Drug &amp; Alcohol Dependence. Vol. 146, pp. e209. Elsevier.
Abstract: Aims: To establish the sensitivity/specificity of a RWSN/ECG approach for discriminating cocaine use from other cardiovascular stimulants. Hypothesis: Wearable “on body” sensors will reliably distinguish cocaine-induced ECG changes from those induced by methylphenidate (MPH) and exercise.
BibTeX:
@article{Angarita2015,
  author = {G. A. Angarita and A. Natarajan and E.C. Gaiser and A. Parate and B. Marlin and R. Gueorguieva and D. Ganesan and R.T. Malison},
  title = {A remote wireless sensor network/electrocardiographic approach to discriminating cocaine use},
  journal = {Drug &amp; Alcohol Dependence},
  publisher = {Elsevier},
  year = {2015},
  volume = {146},
  pages = {e209},
  url = {http://www.drugandalcoholdependence.com/article/S0376-8716(14)01099-0/abstract}
}
Basole RC, Park H, Gupta M, Braunstein ML, Chau DH and Thompson M (2015), "A Visual Analytics Approach to Understanding Care Process Variation and Conformance", In Proceedings of the 2015 Workshop on Visual Analytics in Healthcare. Chicago, Illinois , pp. 6:1-6:8. ACM.
BibTeX:
@inproceedings{Basole:2015:VAA:2836034.2836040,
  author = {Basole, Rahul C. and Park, Hyunwoo and Gupta, Mayank and Braunstein, Mark L. and Chau, Duen Horng and Thompson, Michael},
  title = {A Visual Analytics Approach to Understanding Care Process Variation and Conformance},
  booktitle = {Proceedings of the 2015 Workshop on Visual Analytics in Healthcare},
  publisher = {ACM},
  year = {2015},
  pages = {6:1--6:8},
  url = {http://doi.acm.org/10.1145/2836034.2836040},
  doi = {10.1145/2836034.2836040}
}
Bayram M, Cyr JS and Abraham W (2015), "d-Ribose aids heart failure patients with preserved ejection fraction and diastolic dysfunction: a pilot study.", Ther Adv Cardiovasc Dis.. Thesis at: Cardiovascular Medicine, Ohio State University, Columbus, OH, USA..
Abstract: The incidence of heart failure continues to escalate with >550,000 newly diagnosed patients annually worldwide. More than half of the patients with heart failure have preserved ejection fraction or isolated diastolic dysfunction, for which no current effective therapies for diastolic dysfunction exist. Every cell requires adequate levels of high energy phosphates to maintain integrity and function. Previous studies have demonstrated that diastolic function is energy dependent and supplemental d-ribose has shown to improve diastolic dysfunction. This study investigated what role d-ribose might play in congestive heart failure patients with preserved systolic function and diastolic dysfunction.A total of 11 patients, New York Heart Association class II-IV, with clinical symptoms, normal left ventricular systolic function and echocardiographic evidence of diastolic dysfunction were enrolled after meeting inclusion criteria. Each patient received oral d-ribose (5 g/dose) for 6 weeks. Echocardiographic evaluation, cardiopulmonary metabolic testing and subjective questionnaire assessment were performed at baseline, 6 weeks and at 9 weeks (3 weeks after discontinuing d-ribose).An improvement in their tissue Doppler velocity (E'), which was maintained at 9 weeks, was demonstrated in 64% of the patients. Five patients showed an improvement in their ratio of early diastolic filling velocity (E) to early annulus relaxation velocity (E'). There was no appreciable difference in these measurements during valsalva or with leg raising and handgrip exercises. Four patients also had an improvement in their maximum predicted VO2 values; two demonstrated a worsening effect and no differences were noted in the remaining patients. Subjective assessment revealed a benefit in only one patient, worsening symptoms in one patient and no change in the remaining cohort.This pilot study revealed some beneficial trends with D-ribose even with this small cohort size. However, future investigations are necessary to further substantiate these observed benefits.
BibTeX:
@article{Bayram2015,
  author = {M. Bayram and J.A. St. Cyr and W.T. Abraham},
  title = {d-Ribose aids heart failure patients with preserved ejection fraction and diastolic dysfunction: a pilot study.},
  journal = {Ther Adv Cardiovasc Dis},
  school = {Cardiovascular Medicine, Ohio State University, Columbus, OH, USA.},
  year = {2015},
  url = {http://dx.doi.org/10.1177/1753944715572752}
}
Bettadapura V, Thomaz E, Parnami A, Abowd G and Essa I (2015), "Leveraging Context to Support Automated Food Recognition in Restaurants", In 2015 IEEE Winter Conference on Applications of Computer Vision (WACV). , pp. 580-587.
BibTeX:
@inproceedings{Bettadapura2015,
  author = {V. Bettadapura and E. Thomaz and A. Parnami and G.D. Abowd and I. Essa},
  title = {Leveraging Context to Support Automated Food Recognition in Restaurants},
  booktitle = {2015 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year = {2015},
  pages = {580--587},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7045937}
}
Botoseneanu A, Ambrosius W, Beavers D, de Rekeneire N, Anton S, Church T, Folta S, Goodpaster B, King A, Nicklas B, Spring B, Wang X, Gill T and Groups LIFES (2015), "Prevalence of metabolic syndrome and its association with physical capacity, disability, and self-rated health in lifestyle interventions and independence for elders study participants.", J Am Geriatr Soc.. Thesis at: Department of Health Policy Studies, University of Michigan, Ann Arbor, Dearborn, Michigan; Institute of Gerontology, University of Michigan, Ann Arbor, Dearborn, Michigan; Division of Geriatrics, Dep. Vol. 63(2), pp. 222-232.
Abstract: To evaluate the prevalence of metabolic syndrome (MetS) and its association with physical capacity, disability, and self-rated health in older adults at high risk of mobility disability, including those with and without diabetes mellitus.Cross-sectional analysis.Lifestyle Interventions and Independence for Elders (LIFE) Study.Community-dwelling sedentary adults aged 70 to 89 at high risk of mobility disability (Short Physical Performance Battery (SPPB) score ?9; mean 7.4 ± 1.6) (N = 1,535).Metabolic syndrome was defined according to the 2009 multiagency harmonized criteria; outcomes were physical capacity (400-m walk time, grip strength, SPPB score), disability (composite 19-item score), and self-rated health (5-point scale ranging from excellent to poor).The prevalence of MetS was 49.8% in the overall sample (83.2% of those with diabetes mellitus, 38.1% of those without). MetS was associated with stronger grip strength (mean difference (?) = 1.2 kg, P = .01) in the overall sample and in participants without diabetes mellitus and with poorer self-rated health (? = 0.1 kg, P < .001) in the overall sample only. No significant differences were found in 400-m walk time, SPPB score, or disability score between participants with and without MetS, in the overall sample or diabetes mellitus subgroups.Metabolic dysfunction is highly prevalent in older adults at risk of mobility disability, yet consistent associations were not observed between MetS and walking speed, lower extremity function, or self-reported disability after adjusting for known and potential confounders. Longitudinal studies are needed to investigate whether MetS accelerates declines in functional status in high-risk older adults and to inform clinical and public health interventions aimed at preventing or delaying disability in this group.
BibTeX:
@article{Botoseneanu2015,
  author = {A. Botoseneanu and W.T. Ambrosius and D.P. Beavers and N. de Rekeneire and S. Anton and T. Church and S.C. Folta and B.H. Goodpaster and A.C. King and B.J. Nicklas and B. Spring and X. Wang and T.M. Gill and L. I. F. E Study Groups},
  title = {Prevalence of metabolic syndrome and its association with physical capacity, disability, and self-rated health in lifestyle interventions and independence for elders study participants.},
  journal = {J Am Geriatr Soc},
  school = {Department of Health Policy Studies, University of Michigan, Ann Arbor, Dearborn, Michigan; Institute of Gerontology, University of Michigan, Ann Arbor, Dearborn, Michigan; Division of Geriatrics, Dep},
  year = {2015},
  volume = {63},
  number = {2},
  pages = {222--232},
  url = {http://onlinelibrary.wiley.com/doi/10.1111/jgs.13205/epdf}
}
Castro D, Hickson S, Bettadapura V, Thomaz E, Abowd G, Christensen H and Essa I (2015), "Predicting Daily Activities from Egocentric Images Using Deep Learning", In Proceedings of the 2015 ACM International Symposium on Wearable Computers. Osaka, Japan , pp. 75-82. ACM.
BibTeX:
@inproceedings{Castro:2015:PDA:2802083.2808398,
  author = {Castro, Daniel and Hickson, Steven and Bettadapura, Vinay and Thomaz, Edison and Abowd, Gregory and Christensen, Henrik and Essa, Irfan},
  title = {Predicting Daily Activities from Egocentric Images Using Deep Learning},
  booktitle = {Proceedings of the 2015 ACM International Symposium on Wearable Computers},
  publisher = {ACM},
  year = {2015},
  pages = {75--82},
  url = {http://doi.acm.org/10.1145/2802083.2808398},
  doi = {10.1145/2802083.2808398}
}
Chen TY-H, Ravindranath L, Deng S, Bahl P and Balakrishnan H (2015), "Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices", In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. New York, NY, USA , pp. 155-168. ACM.
Abstract: Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail significant computation, Glimpse runs them on server machines. When the latency between the server and mobile device is higher than a frame-time, this approach lowers object recognition accuracy. To regain accuracy, Glimpse uses an active cache of video frames on the mobile device. A subset of the frames in the active cache are used to track objects on the mobile, using (stale) hints about objects that arrive from the server from time to time. To reduce network bandwidth usage, Glimpse computes trigger frames to send to the server for recognizing and labeling. Experiments with Android smartphones and Google Glass over Verizon, AT&T, and a campus Wi-Fi network show that with hardware face detection support (available on many mobile devices), Glimpse achieves precision between 96.4% to 99.8% for continuous face recognition, which improves over a scheme performing hardware face detection and server-side recognition without Glimpse's techniques by between 1.8-2.5×. The improvement in precision for face recognition without hardware detection is between 1.6-5.5×. For road sign recognition, which does not have a hardware detector, Glimpse achieves precision between 75% and 80%; without Glimpse, continuous detection is non-functional (0.2%-1.9% precision).
BibTeX:
@inproceedings{Chen:2015:GCR:2809695.2809711,
  author = {Chen, Tiffany Yu-Han and Ravindranath, Lenin and Deng, Shuo and Bahl, Paramvir and Balakrishnan, Hari},
  title = {Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices},
  booktitle = {Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems},
  publisher = {ACM},
  year = {2015},
  pages = {155--168},
  url = {http://doi.acm.org/10.1145/2809695.2809711},
  doi = {10.1145/2809695.2809711}
}
Cordeiro F, Epstein D, Thomaz E, Bales E, Jagannathan A, Abowd G and Fogarty J (2015), "Barriers and Negative Nudges: Exploring Challenges in Food Journaling", In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI ’15). Submission.
Abstract: Although food journaling is understood to be both important and difficult, little work has empirically documented the specific challenges people experience with food journals. We identify key challenges in a qualitative study combining a survey of 141 current and lapsed food journalers with analysis of 5,526 posts in community forums for three mobile food journals. Analyzing themes in this data, we find and discuss barriers to reliable food entry, negative nudges caused by current techniques, and challenges with social features. Our results motivate research exploring a wider range of approaches to food journal design and technology.
BibTeX:
@conference{cordeiro2015barriers,
  author = {F. Cordeiro and D. Epstein and E. Thomaz and E. Bales and A.K. Jagannathan and G.D. Abowd and J. Fogarty},
  title = {Barriers and Negative Nudges: Exploring Challenges in Food Journaling},
  booktitle = {Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI ’15)},
  publisher = {Submission},
  year = {2015},
  note = {Accepted to International ACM Conference on Human Factors in Computing Systems (CHI) 2015, Seoul, Korea},
  url = {http://depstein.net/pubs/fcordeiro_chi15.pdf}
}
Costanzo M, Khayat R, Ponikowski P, Augostini R, Stellbrink C, Mianulli M and Abraham W (2015), "Mechanisms and Clinical Consequences of Untreated Central Sleep Apnea in Heart Failure.", Journal of the American College of Cardiology.. Thesis at: Division of Cardiovascular Medicine, The Ohio State University, Columbus, Ohio.., January, 2015. Vol. 65(1), pp. 72-84.
Abstract: Central sleep apnea (CSA) is a highly prevalent, though often unrecognized, comorbidity in patients with heart failure (HF). Data from HF population studies suggest that it may present in 30% to 50% of HF patients. CSA is recognized as an important contributor to the progression of HF and to HF-related morbidity and mortality. Over the past 2 decades, an expanding body of research has begun to shed light on the pathophysiologic mechanisms of CSA. Armed with this growing knowledge base, the sleep, respiratory, and cardiovascular research communities have been working to identify ways to treat CSA in HF with the ultimate goal of improving patient quality of life and clinical outcomes. In this paper, we examine the current state of knowledge about the mechanisms of CSA in HF and review emerging therapies for this disorder.
BibTeX:
@article{Costanzo2015,
  author = {M.R. Costanzo and R. Khayat and P. Ponikowski and R. Augostini and C. Stellbrink and M. Mianulli and W.T. Abraham},
  title = {Mechanisms and Clinical Consequences of Untreated Central Sleep Apnea in Heart Failure.},
  journal = {Journal of the American College of Cardiology},
  school = {Division of Cardiovascular Medicine, The Ohio State University, Columbus, Ohio.},
  year = {2015},
  volume = {65},
  number = {1},
  pages = {72--84},
  url = {http://dx.doi.org/10.1016/j.jacc.2014.10.025}
}
Cui Y, Robinson J, Engelmann J, Lam C, Minnix J, Karam-Hage M, Wetter D, Dani J, Kosten T and Cinciripini P (2015), "Reinforcement Sensitivity Underlying Treatment-Seeking Smokers' Affect, Smoking Reinforcement Motives, and Affective Responses.", Psychology of Addictive Behaviors.
Abstract: Nicotine dependence has been suggested to be related to reinforcement sensitivity, which encompasses behavioral predispositions either to avoid aversive (behavioral inhibition) or to approach appetitive (behavioral activation) stimuli. Reinforcement sensitivity may shape motives for nicotine use and offer potential targets for personalized smoking cessation therapy. However, little is known regarding how reinforcement sensitivity is related to motivational processes implicated in the maintenance of smoking. Additionally, women and men differ in reinforcement sensitivity, and such difference may cause distinct relationships between reinforcement sensitivity and motivational processes for female and male smokers. In this study, the authors characterized reinforcement sensitivity in relation to affect, smoking-related reinforcement motives, and affective responses, using self-report and psychophysiological measures, in over 200 smokers before treating them. The Behavioral Inhibition/Activation Scales (BIS/BAS; Carver & White, 1994) was used to measure reinforcement sensitivity. In female and male smokers, BIS was similarly associated with negative affect and negative reinforcement of smoking. However, positive affect was positively associated with BAS Drive scores in male smokers, and this association was reversed in female smokers. BIS was positively associated with corrugator electromyographic reactivity toward negative stimuli and left frontal electroencephalogram alpha asymmetry. Female and male smokers showed similar relationships for these physiological measures. These findings suggest that reinforcement sensitivity underpins important motivational processes (e.g., affect), and gender is a moderating factor for these relationships. Future personalized smoking intervention, particularly among more dependent treatment-seeking smokers, may experiment to target individual differences in reinforcement sensitivity. (PsycINFO Database Record (c) 2015 APA, all rights reserved).
BibTeX:
@article{Cui2015,
  author = {Y. Cui and J.D. Robinson and J.M. Engelmann and C.Y. Lam and J.A. Minnix and M. Karam-Hage and D.W. Wetter and J.A. Dani and T.R. Kosten and P.M. Cinciripini},
  title = {Reinforcement Sensitivity Underlying Treatment-Seeking Smokers' Affect, Smoking Reinforcement Motives, and Affective Responses.},
  journal = {Psychology of Addictive Behaviors},
  year = {2015},
  url = {http://dx.doi.org/10.1037/adb0000050}
}
Sugavanam N and Ertin E (2015), "Recovery guarantees for multifrequency chirp waveforms in compressed radar sensing", CoRR., January, 2015. Vol. abs/1508.07969
BibTeX:
@article{DBLP:journals/corr/SugavanamE15,
  author = {Nithin Sugavanam and Emre Ertin},
  title = {Recovery guarantees for multifrequency chirp waveforms in compressed radar sensing},
  journal = {CoRR},
  year = {2015},
  volume = {abs/1508.07969},
  url = {http://arxiv.org/abs/1508.07969}
}
Elmalaki S, Wanner L and Srivastava M (2015), "CAreDroid: Adaptation Framework for Android Context-Aware Applications", In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. Paris, France , pp. 386-399. ACM.
Abstract: Context-awareness is the ability of software systems to sense and adapt to their physical environment. Many contemporary mobile applications adapt to changing locations, connectivity states, and available energy resources. Nevertheless, there is little systematic support for context-awareness in mobile operating systems. Because of this, application developers must build their own context-awareness adaptation engines, dealing directly with sensors and polluting application code with complex adaptation decisions. However, with adequate support from the runtime system, context monitoring could be performed efficiently in the background and adaptation could happen automatically [1]. Application developers would then only be required to implement methods tailored to different contexts. Just as file and socket abstractions help applications handle traditional input, output, and communication; a context-aware runtime system could help applications adapt according to user behavior and physical context.
BibTeX:
@inproceedings{Elmalaki:2015:CAF:2789168.2790108,
  author = {Elmalaki, Salma and Wanner, Lucas and Srivastava, Mani},
  title = {CAreDroid: Adaptation Framework for Android Context-Aware Applications},
  booktitle = {Proceedings of the 21st Annual International Conference on Mobile Computing and Networking},
  publisher = {ACM},
  year = {2015},
  pages = {386--399},
  url = {https://md2k.org/images/papers/software/p35-elmalaki_caredroid.pdf},
  doi = {10.1145/2789168.2790108}
}
Gold M, Daubert C, Abraham W, Ghio S, Sutton M, Hudnall J, Cerkvenik J and Linde C (2015), "The effect of reverse remodeling on long-term survival in mildly symptomatic patients with heart failure receiving cardiac resynchronization therapy: Results of the REVERSE study.", Heart Rhythm.. Thesis at: Karolinska University Hospital, Stockholm, Sweden.. Vol. 12(3), pp. 524-530.
Abstract: Cardiac resynchronization therapy (CRT) reduces mortality, improves functional status, and induces reverse left ventricular remodeling in selected populations with heart failure (HF). The magnitude of reverse remodeling predicts survival with many HF medical therapies. However, there are few studies assessing the effect of remodeling on long-term survival with CRT.The purpose of this study was to assess the effect of CRT-induced reverse remodeling on long-term survival in patients with mildly symptomatic heart failure.The REsynchronization reVErses Remodeling in Systolic Left vEntricular Dysfunction trial was a multicenter, double-blind, randomized trial of CRT in patients with mild HF. Long-term follow-up of 5 years was preplanned. The present analysis was restricted to the 353 patients who were randomized to the CRT ON group with paired echocardiographic studies at baseline and 6 months postimplantation. The left ventricular end-systolic volume index (LVESVi) was measured in the core laboratory and was an independently powered end point of the REsynchronization reVErses Remodeling in Systolic Left vEntricular Dysfunction trial.A 68% reduction in mortality was observed in patients with ?15% decrease in LVESVi compared to the rest of the patients (P = .0004). Multivariable analysis showed that the change in LVESVi was a strong independent predictor (P = .0002), with a 14% reduction in mortality for every 10% decrease in LVESVi. Other remodeling parameters such as left ventricular end-diastolic volume index and ejection fraction had a similar association with mortality.The change in left ventricular end-systolic volume after 6 months of CRT is a strong independent predictor of long-term survival in mild HF.
BibTeX:
@article{Gold2015,
  author = {M.R. Gold and C. Daubert and W.T. Abraham and S. Ghio and M.S.J. Sutton and J.H. Hudnall and J. Cerkvenik and C. Linde},
  title = {The effect of reverse remodeling on long-term survival in mildly symptomatic patients with heart failure receiving cardiac resynchronization therapy: Results of the REVERSE study.},
  journal = {Heart Rhythm},
  school = {Karolinska University Hospital, Stockholm, Sweden.},
  year = {2015},
  volume = {12},
  number = {3},
  pages = {524--530},
  url = {http://dx.doi.org/10.1016/j.hrthm.2014.11.014}
}
Han Y, Faulkner M, Fritz H, Fadoju D, Muir A, Abowd G, Head L and Arriaga R (2015), "A Pilot Randomized Trial of Text-Messaging for Symptom Awareness and Diabetes Knowledge in Adolescents With Type 1 Diabetes", Journal of Pediatric Nursing. (0), pp. -.
Abstract: Adolescents with type 1 diabetes typically receive clinical care every 3&#xa0;months. Between visits, diabetes-related issues may not be frequently reflected, learned, and documented by the patients, limiting their self-awareness and knowledge about their condition. We designed a text-messaging system to help resolve this problem. In a pilot, randomized controlled trial with 30 adolescents, we examined the effect of text messages about symptom awareness and diabetes knowledge on glucose control and quality of life. The intervention group that received more text messages between visits had significant improvements in quality of life.
BibTeX:
@article{Han2015,
  author = {Y. Han and M.S. Faulkner and H. Fritz and D. Fadoju and A. Muir and G.D. Abowd and L. Head and R.I. Arriaga},
  title = {A Pilot Randomized Trial of Text-Messaging for Symptom Awareness and Diabetes Knowledge in Adolescents With Type 1 Diabetes},
  journal = {Journal of Pediatric Nursing},
  year = {2015},
  number = {0},
  pages = {-},
  url = {http://www.sciencedirect.com/science/article/pii/S0882596315000342}
}
He Z, Carini S, Sim I and Weng C (2015), "Visual aggregate analysis of eligibility features of clinical trials.", J Biomed Inform.. Thesis at: Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA. Electronic address: cw2384@cumc.columbia.edu..
Abstract: To develop a method for profiling the collective populations targeted for recruitment by multiple clinical studies addressing the same medical condition using one eligibility feature each time.Using a previously published database COMPACT as the backend, we designed a scalable method for visual aggregate analysis of clinical trial eligibility features. This method consists of four modules for eligibility feature frequency analysis, query builder, distribution analysis, and visualization, respectively. This method is capable of analyzing (1) frequently used qualitative and quantitative features for recruiting subjects for a selected medical condition, (2) distribution of study enrollment on consecutive value points or value intervals of each quantitative feature, and (3) distribution of studies on the boundary values, permissible value ranges, and value range widths of each feature. All analysis results were visualized using Google Charts API. Five recruited potential users assessed the usefulness of this method for identifying common patterns in any selected eligibility feature for clinical trial participant selection.We implemented this method as a Web-based analytical system called VITTA (Visual Analysis Tool of Clinical Study Target Populations). We illustrated the functionality of VITTA using two sample queries involving quantitative features BMI and HbA1c for conditions "hypertension" and "Type 2 diabetes", respectively. The recruited potential users rated the user-perceived usefulness of VITTA with an average score of 86.4/100.We contributed a novel aggregate analysis method to enable the interrogation of common patterns in quantitative eligibility criteria and the collective target populations of multiple related clinical studies. A larger-scale study is warranted to formally assess the usefulness of VITTA among clinical investigators and sponsors in various therapeutic areas.
BibTeX:
@article{He2015,
  author = {Z. He and S. Carini and I. Sim and C. Weng},
  title = {Visual aggregate analysis of eligibility features of clinical trials.},
  journal = {J Biomed Inform},
  school = {Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA. Electronic address: cw2384@cumc.columbia.edu.},
  year = {2015},
  url = {http://dx.doi.org/10.1016/j.jbi.2015.01.005}
}
Hinderaker K, Allen A, Tosun N, al'Absi M, Hatsukami D and Allen S (2015), "The effect of combination oral contraceptives on smoking-related symptomatology during short-term smoking abstinence.", Addictive Behavior.. Thesis at: Community Health, Medical School, University of Minnesota, 420 Delaware Street SE, Room A682, Minneapolis, MN 55455, United States. Electronic address: allen001@umn.edu.. Vol. 41, pp. 148-151.
Abstract: Although an estimated 25% of premenopausal smokers report using oral contraceptives (OC), little is known about how OC use may influence smoking cessation. The purpose of this study was to examine the difference in smoking-related symptomatology during acute smoking abstinence between women on a standardized combination OC (Tri-Sprintec(™)) compared to women not on OCs (no-OC). Participants were women aged 18-40 who smoked ?5 cigarettes/day and reported regular menstrual cycles. Using a controlled cross-over design, participants completed two six-day testing weeks: Low Progesterone Week (LPW; Follicular (F) phase in no-OC or 1st week of pills in OC) and High Progesterone Week (HPW; Luteal (L) phase in no-OC or 3rd week of pills in OC). Each testing week included daily assessment of symptomatology and biochemical confirmation of smoking status. During smoking abstinence, the OC group (n=14) reported significantly lower levels of positive affect (21.56±7.12 vs. 24.57±6.46; ?=3.63
BibTeX:
@article{Hinderaker2015,
  author = {K. Hinderaker and A.M. Allen and N. Tosun and M. al'Absi and D. Hatsukami and S.S. Allen},
  title = {The effect of combination oral contraceptives on smoking-related symptomatology during short-term smoking abstinence.},
  journal = {Addictive Behavior},
  school = {Community Health, Medical School, University of Minnesota, 420 Delaware Street SE, Room A682, Minneapolis, MN 55455, United States. Electronic address: allen001@umn.edu.},
  year = {2015},
  volume = {41},
  pages = {148--151},
  url = {http://dx.doi.org/10.1016/j.addbeh.2014.10.018}
}
Hovsepian K, al'Absi M, Ertin E, Kamarck T, Nakajima M and Kumar S (2015), "cStress: Towards a Gold Standard for Continuous Stress Assessment in the Mobile Environment", In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Osaka, Japan , pp. 493-504. ACM.
Abstract: Recent advances in mobile health have produced several new models for inferring stress from wearable sensors. But, the lack of a gold standard is a major hurdle in making clinical use of continuous stress measurements derived from wear-able sensors. In this paper, we present a stress model (called cStress) that has been carefully developed with attention to every step of computational modeling including data collec-tion, screening, cleaning, filtering, feature computation, nor-malization, and model training. More importantly, cStress was trained using data collected from a rigorous lab study with 21 participants and validated on two independently col-lected data sets — in a lab study on 26 participants and in a week-long field study with 20 participants. In testing, the model obtains a recall of 89% and a false positive rate of 5%on lab data. On field data, the model is able to predict each instantaneous self-report with an accuracy of 72%.
BibTeX:
@inproceedings{Hovsepian:2015:CTG:2750858.2807526,
  author = {Hovsepian, Karen and al'Absi, Mustafa and Ertin, Emre and Kamarck, Thomas and Nakajima, Motohiro and Kumar, Santosh},
  title = {cStress: Towards a Gold Standard for Continuous Stress Assessment in the Mobile Environment},
  booktitle = {Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2015},
  pages = {493--504},
  url = {http://doi.acm.org/10.1145/2750858.2807526},
  doi = {10.1145/2750858.2807526}
}
Hu P, Zhang P and Ganesan D (2015), "Laissez-Faire: Fully Asymmetric Backscatter Communication", In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication. London, United Kingdom , pp. 255-267. ACM.
BibTeX:
@inproceedings{Hu:2015:LFA:2785956.2787477,
  author = {Hu, Pan and Zhang, Pengyu and Ganesan, Deepak},
  title = {Laissez-Faire: Fully Asymmetric Backscatter Communication},
  booktitle = {Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication},
  publisher = {ACM},
  year = {2015},
  pages = {255--267},
  url = {http://doi.acm.org/10.1145/2785956.2787477},
  doi = {10.1145/2785956.2787477}
}
Interlandi M, Shah K, Tetali SD, Gulzar MA, Yoo S, Kim M, Millstein T and Condie T (2015), "Titian: Data Provenance Support in Spark", Proc. VLDB Endow.. Vol. 9(3), pp. 216-227. VLDB Endowment.
Abstract: Debugging data processing logic in Data-Intensive Scalable Computing (DISC) systems is a difficult and time consuming effort. Today's DISC systems offer very little tooling for debugging programs, and as a result programmers spend countless hours collecting evidence (e.g., from log files) and performing trial and error debugging. To aid this effort, we built Titian, a library that enables data provenance---tracking data through transformations---in Apache Spark. Data scientists using the Titian Spark extension will be able to quickly identify the input data at the root cause of a potential bug or outlier result. Titian is built directly into the Spark platform and offers data provenance support at interactive speeds---orders-of-magnitude faster than alternative solutions---while minimally impacting Spark job performance; observed overheads for capturing data lineage rarely exceed 30% above the baseline job execution time.
BibTeX:
@article{Interlandi:2015:TDP:2850583.2850595,
  author = {Interlandi, Matteo and Shah, Kshitij and Tetali, Sai Deep and Gulzar, Muhammad Ali and Yoo, Seunghyun and Kim, Miryung and Millstein, Todd and Condie, Tyson},
  title = {Titian: Data Provenance Support in Spark},
  journal = {Proc. VLDB Endow.},
  publisher = {VLDB Endowment},
  year = {2015},
  volume = {9},
  number = {3},
  pages = {216--227},
  url = {http://dl.acm.org/citation.cfm?id=2850583.2850595

https://md2k.org/images/papers/software/p216-interlandi_titian.pdf}, doi = {10.14778/2850583.2850595} }
Kennedy AP, Epstein DH, Jobes ML, Agage D, Tyburski M, Phillips KA, Ali AA, Bari R, Hossain SM, Hovsepian K, Rahman M, Ertin E, Kumar S and Preston KL (2015), "Continuous In-The-Field Measurement of Heart Rate: Correlates of Drug Use, Craving, Stress, and Mood in Polydrug Users", Drug and Alcohol Dependence. (0), pp. -.
Abstract: AbstractBackground Ambulatory physiological monitoring could clarify antecedents and consequences of drug use and could contribute to a sensor-triggered mobile intervention that automatically detects behaviorally risky situations. Our goal was to show that such monitoring is feasible and can produce meaningful data. Methods We assessed heart rate (HR) with AutoSense, a suite of biosensors that wirelessly transmits data to a smartphone, for up to four weeks in 40 polydrug users in opioid-agonist maintenance as they went about their daily lives. Participants also self-reported drug use, mood, and activities on electronic diaries. We compared HR with self-report using multilevel modeling (SAS Proc Mixed). Results Compliance with AutoSense was good; the data yield from the wireless electrocardiographs was 85.7%. HR was higher when participants reported cocaine use than when they reported heroin use (F(2,9)&#xa0;=&#xa0;250.3, p&lt;.0001) and was also higher as a function of the dose of cocaine reported (F(1,8)&#xa0;=&#xa0;207.7, p&lt;.0001). HR was higher when participants reported craving heroin (F(1,16)&#xa0;=&#xa0;230.9, p&lt;.0001) or cocaine (F(1,14)&#xa0;=&#xa0;157.2, p&lt;.0001) than when they reported of not craving. HR was lower (p&lt;.05) in randomly prompted entries in which participants reported feeling relaxed, feeling happy, or watching TV, and was higher when they reported feeling stressed, being hassled, or walking. Conclusions High-yield, high-quality heart-rate data can be obtained from drug users in their natural environment as they go about their daily lives, and the resultant data robustly reflect episodes of cocaine and heroin use and other mental and behavioral events of interest.
BibTeX:
@article{Kennedy2015,
  author = {Ashley P. Kennedy and David H. Epstein and Michelle L. Jobes and Daniel Agage and Matthew Tyburski and Karran A. Phillips and Amin Ahsan Ali and Rummana Bari and Syed Monowar Hossain and Karen Hovsepian and Mahbubur Rahman and Emre Ertin and Santosh Kumar and Kenzie L. Preston},
  title = {Continuous In-The-Field Measurement of Heart Rate: Correlates of Drug Use, Craving, Stress, and Mood in Polydrug Users},
  journal = {Drug and Alcohol Dependence},
  year = {2015},
  number = {0},
  pages = {-},
  url = {http://www.sciencedirect.com/science/article/pii/S0376871615001805},
  doi = {10.1016/j.drugalcdep.2015.03.024}
}
Khayat R, Jarjoura D, Porter K, Sow A, Wannemacher J, Dohar R, Pleister A and Abraham W (2015), "Sleep disordered breathing and post-discharge mortality in patients with acute heart failure.", Eur Heart J.. Thesis at: Sleep Heart Program, The Ohio State University, Columbus, OH, USA Division of Cardiovascular Medicine, The Ohio State University, Columbus, OH, USA..
Abstract: Hospitalizations for heart failure are associated with a high post-discharge risk for mortality. Identification of modifiable predictors of post-discharge mortality during hospitalization may improve outcome. Sleep disordered breathing (SDB) is the most common co-morbidity in heart failure patients.Prospective cohort study of patients hospitalized with acute heart failure (AHF) in a single academic heart hospital. Between January 2007 and December 2010, all patients hospitalized with AHF who have left ventricular ejection fraction (LVEF) ? 45% and were not already diagnosed with SDB were the target population.Patients underwent in-hospital attended polygraphy testing for SDB and were followed for a median of 3 years post-discharge. Mortality was recorded using national and state vital statistics databases.During the study period, 1117 hospitalized AHF patients underwent successful sleep testing. Three hundred and forty-four patients (31%) had central sleep apnoea (CSA), 525(47%) patients had obstructive sleep apnoea (OSA), and 248 had no or minimal SDB (nmSDB). Of those, 1096 patients survived to discharge and were included in the mortality analysis. Central sleep apnoea was independently associated with mortality. The multivariable hazard ratio (HR) for time to death for CSA vs. nmSDB was 1.61 (95% CI: 1.1, 2.4
BibTeX:
@article{Khayat2015,
  author = {R. Khayat and D. Jarjoura and K. Porter and A. Sow and J. Wannemacher and R. Dohar and A. Pleister and W.T. Abraham},
  title = {Sleep disordered breathing and post-discharge mortality in patients with acute heart failure.},
  journal = {Eur Heart J},
  school = {Sleep Heart Program, The Ohio State University, Columbus, OH, USA Division of Cardiovascular Medicine, The Ohio State University, Columbus, OH, USA.},
  year = {2015},
  url = {http://dx.doi.org/10.1093/eurheartj/ehu522}
}
Klasnja P, Hekler E, Shiffman S, Boruvka A, Almirall D, Tewari A and Murphy S (2015), "Microrandomized trials: An experimental design for developing just-in-time adaptive interventions", Health Psychology. Vol. 34 (suppl), pp. 1220-1228.
Abstract: Objective: This article presents an experimental design, the microrandomized trial, developed to support optimization of just-in-time adaptive interventions (JITAIs). JITAIs are mHealth technologies that aim to deliver the right intervention components at the right times and locations to optimally support individuals’ health behaviors. Microrandomized trials offer a way to optimize such interventions by enabling modeling of causal effects and time-varying effect moderation for individual intervention components within a JITAI. Method: The article describes the microrandomized trial design, enumerates research questions that this experimental design can help answer, and provides an overview of the data analyses that can be used to assess the causal effects of studied intervention components and investigate time-varying moderation of those effects. Results: Microrandomized trials enable causal modeling of proximal effects of the randomized intervention components and assessment of time-varying moderation of those effects. Conclusion: Microrandomized trials can help researchers understand whether their interventions are having intended effects, when and for whom they are effective, and what factors moderate the interventions’ effects, enabling creation of more effective JITAIs. (PsycINFO Database Record (c) 2015 APA, all rights reserved)
BibTeX:
@article{Klasnja2015,
  author = {P. Klasnja and E.B. Hekler and S. Shiffman and A. Boruvka and D. Almirall and A. Tewari and S.A. Murphy},
  title = {Microrandomized trials: An experimental design for developing just-in-time adaptive interventions},
  journal = {Health Psychology},
  year = {2015},
  volume = {34 (suppl)},
  pages = {1220-1228},
  url = {https://md2k.org/images/papers/jitai/nihms732638_Klasnja.pdf},
  doi = {10.1037/hea0000305}
}
Kumar S, Abowd GD, Abraham WT, al’Absi M, Gayle Beck J, Chau DH, Condie T, Conroy DE, Ertin E, Estrin D, Ganesan D, Lam C, Marlin B, Marsh CB, Murphy SA, Nahum-Shani I, Patrick K, Rehg JM, Sharmin M, Shetty V, Sim I, Spring B, Srivastava M and Wetter DW (2015), "Center of excellence for mobile sensor data-to-knowledge (MD2K)", Journal of the American Medical Informatics Association. Vol. 22(6), pp. 1137-1142.
Abstract: Mobile sensor data-to-knowledge (MD2K) was chosen as one of 11 Big Data Centers of Excellence by the National Institutes of Health, as part of its Big Data-to-Knowledge initiative. MD2K is developing innovative tools to streamline the collection, integration, management, visualization, analysis, and interpretation of health data generated by mobile and wearable sensors. The goal of the big data solutions being developed by MD2K is to reliably quantify physical, biological, behavioral, social, and environmental factors that contribute to health and disease risk. The research conducted by MD2K is targeted at improving health through early detection of adverse health events and by facilitating prevention. MD2K will make its tools, software, and training materials widely available and will also organize workshops and seminars to encourage their use by researchers and clinicians.
BibTeX:
@article{Kumar2015,
  author = {Kumar, Santosh and Abowd, Gregory D and Abraham, William T and al’Absi, Mustafa and Gayle Beck, J and Chau, Duen Horng and Condie, Tyson and Conroy, David E and Ertin, Emre and Estrin, Deborah and Ganesan, Deepak and Lam, Cho and Marlin, Benjamin and Marsh, Clay B and Murphy, Susan A and Nahum-Shani, Inbal and Patrick, Kevin and Rehg, James M and Sharmin, Moushumi and Shetty, Vivek and Sim, Ida and Spring, Bonnie and Srivastava, Mani and Wetter, David W},
  title = {Center of excellence for mobile sensor data-to-knowledge (MD2K)},
  journal = {Journal of the American Medical Informatics Association},
  year = {2015},
  volume = {22},
  number = {6},
  pages = {1137-1142},
  url = { + http://dx.doi.org/10.1093/jamia/ocv056},
  doi = {10.1093/jamia/ocv056}
}
Lemieux A, Li B and al'Absi M (2015), "Khat use and appetite: an overview and comparison of amphetamine, khat and cathinone.", Journal of Ethnopharmacology.. Thesis at: University of Minnesota Medical School Duluth Campus, Duluth, MN, USA. Electronic address: malabsi@umn.edu.. Vol. 160, pp. 78-85.
Abstract: To understand the role of khat (Catha edulis) use on the aberrations in appetite and weight which are common comorbidities for khat and other amphetamine users.We provide a comprehensive overview and conceptual summary of the historical cultural use of khat as a natural stimulant and describe the similarities and differences between cathinone (the main psychoactive constituent of khat) and amphetamine highlighting the limited literature on the neurophysiology of appetite and subsequent weight effects of khat.Animal and some human studies indicate that khat produces appetite suppression, although little is known about mechanisms of this effect. Both direct and indirect effects of khat stem from multiple factors including behavioral, chemical and neurophysiological effects on appetite and metabolism. Classic and newly identified appetite hormones have not been explored sufficiently in the study of appetite and khat use. Unique methodological challenges and opportunities are encountered when examining effects of khat and cathinone including khat-specific medical comorbidities, unique route of administration, differential patterns of behavioral effects relative to amphetamines and the nascent state of our understanding of the neurobiology of this drug.A considerable amount of work remains in the study of the appetite effects of khat chewing and outline a program of research that could inform our understanding of this natural amphetamine?s appetite effects and help prepare health care workers for the unique health effects of this drug.
BibTeX:
@article{Lemieux2015,
  author = {A.M. Lemieux and B. Li and M. al'Absi},
  title = {Khat use and appetite: an overview and comparison of amphetamine, khat and cathinone.},
  journal = {Journal of Ethnopharmacology},
  school = {University of Minnesota Medical School Duluth Campus, Duluth, MN, USA. Electronic address: malabsi@umn.edu.},
  year = {2015},
  volume = {160},
  pages = {78--85},
  url = {http://dx.doi.org/10.1016/j.jep.2014.11.002}
}
Li Y, Ye Z and Rehg JM (2015), "Delving Into Egocentric Actions", In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Abstract: We address the challenging problem of recognizing the camera wearer's actions from videos captured by an egocentric camera. Egocentric videos encode a rich set of signals regarding the camera wearer, including head movement, hand pose and gaze information. We propose to utilize these mid-level egocentric cues for egocentric action recognition. We present a novel set of egocentric features and show how they can be combined with motion and object features. The result is a compact representation with superior performance. In addition, we provide the first systematic evaluation of motion, object and egocentric cues in egocentric action recognition. Our benchmark leads to several surprising findings. These findings uncover the best practices for egocentric actions, with a significant performance boost over all previous state-of-the-art methods on three publicly available datasets.
BibTeX:
@inproceedings{Li_2015_CVPR,
  author = {Yin Li and Zhefan Ye and James M. Rehg},
  title = {Delving Into Egocentric Actions},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2015}
}
Liao P, Klasnja P, Tewari A and Murphy S (2015), "Micro-Randomized Trials in mHealth", Statistics in Medicine.
Abstract: The use and development of mobile interventions is experiencing rapid growth. In “just-in-time” mobile
interventions, treatments are provided via a mobile device that are intended to help an individual make healthy decisions “in the moment,” and thus have a proximal, near future impact. Currently the development of mobile
interventions is proceeding at a much faster pace than that of associated data science methods. A first step
toward developing data-based methods is to provide an experimental design for use in testing the proximal effects of these just-in-time treatments. In this paper, we propose a “micro-randomized” trial design for this
purpose. In a micro-randomized trial, treatments are sequentially randomized throughout the conduct of the
study, with the result that each participant may be randomized at the 100s or 1000s of occasions at which a treatment might be provided. Further, we develop a test statistic for assessing the proximal effect of a treatment as well as an associated sample size calculator. We conduct simulation evaluations of the sample size calculator
in various settings. Rules of thumb that might be used in designing the micro-randomized trial are discussed. This work is motivated by our collaboration on the HeartSteps mobile application designed to increase physical activity.
BibTeX:
@article{liao2015micro,
  author = {P. Liao and P. Klasnja and A. Tewari and S.A. Murphy},
  title = {Micro-Randomized Trials in mHealth},
  journal = {Statistics in Medicine},
  year = {2015},
  url = {https://md2k.org/images/papers/jitai/nihms732638_Klasnja.pdf}
}
Liao P, Klasnja P, Tewari A and Murphy SA (2015), "Sample Size Calculations for Micro-randomized Trials in mHealth", Statistics in Medicine. Vol. 35(12), pp. 1944-1971.
Abstract: The use and development of mobile interventions are experiencing rapid growth. In “just-in-time” mobile interventions, treatments are provided via a mobile device and they are intended to help an individual make healthy decisions “in the moment,” and thus have a proximal, near future impact. Currently the development of mobile interventions is proceeding at a much faster pace than that of associated data science methods. A first step toward developing data-based methods is to provide an experimental design for testing the proximal effects of these just-in-time treatments. In this paper, we propose a “micro-randomized” trial design for this purpose. In a micro-randomized trial, treatments are sequentially randomized throughout the conduct of the study, with the result that each participant may be randomized at the 100s or 1000s of occasions at which a treatment might be provided. Further, we develop a test statistic for assessing the proximal effect of a treatment as well as an associated sample size calculator. We conduct simulation evaluations of the sample size calculator in various settings. Rules of thumb that might be used in designing a micro-randomized trial are discussed. This work is motivated by our collaboration on the HeartSteps mobile application designed to increase physical activity.
BibTeX:
@article{Liao2017,
  author = {Peng Liao and Predrag Klasnja and Ambuj Tewari and Susan A. Murphy},
  title = {Sample Size Calculations for Micro-randomized Trials in mHealth},
  journal = {Statistics in Medicine},
  year = {2015},
  volume = {35},
  number = {12},
  pages = {1944-1971},
  url = {https://md2k.org/images/papers/jitai/nihms744437_murphy.pdf},
  doi = {10.1002/sim.6847}
}
Mayberry A, Tun Y, Hu P, Smith-Freedman D, Ganesan D, Marlin BM and Salthouse C (2015), "CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass", In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. Paris, France , pp. 400-412. ACM.
BibTeX:
@inproceedings{Mayberry:2015:CER:2789168.2790096,
  author = {Mayberry, Addison and Tun, Yamin and Hu, Pan and Smith-Freedman, Duncan and Ganesan, Deepak and Marlin, Benjamin M. and Salthouse, Christopher},
  title = {CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass},
  booktitle = {Proceedings of the 21st Annual International Conference on Mobile Computing and Networking},
  publisher = {ACM},
  year = {2015},
  pages = {400--412},
  url = {http://doi.acm.org/10.1145/2789168.2790096},
  doi = {10.1145/2789168.2790096}
}
Nahum-Shani I, Smith S, Tewari A, Witkiewitz K, Collins L, Spring B and Murphy S (2015), "Just-in-time adaptive interventions (JITAIs): An organizing framework for ongoing health behavior support", Technical Report No. 14-126 The Methodology Center, Penn State.. Thesis at: The Methodology Center, Pennsylvania State University. Vol. 14(126)
Abstract: An emerging mobile phone intervention design, called the just-in-time adaptive intervention (JITAI), holds enormous potential for adapting mobile phone-delivered interventions to the dynamics of an individual’s emotional, social, physical and contextual state, so as to prevent negative health outcomes and promote the adoption and maintenance of healthy behaviors. A JITAI is an intervention design aiming to address the dynamically changing needs of individuals via the provision of the type/amount of support needed, at the right time, and only when needed. Despite the increasing use and the practical and conceptual appeal of JITAIs, a comprehensive organizing scientific framework to guide the construction of efficacious evidence-based JITAIs has yet to be provided. To bridge this gap, the current manuscript provides an organizing scientific framework to guide the construction of JITAIs. The key components of a JITAI are described and illustrated using examples of JITAIs from various domains of psychological and health behavior research. Design principles are discussed, as well as practical and theoretical challenges that require consideration in the process of constructing efficacious JITAIs.
BibTeX:
@techreport{nahumshani2014b,
  author = {I. Nahum-Shani and S.N. Smith and A. Tewari and K. Witkiewitz and L.M. Collins and B. Spring and S.A. Murphy},
  title = {Just-in-time adaptive interventions (JITAIs): An organizing framework for ongoing health behavior support},
  journal = {Technical Report No. 14-126 The Methodology Center, Penn State},
  school = {The Methodology Center, Pennsylvania State University},
  year = {2015},
  volume = {14},
  number = {126},
  url = {http://methodology.psu.edu/media/techreports/14-126.pdf}
}
Pellegrini C, Steglitz J, Johnston W, Warnick J, Adams T, McFadden H, Siddique J, Hedeker D and Spring B (2015), "Design and protocol of a randomized multiple behavior change trial: Make Better Choices 2 (MBC2).", Contemporary Clinical Trials.. Thesis at: Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, 680N. Lake Shore Drive, Suite 1400, Chicago, IL 60611, United States.. Vol. 41C, pp. 85-92.
Abstract: Suboptimal diet and inactive lifestyle are among the most prevalent preventable causes of premature death. Interventions that target multiple behaviors are potentially efficient; however the optimal way to initiate and maintain multiple health behavior changes is unknown.The Make Better Choices 2 (MBC2) trial aims to examine whether sustained healthful diet and activity change are best achieved by targeting diet and activity behaviors simultaneously or sequentially. Study design approximately 250 inactive adults with poor quality diet will be randomized to 3 conditions examining the best way to prescribe healthy diet and activity change. The 3 intervention conditions prescribe: 1) an increase in fruit and vegetable consumption (F/V+), decrease in sedentary leisure screen time (Sed-), and increase in physical activity (PA+) simultaneously (Simultaneous); 2) F/V+ and Sed- first, and then sequentially add PA+ (Sequential); or 3) Stress Management Control that addresses stress, relaxation, and sleep. All participants will receive a smartphone application to self-monitor behaviors and regular coaching calls to help facilitate behavior change during the 9month intervention. Healthy lifestyle change in fruit/vegetable and saturated fat intakes, sedentary leisure screen time, and physical activity will be assessed at 3, 6, and 9months.MBC2 is a randomized m-Health intervention examining methods to maximize initiation and maintenance of multiple healthful behavior changes. Results from this trial will provide insight about an optimal technology supported approach to promote improvement in diet and physical activity.
BibTeX:
@article{Pellegrini2015,
  author = {C.A. Pellegrini and J. Steglitz and W. Johnston and J. Warnick and T. Adams and H.G. McFadden and J. Siddique and D. Hedeker and B. Spring},
  title = {Design and protocol of a randomized multiple behavior change trial: Make Better Choices 2 (MBC2).},
  journal = {Contemporary Clinical Trials},
  school = {Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, 680N. Lake Shore Drive, Suite 1400, Chicago, IL 60611, United States.},
  year = {2015},
  volume = {41C},
  pages = {85--92},
  url = {http://dx.doi.org/10.1016/j.cct.2015.01.009}
}
Pellegrini C, Pfammatter A, Conroy D and Spring B (2015), "Smartphone applications to support weight loss: current perspectives", Journal of Advanced Healthcare Technologies. Vol. July 2015(1), pp. 13-22.
Abstract: Lower cost alternatives are needed for the traditional in-person behavioral weight loss programs to overcome challenges of lowering the worldwide prevalence of overweight and obesity. Smartphones have become ubiquitous and provide a unique platform to aid in the delivery of a behavioral weight loss program. The technological capabilities of a smartphone may address certain limitations of a traditional weight loss program, while also reducing the cost and burden on participants, interventionists, and health care providers. Awareness of the advantages smartphones offer for weight loss has led to the rapid development and proliferation of weight loss applications (apps). The built-in features and the mechanisms by which they work vary across apps. Although there are an extraordinary number of a weight loss apps available, most lack the same magnitude of evidence-based behavior change strategies typically used in traditional programs. As features develop and new capabilities are identified, we propose a conceptual model as a framework to guide the inclusion of features that can facilitate behavior change and lead to reductions in weight. Whereas the conventional wisdom about behavior change asserts that more is better (with respect to the number of behavior change techniques involved), this model suggests that less may be more because extra techniques may add burden and adversely impact engagement. Current evidence is promising and continues to emerge on the potential of smartphone use within weight loss programs; yet research is unable to keep up with the rapidly improving smartphone technology. Future studies are needed to refine the conceptual model's utility in the use of technology for weight loss, determine the effectiveness of intervention components utilizing smartphone technology, and identify novel and faster ways to evaluate the ever-changing technology.
BibTeX:
@article{Pelligrini2015,
  author = {C.A. Pellegrini and A.F. Pfammatter and D.E. Conroy and B. Spring},
  title = {Smartphone applications to support weight loss: current perspectives},
  journal = {Journal of Advanced Healthcare Technologies},
  year = {2015},
  volume = {July 2015},
  number = {1},
  pages = {13-22},
  url = {https://md2k.org/images/papers/jitai/nihms709018_pellegrini.pdf}
}
Pienta R, Tamersoy A, Tong H, Endert A and Chau D (2015), "Interactive Querying over Large Network Data: Scalability, Visualization, and Interaction Design", Proceedings of the 20th ACM Conference on Intelligent User Interfaces (IUI '15).
Abstract: Given the explosive growth of modern graph data, new methods are needed that allow for the querying of complex graph structures without the need of a complicated querying languages; in short, interactive graph querying is desirable. We describe our work towards achieving our overall research goal of designing and developing an interactive querying system for large network data. We focus on three critical aspects: scalable data mining algorithms, graph visualization, and interaction design. We have already completed an approximate subgraph matching system called MAGE in our previous work that fulfills the algorithmic foundation allowing us to query a graph with hundreds of millions of edges. Our preliminary work on visual graph querying, Graphite, was the first step in the process to making an interactive graph querying system. We are in the process of designing the graph visualization and robust interaction needed to make truly interactive graph querying a reality
BibTeX:
@article{pienta2015,
  author = {R. Pienta and A. Tamersoy and H. Tong and A. Endert and D.H. Chau},
  title = {Interactive Querying over Large Network Data: Scalability, Visualization, and Interaction Design},
  journal = {Proceedings of the 20th ACM Conference on Intelligent User Interfaces (IUI '15)},
  year = {2015},
  url = {http://www.cc.gatech.edu/ atamerso/papers/pienta_iui15.pdf}
}
Jr. PJP, Chen S-T, Kahng M, Sharmin M and Chau DH (2015), "TimeStitch: Interactive Multi-focus Cohort Discovery and Comparison", In IEEE VIS 2015 Chicago, IL, USA..
Abstract: Whereas event-based timelines for healthcare enable users to visualize the chronology of events surrounding events of interest, they are often not designed to aid the discovery, construction, or comparison of associated cohorts. We present TimeStitch, a system that helps health researchers discover and understand events that may cause abstinent smokers to lapse. TimeStitch
extracts common sequences of events performed by abstinent smokers from large amounts of mobile health sensor data, and offers a suite of interactive and visualization techniques to enable cohort discovery, construction, and comparison, using extracted sequences as interactive elements. We are extending TimeStitch to support more complex health conditions with high mortality risk, such as reducing hospital readmission in congestive heart failure.
BibTeX:
@inproceedings{Polack2015,
  author = {Peter J. Polack Jr. and Shang-Tse Chen and Minsuk Kahng and Moushumi Sharmin and Duen Horng Chau},
  title = {TimeStitch: Interactive Multi-focus Cohort Discovery and Comparison},
  booktitle = {IEEE VIS 2015 Chicago, IL, USA.},
  year = {2015}
}
Poncela-Casasnovas J, Spring B, McClary D, Moller A, Mukogo R, Pellegrini C, Coons M, Davidson M, Mukherjee S and Amaral LN (2015), "Social embeddedness in an online weight management programme is linked to greater weight loss.", the Journal of the Royal Society Interface.. Thesis at: Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL 60208, USA HHMI, Northwestern University, Evanston, IL 60208, USA Northwestern Institute on Complex Systems, No. Vol. 12(104)
Abstract: The obesity epidemic is heightening chronic disease risk globally. Online weight management (OWM) communities could potentially promote weight loss among large numbers of people at low cost. Because little is known about the impact of these online communities, we examined the relationship between individual and social network variables, and weight loss in a large, international OWM programme. We studied the online activity and weight change of 22 419 members of an OWM system during a six-month period, focusing especially on the 2033 members with at least one friend within the community. Using Heckman's sample-selection procedure to account for potential selection bias and data censoring, we found that initial body mass index, adherence to self-monitoring and social networking were significantly correlated with weight loss. Remarkably, greater embeddedness in the network was the variable with the highest statistical significance in our model for weight loss. Average per cent weight loss at six months increased in a graded manner from 4.1% for non-networked members, to 5.2% for those with a few (two to nine) friends, to 6.8% for those connected to the giant component of the network, to 8.3% for those with high social embeddedness. Social networking within an OWM community, and particularly when highly embedded, may offer a potent, scalable way to curb the obesity epidemic and other disorders that could benefit from behavioural changes.
BibTeX:
@article{Poncela-Casasnovas2015,
  author = {J. Poncela-Casasnovas and B. Spring and D. McClary and A.C. Moller and R. Mukogo and C.A. Pellegrini and M.J. Coons and M. Davidson and S. Mukherjee and L.A. Nunes Amaral},
  title = {Social embeddedness in an online weight management programme is linked to greater weight loss.},
  journal = {the Journal of the Royal Society Interface},
  school = {Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL 60208, USA HHMI, Northwestern University, Evanston, IL 60208, USA Northwestern Institute on Complex Systems, No},
  year = {2015},
  volume = {12},
  number = {104},
  url = {http://dx.doi.org/10.1098/rsif.2014.0686}
}
Rabbi M, Pfammatter A, Zhang M, Spring B and Choudhury T (2015), "Automated Personalized Feedback for Physical Activity and Dietary Behavior Change With Mobile Phones: A Randomized Controlled Trial on Adults", Journal of Medical Internet Research. Vol. 3(2), pp. e42.
Abstract: Background: A dramatic rise in health-tracking apps for mobile phones has occurred recently. Rich user interfaces make manual logging of users’ behaviors easier and more pleasant, and sensors make tracking effortless. To date, however, feedback technologies have been limited to providing overall statistics, attractive visualization of tracked data, or simple tailoring based on age, gender, and overall calorie or activity information. There are a lack of systems that can perform automated translation of behavioral data into specific actionable suggestions that promote healthier lifestyle without any human involvement.
Objective: MyBehavior, a mobile phone app, was designed to process tracked physical activity and eating behavior data in order to provide personalized, actionable, low-effort suggestions that are contextualized to the user’s environment and previous behavior. This study investigated the technical feasibility of implementing an automated feedback system, the impact of the suggestions on user physical activity and eating behavior, and user perceptions of the automatically generated suggestions.
Methods: MyBehavior was designed to (1) use a combination of automatic and manual logging to track physical activity (eg, walking, running, gym), user location, and food, (2) automatically analyze activity and food logs to identify frequent and nonfrequent behaviors, and (3) use a standard machine-learning, decision-making algorithm, called multi-armed bandit (MAB), to generate personalized suggestions that ask users to either continue, avoid, or make small changes to existing behaviors to help users reach behavioral goals. We enrolled 17 participants, all motivated to self-monitor and improve their fitness, in a pilot study of MyBehavior. In a randomized two-group trial, investigators randomly assigned participants to receive either MyBehavior’s personalized suggestions (n=9) or nonpersonalized suggestions (n=8), created by professionals, from a mobile phone app over 3 weeks. Daily activity level and dietary intake was monitored from logged data. At the end of the study, an in-person survey was conducted that asked users to subjectively rate their intention to follow MyBehavior suggestions.
Results: In qualitative daily diary, interview, and survey data, users reported MyBehavior suggestions to be highly actionable and stated that they intended to follow the suggestions. MyBehavior users walked significantly more than the control group over the 3 weeks of the study (P=.05). Although some MyBehavior users chose lower-calorie foods, the between-group difference was not significant (P=.15). In a poststudy survey, users rated MyBehavior’s personalized suggestions more positively than the nonpersonalized, generic suggestions created by professionals (P<.001).
Conclusions: MyBehavior is a simple-to-use mobile phone app with preliminary evidence of efficacy. To the best of our knowledge, MyBehavior represents the first attempt to create personalized, contextualized, actionable suggestions automatically from self-tracked information (ie, manual food logging and automatic tracking of activity). Lessons learned about the difficulty of manual logging and usability concerns, as well as future directions, are discussed.
BibTeX:
@article{Rabbi2015,
  author = {M Rabbi and A Pfammatter and M Zhang and B Spring and T Choudhury},
  title = {Automated Personalized Feedback for Physical Activity and Dietary Behavior Change With Mobile Phones: A Randomized Controlled Trial on Adults},
  journal = {Journal of Medical Internet Research},
  year = {2015},
  volume = {3},
  number = {2},
  pages = {e42},
  url = {https://md2k.org/images/papers/jitai/jmir_spring.pdf},
  doi = {10.2196/mhealth.4160}
}
Spruijt-Metz D, Hekler E, Saranummi N, Intille S, Korhonen I, Nilsen W, Rivera DE, Spring B, Michie S, Asch DA, Sanna A, Salcedo VT, Kukakfa R and Pavel M (2015), "Building new computational models to support health behavior change and maintenance: new opportunities in behavioral research", Translational Behavioral Medicine. Vol. 5(3), pp. 335-346. Springer US.
Abstract: Adverse and suboptimal health behaviors and habits are responsible for approximately 40 % of preventable deaths, in addition to their unfavorable effects on quality of life and economics. Our current understanding of human behavior is largely based on static “snapshots” of human behavior, rather than ongoing, dynamic feedback loops of behavior in response to ever-changing biological, social, personal, and environmental states. This paper first discusses how new technologies (i.e., mobile sensors, smartphones, ubiquitous computing, and cloud-enabled processing/computing) and emerging systems modeling techniques enable the development of new, dynamic, and empirical models of human behavior that could facilitate just-in-time adaptive, scalable interventions. The paper then describes concrete steps to the creation of robust dynamic mathematical models of behavior including: (1) establishing “gold standard” measures, (2) the creation of a behavioral ontology for shared language and understanding tools that both enable dynamic theorizing across disciplines, (3) the development of data sharing resources, and (4) facilitating improved sharing of mathematical models and tools to support rapid aggregation of the models. We conclude with the discussion of what might be incorporated into a “knowledge commons,” which could help to bring together these disparate activities into a unified system and structure for organizing knowledge about behavior.
BibTeX:
@article{raey,
  author = {Donna Spruijt-Metz and Eric Hekler and Niilo Saranummi and Stephen Intille and Ilkka Korhonen and Wendy Nilsen and Daniel E. Rivera and Bonnie Spring and Susan Michie and David A. Asch and Alberto Sanna and Vicente Traver Salcedo and Rita Kukakfa and Misha Pavel},
  title = {Building new computational models to support health behavior change and maintenance: new opportunities in behavioral research},
  journal = {Translational Behavioral Medicine},
  publisher = {Springer US},
  year = {2015},
  volume = {5},
  number = {3},
  pages = {335-346},
  url = {https://md2k.org/images/papers/jitai/TBM_Spring.pdf},
  doi = {10.1007/s13142-015-0324-1}
}
Rebar A, Ram N and Conroy D (2015), "Using the EZ-Diffusion Model to Score a Single-Category Implicit Association Test of Physical Activity.", Psychology of Sport &amp; Exercise.. Thesis at: The Pennsylvania State University, Department of Kinesiology ; The Pennsylvania State University, Department of Human Development and Family Studies.. Vol. 16(3), pp. 96-105.
Abstract: The Single-Category Implicit Association Test (SC-IAT) has been used as a method for assessing automatic evaluations of physical activity, but measurement artifact or consciously-held attitudes could be confounding the outcome scores of these measures. The objective of these two studies was to address these measurement concerns by testing the validity of a novel SC-IAT scoring technique.Study 1 was a cross-sectional study, and study 2 was a prospective study.In study 1, undergraduate students (N = 104) completed SC-IATs for physical activity, flowers, and sedentary behavior. In study 2, undergraduate students (N = 91) completed a SC-IAT for physical activity, self-reported affective and instrumental attitudes toward physical activity, physical activity intentions, and wore an accelerometer for two weeks. The EZ-diffusion model was used to decompose the SC-IAT into three process component scores including the information processing efficiency score.In study 1, a series of structural equation model comparisons revealed that the information processing score did not share variability across distinct SC-IATs, suggesting it does not represent systematic measurement artifact. In study 2, the information processing efficiency score was shown to be unrelated to self-reported affective and instrumental attitudes toward physical activity, and positively related to physical activity behavior, above and beyond the traditional D-score of the SC-IAT.The information processing efficiency score is a valid measure of automatic evaluations of physical activity.
BibTeX:
@article{Rebar2015,
  author = {A.L. Rebar and N. Ram and D.E. Conroy},
  title = {Using the EZ-Diffusion Model to Score a Single-Category Implicit Association Test of Physical Activity.},
  journal = {Psychology of Sport &amp; Exercise},
  school = {The Pennsylvania State University, Department of Kinesiology ; The Pennsylvania State University, Department of Human Development and Family Studies.},
  year = {2015},
  volume = {16},
  number = {3},
  pages = {96--105},
  url = {http://dx.doi.org/10.1016/j.psychsport.2014.09.008}
}
Steglitz J, Sommers M, Talen M, Thornton L and Spring B (2015), "Evaluation of an electronic health record-supported obesity management protocol implemented in a community health center: a cautionary note", Journal of the American Medical Informatics Association. The Oxford University Press.
Abstract: Jeremy Steglitz1, Mary Sommers2, Mary R Talen2, Louise K Thornton1,3 and Bonnie Spring11Department of Preventive Medicine, Northwestern University, 680 N Lake Shore Dr, Chicago, IL 60611, USA2Erie Family Health Center, Chicago, IL, USA3Priority Research Centre for Translational Neuroscience and Mental Health, University of Newcastle, AustraliaCorrespondence to Jeremy Steglitz, MPH, MS, Email: jeremy.steglitzatnorthwestern.edu, Tel: 312.503.1216Received August 6, 2014.Revision received October 31, 2014.Accepted November 24, 2014.Abstract Objective Primary care clinicians are well-positioned to intervene in the obesity epidemic. We studied whether implementation of an obesity intake protocol and electronic health record (EHR) form to guide behavior modification would facilitate identification and management of adult obesity in a Federally Qualified Health Center serving low-income, Hispanic patients. Materials and Methods In three studies, we examined clinician and patient outcomes before and after the addition of the weight management protocol and form. In the Clinician Study, 12 clinicians self-reported obesity management practices. In the Population Study, BMI and order data from 5000 patients and all 40 clinicians in the practice were extracted from the EHR preintervention and postintervention. In the Exposure Study, EHR-documented outcomes for a sub-sample of 46 patients actually exposed to the obesity management form were compared to matched controls. Results Clinicians reported that the intake protocol and form increased their performance of obesity-related assessments and their confidence in managing obesity. However, no improvement in obesity management practices or patient weight-loss was evident in EHR records for the overall clinic population. Further analysis revealed that only 55 patients were exposed to the form. Exposed patients were twice as likely to receive weight-loss counseling following the intervention, as compared to before, and more likely than matched controls. However, their obesity outcomes did not differ. Conclusion Results suggest that an obesity intake protocol and EHR-based weight management form may facilitate clinician weight-loss counseling among those exposed to the form. Significant implementation barriers can limit exposure, however, and need to be addressed. electronic health recordobesityprimary careevidence-based practicecommunity healthtextcopyright The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissionsatoup.com For numbered affiliations see end of article.
BibTeX:
@article{rohtua,
  author = {J. Steglitz and M. Sommers and M.R. Talen and L.K. Thornton and B. Spring},
  title = {Evaluation of an electronic health record-supported obesity management protocol implemented in a community health center: a cautionary note},
  journal = {Journal of the American Medical Informatics Association},
  publisher = {The Oxford University Press},
  year = {2015},
  url = {http://dx.doi.org/10.1093/jamia/ocu034}
}
Saleheen N, Ali AA, Hossain SM, Sarker H, Chatterjee S, Marlin B, Ertin E, al'Absi M and Kumar S (2015), "puffMarker: A Multi-sensor Approach for Pinpointing the Timing of First Lapse in Smoking Cessation", In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Osaka, Japan , pp. 999-1010. ACM.
Abstract: Recent researches have demonstrated the feasibility of detect-ing smoking from wearable sensors, but their performance on real-life smoking lapse detection is unknown. In this pa-per, we propose a new model and evaluate its performance on 61 newly abstinent smokers for detecting a first lapse. We use two wearable sensors — breathing pattern from respira-tion and arm movements from 6-axis inertial sensors worn on wrists. In 10-fold cross-validation on 40 hours of training data from 6 daily smokers, our model achieves a recall rate of 96.9%, for a false positive rate of 1.1%. When our model is applied to 3 days of post-quit data from 32 lapsers, it cor-rectly pinpoints the timing of first lapse in 28 participants. Only 2 false episodes are detected on 20 abstinent days of these participants. When tested on 84 abstinent days from 28 abstainers, the false episode per day is limited to 1/6.
BibTeX:
@inproceedings{Saleheen:2015:PMA:2750858.2806897,
  author = {Saleheen, Nazir and Ali, Amin Ahsan and Hossain, Syed Monowar and Sarker, Hillol and Chatterjee, Soujanya and Marlin, Benjamin and Ertin, Emre and al'Absi, Mustafa and Kumar, Santosh},
  title = {puffMarker: A Multi-sensor Approach for Pinpointing the Timing of First Lapse in Smoking Cessation},
  booktitle = {Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2015},
  pages = {999--1010},
  url = {http://doi.acm.org/10.1145/2750858.2806897},
  doi = {10.1145/2750858.2806897}
}
Shalaby A, Abraham W, Fonarow G, Bersohn M, Gorcsan. J, Lee L, Halilovic J, Saba S, Maisel A, Singh J, Sonel A and Kadish A (2015), "Association of BNP and Troponin Levels with Outcome among Cardiac Resynchronization Therapy Recipients.", Pacing &amp; Clinical Electrophysiology.. Thesis at: University of Pittsburgh, Pittsburgh, PA; VA Pittsburgh Healthcare System, Pittsburgh, PA..
Abstract: We conducted a prospective multicenter study to assess the prognostic value of combined baseline pre-implant plasma levels of the biomarkers cardiac troponin T (TnT) and BNP among CRT-D recipients.At CRT-D implant, patients were stratified based on detectable TnT (?0.01 ng/ml) and elevated BNP (predefined as >440 pg/ml) levels. Patients were classified into 3 groups high (both detectable TnT and high BNP), intermediate (either detectable TnT or high BNP), or low (non-detectable TnT and low BNP). Patients were followed for 12 months. Survival curves free from mortality or HFH were assessed. To assess the predictive value of biomarker category, we constructed a multivariate Cox regression model, including the covariates of age, NYHA class, LVEF, and QRS duration.A total of 267 patients (age 66 ± 12 years, males 80%, LVEF 25% ± 8%, ischemic CM 52%, QRSd 155 ± 26 ms) were studied. After one year, there were 13 deaths and 25 HFH events. A significant difference in event free survival among the 3 groups was observed, with high and intermediate categories having worse survival than low (log-rank test, p <0.001). In the multivariate model, risk category was a significant predictor of outcome: Hazard ratios were 7.34 (95% CI: 2.48 to 21.69) and 2.50 (95% CI: 1.04 to 6.04) for high and intermediate risk groups respectively (p<0.0001).Among CRT-D recipients, baseline TnT and BNP values alone or in combination provide significant prognostic value for the outcome of mortality or HFH. This article is protected by copyright. All rights reserved.
BibTeX:
@article{Shalaby2015,
  author = {A.A. Shalaby and W.T. Abraham and G.C. Fonarow and M.M. Bersohn and J. Gorcsan. and L. Lee and J. Halilovic and S. Saba and A. Maisel and J.P. Singh and A. Sonel and A. Kadish},
  title = {Association of BNP and Troponin Levels with Outcome among Cardiac Resynchronization Therapy Recipients.},
  journal = {Pacing &amp; Clinical Electrophysiology},
  school = {University of Pittsburgh, Pittsburgh, PA; VA Pittsburgh Healthcare System, Pittsburgh, PA.},
  year = {2015},
  url = {http://dx.doi.org/10.1111/pace.12610}
}
Sharma V, Rathman L, Small R, Whellan D, Koehler J, Warman E and Abraham W (2015), "Stratifying patients at the risk of heart failure hospitalization using existing device diagnostic thresholds", Heart &amp; Lung: The Journal of Acute and Critical Care. Vol. 44(2), pp. 129 - 136.
Abstract: AbstractBackground Heart failure hospitalizations (HFHs) cost the US health care system ∼$20 billion annually. Identifying patients at risk of HFH to enable timely intervention and prevent expensive hospitalization remains a challenge. Implantable cardioverter defibrillators (ICDs) and cardiac resynchronization devices with defibrillation capability (CRT-Ds) collect a host of diagnostic parameters that change with HF status and collectively have the potential to signal an increasing risk of HFH. These device-collected diagnostic parameters include activity, day and night heart rate, atrial tachycardia/atrial fibrillation (AT/AF) burden, mean rate during AT/AF, percent CRT pacing, number of shocks, and intrathoracic impedance. There are thresholds for these parameters that when crossed trigger a notification, referred to as device observation, which gets noted on the device report. We investigated if these existing device observations can stratify patients at varying risk of HFH. Methods We analyzed data from 775 patients (age: 69 ± 11 year, 68% male) with CRT-D devices followed for 13 ± 5 months with adjudicated HFHs. HFH rate was computed for increasing number of device observations. Data were analyzed by both excluding and including intrathoracic impedance. HFH risk was assessed at the time of a device interrogation session, and all the data between previous and current follow-up sessions were used to determine the HFH risk for the next 30 days. Results 2276 follow-up sessions in 775 patients were evaluated with 42 HFHs in 37 patients. Percentage of evaluations that were followed by an HFH within the next 30 days increased with increasing number of device observations. Patients with 3 or more device observations were at 42× HFH risk compared to patients with no device observation. Even after excluding intrathoracic impedance, the remaining device parameters effectively stratified patients at HFH risk. Conclusion Available device observations could provide an effective method to stratify patients at varying risk of heart failure hospitalization.
BibTeX:
@article{Sharma2015129,
  author = {V. Sharma and L.D. Rathman and R.S. Small and D.J. Whellan and J. Koehler and E. Warman and W.T. Abraham},
  title = {Stratifying patients at the risk of heart failure hospitalization using existing device diagnostic thresholds},
  journal = {Heart &amp; Lung: The Journal of Acute and Critical Care},
  year = {2015},
  volume = {44},
  number = {2},
  pages = {129 - 136},
  url = {http://www.sciencedirect.com/science/article/pii/S014795631400418X}
}
Sharmin M, Raij A, Epstien D, Nahum-Shani I, Beck JG, Vhaduri S, Preston K and Kumar S (2015), "Visualization of Time-series Sensor Data to Inform the Design of Just-in-time Adaptive Stress Interventions", In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Osaka, Japan , pp. 505-516. ACM.
Abstract: We investigate needs, challenges, and opportunities in visualizing time-series sensor data on stress to inform the design of just-in-time adaptive interventions (JITAIs). We identify seven key challenges: massive volume and variety of data, complexity in identifying stressors, scalability of space, multifaceted relationship between stress and time, a need for representation at multiple granularities, inter-person variability, and limited understanding of JITAI design requirements due to its novelty. We propose four new visualizations based on one million minutes of sensor data (n=70). We evaluate our visualizations with stress researchers (n=6) to gain first insights into its usability and usefulness in JITAI design. Our results indicate that spatio-temporal visualizations help identify and explain between- and within-person variability in stress patterns and contextual visualizations enable decisions regarding the timing, content, and modality of intervention. Interestingly, a granular representation is considered informative but noise-prone; an abstract representation is the preferred starting point for designing JITAIs.
BibTeX:
@inproceedings{Sharmin:2015:VTS:2750858.2807537,
  author = {Sharmin, Moushumi and Raij, Andrew and Epstien, David and Nahum-Shani, Inbal and Beck, J. Gayle and Vhaduri, Sudip and Preston, Kenzie and Kumar, Santosh},
  title = {Visualization of Time-series Sensor Data to Inform the Design of Just-in-time Adaptive Stress Interventions},
  booktitle = {Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2015},
  pages = {505--516},
  url = {http://doi.acm.org/10.1145/2750858.2807537},
  doi = {10.1145/2750858.2807537}
}
Dempsey W, Liao P, Klasnja P, Nahum-Shani I and Murphy SA (2015), "Randomised trials for the Fitbit generation", Significance. Vol. 12(6), pp. 20-23.
Abstract: Data from activity trackers and mobile phones can be used to craft personalised health interventions. But measuring the efficacy of these “treatments” requires a rethink of the traditional randomised trial. By Walter Dempsey, Peng Liao, Pedja Klasnja, Inbal Nahum-Shani and Susan A. Murphy
BibTeX:
@article{SIGN:SIGN863,
  author = {Walter Dempsey and Peng Liao and Pedja Klasnja and Inbal Nahum-Shani and Susan A. Murphy},
  title = {Randomised trials for the Fitbit generation},
  journal = {Significance},
  year = {2015},
  volume = {12},
  number = {6},
  pages = {20--23},
  url = {http://dx.doi.org/10.1111/j.1740-9713.2015.00863.x},
  doi = {10.1111/j.1740-9713.2015.00863.x}
}
Spring B, King AC, Pagoto SL, Horn LV and Fisher JD (2015), "Fostering multiple healthy lifestyle behaviors for primary prevention of cancer", American Psychologist. Vol. 70(2), pp. 75-90.
Abstract: The odds of developing cancer are increased by specific lifestyle behaviors (tobacco use, excess energy and alcohol intakes, low fruit and vegetable intake, physical inactivity, risky sexual behaviors, and inadequate sun protection) that are established risk factors for developing cancer. These behaviors are largely absent in childhood, emerge and tend to cluster over the life span, and show an increased prevalence among those disadvantaged by low education, low income, or minority status. Even though these risk behaviors are modifiable, few are diminishing in the population over time. We review the prevalence and population distribution of these behaviors and apply an ecological model to describe effective or promising healthy lifestyle interventions targeted to the individual, the sociocultural context, or environmental and policy influences. We suggest that implementing multiple health behavior change interventions across these levels could substantially reduce the prevalence of cancer and the burden it places on the public and the health care system. We note important still-unresolved questions about which behaviors can be intervened upon simultaneously in order to maximize positive behavioral synergies, minimize negative ones, and effectively engage underserved populations. We conclude that interprofessional collaboration is needed to appropriately determine and convey the value of primary prevention of cancer and other chronic diseases. (PsycINFO Database Record (c) 2015 APA, all rights reserved)
BibTeX:
@article{Spring2015,
  author = {Bonnie Spring and Abby C. King and Sherry L. Pagoto and Linda Van Horn and Jeffery D. Fisher},
  editor = {. , http://dx.doi.org/10.1037/a0038806},
  title = {Fostering multiple healthy lifestyle behaviors for primary prevention of cancer},
  journal = {American Psychologist},
  year = {2015},
  volume = {70},
  number = {2},
  pages = {75-90},
  url = {https://md2k.org/images/papers/jitai/nihms729492_spring.pdf},
  doi = {10.1037/a0038806}
}
Tamersoy A, De Choudhury M and Chau DH (2015), "Characterizing Smoking and Drinking Abstinence from Social Media", In Proceedings of the 26th ACM Conference on Hypertext &amp;#38; Social Media. Guzelyurt, Northern Cyprus , pp. 139-148. ACM.
BibTeX:
@inproceedings{Tamersoy:2015:CSD:2700171.2791247,
  author = {Tamersoy, Acar and De Choudhury, Munmun and Chau, Duen Horng},
  title = {Characterizing Smoking and Drinking Abstinence from Social Media},
  booktitle = {Proceedings of the 26th ACM Conference on Hypertext &amp;#38; Social Media},
  publisher = {ACM},
  year = {2015},
  pages = {139--148},
  url = {http://doi.acm.org/10.1145/2700171.2791247},
  doi = {10.1145/2700171.2791247}
}
Thanikachalam S, Harivanzan V, Mahadevan M, Murthy J, Anbarasi C, Saravanababu C, Must A, Baliga R, Abraham W and Thanikachalam M (2015), "Population Study of Urban, Rural, and Semiurban Regions for the Detection of Endovascular Disease and Prevalence of Risk Factors and Holistic Intervention Study (PURSE-HIS): Rationale, Study Design, and Baseline Characteristics", Global Heart., February, 2015. (0), pp. -.
Abstract: Abstract We designed and implemented the PURSE-HIS (Population Study of Urban, Rural and Semiurban Regions for the Detection of Endovascular Disease and Prevalence of Risk Factors and Holistic Intervention Study) to understand the prevalence and progression of subclinical and overt endovascular disease (EVD) and its risk factors in urban, semiurban, and rural communities in South India. The study is also designed to generate clinical evidence for effective, affordable, and sustainable community-specific intervention strategies to control risks factors for EVD. As of June 2012, 8,080 (urban: 2,221; semiurban: 2,821; rural: 3,038) participants &gt;20 years of age were recruited using 2-stage cluster sampling. Baseline measurements included standard cardiovascular disease risk factors, sociodemographic factors, lifestyle habits, psychosocial factors, and nutritional assessment. Fasting blood samples were assayed for putative biochemical risk factors and urine samples for microalbuminuria. All nondiabetic participants underwent oral glucose tolerance test with blood and urine samples collected every 30 min for 2 h. Additional baseline measurements included flow-mediated brachial artery endothelial vasodilation, assessment of carotid intimal medial wall thickness using ultrasonography, screening for peripheral vascular disease using ankle and brachial blood pressures, hemodynamic screening using a high-fidelity applanation tonometry to measure central blood pressure parameters, and aortic pulse wave velocity. To assess prevalence of coronary artery disease, all participants underwent surface electrocardiography and documentation of ventricular wall motion abnormality and function using echocardiography imaging. To detect subclinical lesions, all eligible participants completed an exercise treadmill test. Prospectively, the study will assess progression of subclinical and overt EVD, including risk factor–outcome relation differences across communities. The study will also evaluate community-specific EVD prevention using traditional Indian system of medicine versus recognized allopathic (mainstream) systems of medicine.
BibTeX:
@article{Thanikachalam2015,
  author = {S. Thanikachalam and V. Harivanzan and M.V. Mahadevan and J.S.N. Murthy and C. Anbarasi and C.S. Saravanababu and A. Must and R.R. Baliga and W.T. Abraham and M. Thanikachalam},
  title = {Population Study of Urban, Rural, and Semiurban Regions for the Detection of Endovascular Disease and Prevalence of Risk Factors and Holistic Intervention Study (PURSE-HIS): Rationale, Study Design, and Baseline Characteristics},
  journal = {Global Heart},
  year = {2015},
  number = {0},
  pages = {-},
  url = {http://www.sciencedirect.com/science/article/pii/S2211816014026696}
}
Thomaz E, Zhang C, Essa I and Abowd G (2015), "Inferring Meal Eating Activities in Real World Settings from Ambient Sounds: A Feasibility Study", In Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI '15). Atlanta, Georgia, USA , pp. 427-431. ACM.
Abstract: Dietary self-monitoring has been shown to be an effective method for weight-loss, but it remains an onerous task despite recent advances in food journaling systems. Semi-automated food journaling can reduce the effort of logging, but often requires that eating activities be detected automatically. In this work we describe results from a feasibility study conducted in-the-wild where eating activities were inferred from ambient sounds captured with a wrist-mounted device; twenty participants wore the device during one day for an average of 5 hours while performing normal everyday activities. Our system was able to identify meal eating with an F-score of 79.8% in a person-dependent evaluation, and with 86.6% accuracy in a person-independent evaluation. Our approach is intended to be practical, leveraging off-the-shelf devices with audio sensing capabilities in contrast to systems for automated dietary assessment based on specialized sensors.
BibTeX:
@inproceedings{Thomaz:2015:IME:2678025.2701405,
  author = {E. Thomaz and C. Zhang and I. Essa and G.D. Abowd},
  title = {Inferring Meal Eating Activities in Real World Settings from Ambient Sounds: A Feasibility Study},
  booktitle = {Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI '15)},
  publisher = {ACM},
  year = {2015},
  pages = {427--431},
  url = {http://doi.acm.org/10.1145/2678025.2701405}
}
Thomaz E, Essa I and Abowd GD (2015), "A Practical Approach for Recognizing Eating Moments with Wrist-mounted Inertial Sensing", In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Osaka, Japan , pp. 1029-1040. ACM.
Abstract: Recognizing when eating activities take place is one of the key challenges in automated food intake monitoring. Despite progress over the years, most proposed approaches have been largely impractical for everyday usage, requiring multiple on-body sensors or specialized devices such as neck collars for swallow detection. In this paper, we describe the implemen-tation and evaluation of an approach for inferring eating mo-ments based on 3-axis accelerometry collected with a popu-lar off-the-shelf smartwatch. Trained with data collected in a semi-controlled laboratory setting with 20 subjects, our sys-tem recognized eating moments in two free-living condition studies (7 participants, 1 day; 1 participant, 31 days), with F-scores of 76.1% (66.7% Precision, 88.8% Recall), and 71.3%(65.2% Precision, 78.6% Recall). This work represents a contribution towards the implementation of a practical, au-tomated system for everyday food intake monitoring, with applicability in areas ranging from health research and food journaling.
BibTeX:
@inproceedings{Thomaz:2015:PAR:2750858.2807545,
  author = {Thomaz, Edison and Essa, Irfan and Abowd, Gregory D.},
  title = {A Practical Approach for Recognizing Eating Moments with Wrist-mounted Inertial Sensing},
  booktitle = {Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2015},
  pages = {1029--1040},
  url = {http://doi.acm.org/10.1145/2750858.2807545},
  doi = {10.1145/2750858.2807545}
}
Weimer M, Chen Y, Chun B-G, Condie T, Curinoo C, Douglas C, Lee Y, Majestro T, Malkhi D, Matusevych S, Myers B, Narayanamurthy S, Ramakrishnan R, Rao S, Sears R, Sezgin B and Wang J (2015), "REEF: Retainable Evaluator Execution Framework", In Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. Melbourne, Victoria, Australia , pp. 1343-1355. ACM.
Abstract: In this demo proposal, we describe REEF, a framework that makes it easy to implement scalable, fault-tolerant runtime environments for a range of computational models. We will demonstrate diverse workloads, including extract-transform-load MapReduce jobs, iterative machine learning algorithms, and ad-hoc declarative query processing. At its core, REEF builds atop YARN (Apache Hadoop 2's resource manager) to provide retainable hardware resources with lifetimes that are decoupled from those of computational tasks. This allows us to build persistent (cross-job) caches and cluster-wide services, but, more importantly, supports high-performance iterative graph processing and machine learning algorithms. Unlike existing systems, REEF aims for composability of jobs across computational models, providing significant performance and usability gains, even with legacy code. REEF includes a library of interoperable data management primitives optimized for communication and data movement (which are distinct from storage locality). The library also allows REEF applications to access external services, such as user-facing relational databases. We were careful to decouple lower levels of REEF from the data models and semantics of systems built atop it. The result was two new standalone systems: Tang, a configuration manager and dependency injector, and Wake, a state-of-the-art event-driven programming and data movement framework. Both are language independent, allowing REEF to bridge the JVM and .NET.
BibTeX:
@inproceedings{Weimer:2015:RRE:2723372.2742793,
  author = {Markus Weimer and Yingda Chen and Byung-Gon Chun and Tyson Condie and Carlo Curinoo and Chris Douglas and Yunseong Lee and Tony Majestro and Dahlia Malkhi and Sergiy Matusevych and Brandon Myers and Shravan Narayanamurthy and Raghu Ramakrishnan and Sriram Rao and Russel Sears and Beysim Sezgin and Julia Wang},
  title = {REEF: Retainable Evaluator Execution Framework},
  booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data},
  publisher = {ACM},
  year = {2015},
  pages = {1343--1355},
  url = {https://md2k.org/images/papers/software/p1343-weimer_reef.pdf},
  doi = {10.1145/2723372.2742793}
}
Wilson K, Senay I, Durantini M, Sánchez F, Spring MHB and Albarracín D (2015), "When it comes to lifestyle recommendations, more is sometimes less", Psychological Bulletin. Vol. 141(2), pp. 474-509.
Abstract: A meta-analysis of 150 research reports summarizing the results of multiple behavior domain interventions examined theoretical predictions about the effects of the included number of recommendations on behavioral and clinical change in the domains of smoking, diet, and physical activity. The meta-analysis yielded 3 main conclusions. First, there is a curvilinear relation between the number of behavioral recommendations and improvements in behavioral and clinical measures, with a moderate number of recommendations producing the highest level of change. A moderate number of recommendations is likely to be associated with stronger effects because the intervention ensures the necessary level of motivation to implement the recommended changes, thereby increasing compliance with the goals set by the intervention, without making the intervention excessively demanding. Second, this curve was more pronounced when samples were likely to have low motivation to change, such as when interventions were delivered to nonpatient (vs. patient) populations, were implemented in nonclinic (vs. clinic) settings, used lay community (vs. expert) facilitators, and involved group (vs. individual) delivery formats. Finally, change in behavioral outcomes mediated the effects of number of recommended behaviors on clinical change. These findings provide important insights that can help guide the design of effective multiple behavior domain interventions. (PsycINFO Database Record (c) 2015 APA, all rights reserved)
BibTeX:
@article{Wilson2015,
  author = {Kristina Wilson and Ibrahim Senay and Marta Durantini and Flor Sánchez and Michael Hennessyand Bonnie Spring and Doloroes Albarracín},
  title = {When it comes to lifestyle recommendations, more is sometimes less},
  journal = {Psychological Bulletin},
  year = {2015},
  volume = {141},
  number = {2},
  pages = {474-509},
  url = {https://md2k.org/images/papers/jitai/nihms-635817_wilson.pdf},
  doi = {10.1037/a0038295}
}
Xu J, Mukherjee L, Li Y, Warner J, Rehg JM and Singh V (2015), "Gaze-Enabled Egocentric Video Summarization via Constrained Submodular Maximization", In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
BibTeX:
@inproceedings{Xu_2015_CVPR,
  author = {Jia Xu and Lopamudra Mukherjee and Yin Li and Jamieson Warner and James M. Rehg and Vikas Singh},
  title = {Gaze-Enabled Egocentric Video Summarization via Constrained Submodular Maximization},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2015}
}
Yang C, Maher J and Conroy D (2015), "Implementation of Behavior Change Techniques in Mobile Applications for Physical Activity.", American Journal of Preventive Medicine.. Thesis at: Department of Preventive Medicine, Northwestern University, Chicago, Illinois. Electronic address: conroy@northwestern.edu..
Abstract: Mobile applications (apps) for physical activity are popular and hold promise for promoting behavior change and reducing non-communicable disease risk. App marketing materials describe a limited number of behavior change techniques (BCTs), but apps may include unmarketed BCTs, which are important as well.To characterize the extent to which BCTs have been implemented in apps from a systematic user inspection of apps.Top-ranked physical activity apps (N=100) were identified in November 2013 and analyzed in 2014. BCTs were coded using a contemporary taxonomy following a user inspection of apps.Users identified an average of 6.6 BCTs per app and most BCTs in the taxonomy were not represented in any apps. The most common BCTs involved providing social support, information about others' approval, instructions on how to perform a behavior, demonstrations of the behavior, and feedback on the behavior. A latent class analysis of BCT configurations revealed that apps focused on providing support and feedback as well as support and education.Contemporary physical activity apps have implemented a limited number of BCTs and have favored BCTs with a modest evidence base over others with more established evidence of efficacy (e.g., social media integration for providing social support versus active self-monitoring by users). Social support is a ubiquitous feature of contemporary physical activity apps and differences between apps lie primarily in whether the limited BCTs provide education or feedback about physical activity.
BibTeX:
@article{Yang2015a,
  author = {C. Yang and J.P. Maher and D.E. Conroy},
  title = {Implementation of Behavior Change Techniques in Mobile Applications for Physical Activity.},
  journal = {American Journal of Preventive Medicine},
  school = {Department of Preventive Medicine, Northwestern University, Chicago, Illinois. Electronic address: conroy@northwestern.edu.},
  year = {2015},
  url = {https://md2k.org/images/papers/jitai/amjprevmed_conroy.pdf},
  doi = {10.1016/j.amepre.2014.10.010}
}
Ye Z, Yin L, Liu Y, Bridges C, Rozga A and Rehg JM (2015), "Detecting Bids for Eye Contact Using a Wearable Camera", In Detecting Bids for Eye Contact Using a Wearable Camera. IEEE.
Abstract: We propose a system for detecting bids for eye contact directed from a child to an adult who is wearing a point-of-view camera. The camera captures an egocentric view of the child-adult interaction from the adult’s perspective. We detect and analyze the child’s face in the egocentric video in order to automatically identify moments in which the child is trying to make eye contact with the adult. We present a learning-based method that couples a pose-dependent appearance model with a temporal Conditional Random Field (CRF). We present encouraging findings from an experimental evaluation using a newly collected dataset of 12 children. Our method outperforms state-of-the-art approaches and enables measuring gaze behavior in naturalistic social interactions.
BibTeX:
@inproceedings{Ye2015,
  author = {Zhefan Ye and Yin L and Yun Liu and Chanel Bridges and Agata Rozga and James M. Rehg},
  title = {Detecting Bids for Eye Contact Using a Wearable Camera},
  booktitle = {Detecting Bids for Eye Contact Using a Wearable Camera},
  publisher = {IEEE},
  year = {2015},
  url = {http://cbi.gatech.edu/eyecontact/}
}
Bekiroglu K, Lagoa C, Murphy SA and Lanza ST (2016), "Control Engineering Methods for the Design of Robust Behavioral Treatments", IEEE Transactions on Control Systems Technology. Vol. PP(99), pp. 1-12.
Abstract: In this paper, a robust control approach is used to address the problem of adaptive behavioral treatment design. Human behavior (e.g., smoking and exercise) and reactions to treatment are complex and depend on many unmeasurable external stimuli, some of which are unknown. Thus, it is crucial to model human behavior over many subject responses. We propose a simple (low order) uncertain affine model subject to uncertainties whose response covers the most probable behavioral responses. The proposed model contains two different types of uncertainties: uncertainty of the dynamics and external perturbations that patients face in their daily life. Once the uncertain model is defined, we demonstrate how least absolute shrinkage and selection operator (lasso) can be used as an identification tool. The lasso algorithm provides a way to directly estimate a model subject to sparse perturbations. With this estimated model, a robust control algorithm is developed, where one relies on the special structure of the uncertainty to develop efficient optimization algorithms. This paper concludes by using the proposed algorithm in a numerical experiment that simulates treatment for the urge to smoke.
BibTeX:
@article{7501575,
  author = {Korkut Bekiroglu and Constantino Lagoa and Susan A. Murphy and Stephanie T. Lanza},
  title = {Control Engineering Methods for the Design of Robust Behavioral Treatments},
  journal = {IEEE Transactions on Control Systems Technology},
  year = {2016},
  volume = {PP},
  number = {99},
  pages = {1-12},
  url = {https://md2k.org/images/papers/jitai/ieee_murphy2016.pdf},
  doi = {10.1109/TCST.2016.2580661}
}
Gao J, Teng D and Ertin E (2016), "ECG feature detection using randomly compressed samples for stable HRV analysis over low rate links", In 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN). , pp. 165-170.
Abstract: Wireless biosensors enable continuous monitoring of physiology and can provide early signs of imminent problems allowing for quick intervention and improved outcomes. Wireless communication of the sensor data for remote storage and analysis dominates the device power budget and puts severe constraints on lifetime and size of these sensors. Traditionally, to minimize the wireless communication bandwidth, data compression at the sensor node and signal reconstruction at the remote terminal is utilized. Here we consider an alternative strategy of feature detection with compressed samples without the intermediate step of signal reconstruction. Specifically, we present a compressed matched subspace detection algorithm to detect fiducial points of ECG waveform from streaming random projections of the data. We provide a theoretical analysis to compare the performance of the compressed matched detector performance to that of a matched detector operating with uncompressed data. We present extensive experimental results with ECG data collected in the field illustrating that the proposed system can provide high quality heart rate variability indices and achieve an order of magnitude better RMSE in beat-to-beat heart rate estimation than the traditional filter/downsample solutions at low data rates.
BibTeX:
@inproceedings{7516253,
  author = {J. Gao and D. Teng and E. Ertin},
  title = {ECG feature detection using randomly compressed samples for stable HRV analysis over low rate links},
  booktitle = {2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN)},
  year = {2016},
  pages = {165-170},
  url = {http://ieeexplore.ieee.org/document/7516253/},
  doi = {10.1109/BSN.2016.7516253}
}
Zhang C, Yang J, Southern C, Starner T and Abowd G (2016), "WatchOut: Extending Interactions on a Smartwatch with Inertial Sensing", In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing.
Abstract: Current interactions on a smartwatch are generally limited to a tiny touchscreen, physical buttons or knobs, and speech. We present WatchOut, a suite of interaction techniques that includes three families of tap and swipe gestures which extend input modalities to the watch's case, bezel, and band. We describe the implementation of a user-independent gesture recognition pipeline based on data from the watch's embedded inertial sensors. In a study with 12 participants using both a round- and square-screen watch, the average gesture classification accuracies ranged from 88.7% to 99.4%. We demonstrate applications of this richer interaction capability, and discuss the strengths, limitations, and future potential for this work.
BibTeX:
@inproceedings{Abowd2016,
  author = {Cheng Zhang and Junrui Yang and Caleb Southern and Thad Starner and Gregory Abowd},
  title = {WatchOut: Extending Interactions on a Smartwatch with Inertial Sensing},
  booktitle = {Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  year = {2016},
  url = {https://md2k.org/images/papers/software/p136-zhang_watchout},
  doi = {10.1145/2971763.2971775}
}
Adams RJ, Parate A and Marlin BM (2016), "Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams", In Proceedings of The 33rd International Conference on Machine Learning. , pp. 334-343.
Abstract: The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchi-cal span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segment-ing these events into high-level activity sessions. Our model includes higher-order cardinality fac-tors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP in-ference in quadratic time via dynamic program-ming, which we leverage to perform learning in the structured support vector machine frame-work. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance rel-ative to a hierarchical pairwise CRF.
BibTeX:
@inproceedings{adams2016hierarchical,
  author = {Roy J Adams and Abinhav Parate and Benjamin M Marlin},
  title = {Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams},
  booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
  year = {2016},
  pages = {334--343},
  url = {https://md2k.org/images/papers/methods/adams16.pdf}
}
Nahum-Shani I, Ertefaie A, Lu X, Lynch KG, McKay JR, Oslin D and Almirall D (2016), "A SMART Data Analysis Method for Constructing Adaptive Treatment Strategies for Substance Use Disorders", Addiction. , pp. n/a-n/a.
Abstract: Aims To demonstrate how Q-learning, a novel data analysis method, can be used with data from a sequential, multipleassignment, randomized trial (SMART) to construct empirically an adaptive treatment strategy (ATS) that is more tailoredthan the ATSs already embedded in a SMART. Method We use Q-learning with data from the Extending Treatment Ef-fectiveness of Naltrexone (ExTENd) SMART (N = 250) to construct empirically an ATS employing naltrexone, behavioralintervention, and telephone disease management to reduce alcohol consumption over 24 weeks in alcohol dependent in-dividuals.Results Q-learning helped to identify a subset of individuals who, despite showing early signs of response tonaltrexone, require additional treatment to maintain progress. Conclusions Q-learning can inform the developmentof more cost-effective, adaptive treatment strategies for treating substance use disorders.
BibTeX:
@article{ADD:ADD13743,
  author = {Inbal Nahum-Shani and Ashkan Ertefaie and Xi Lu and Kevin G. Lynch and James R. McKay and David Oslin and Daniel Almirall},
  title = {A SMART Data Analysis Method for Constructing Adaptive Treatment Strategies for Substance Use Disorders},
  journal = {Addiction},
  year = {2016},
  pages = {n/a--n/a},
  note = {ADD-16-0011.R2},
  url = {https://md2k.org/images/papers/jitai/nahum-shani_addiction.pdf},
  doi = {10.1111/add.13743}
}
Bierer BE, Li R, Barnes M and Sim I (2016), "A Global, Neutral Platform for Sharing Trial Data", New England Journal of Medicine. Massachusetts Medical Society.
Abstract: Sharing clinical trial data is critical in order to inform clinical and regulatory decision making and honor trial partici-pants who put themselves at risk to advance science. A recent In-stitute of Medicine (IOM) report argues that availability of de-identified (anonymized) patient-level data from clinical trials can permit verification of original results, enhancing public trust and accountability; facilitate other critical research (e.g., evaluation of adverse event rates according to compound class or subpopula-tion or identification of surro-gate end points); and avert dupli-cate trials, shielding participants from unnecessary risk.1 If such goals are to be achieved, patient-level data must be readily find-able and available for aggrega-tion and analysis across multiple sources to enable the widest range of secondary research uses.
BibTeX:
@article{bierer2016global,
  author = {Barbara E Bierer and Rebecca Li and Mark Barnes and Ida Sim},
  title = {A Global, Neutral Platform for Sharing Trial Data},
  journal = {New England Journal of Medicine},
  publisher = {Massachusetts Medical Society},
  year = {2016},
  url = {https://md2k.org/images/papers/software/nejmp1605348_Sim.pdf}
}
Boruvka A, Almirall D, Witkiewitz K and Murphy SA (2016), "Assessing Time-Varying Causal Effect Moderation in Mobile Health", arXiv preprint arXiv:1601.00237.
Abstract: In mobile health interventions aimed at behavior change and maintenance, treatments are provided in real time to manage current or impending high risk situations or promote healthy behaviors in near real time. Currently there is great scientific interest in developing data analysis approaches to guide the development of mobile interventions. In particular data from mobile health studies might be used to examine effect moderators — individual characteristics, time-varying context or past treatment response that moderate the effect of current treatment on a subsequent response. This paper introduces a formal definition for moderated effects in terms of potential outcomes, a definition that is particularly suited to mobile interventions, where treatment occasions are numerous, individuals are not always available for treatment, and potential moderators might be influenced by past treatment. Methods for estimating moderated effects are developed and compared. The proposed approach is illustrated using BASICS-Mobile, a smartphone-based intervention designed to curb heavy drinking and smoking among college students.
BibTeX:
@article{boruvka2016assessing,
  author = {Audrey Boruvka and Daniel Almirall and Katie Witkiewitz and Susan A Murphy},
  title = {Assessing Time-Varying Causal Effect Moderation in Mobile Health},
  journal = {arXiv preprint arXiv:1601.00237},
  year = {2016},
  url = {https://md2k.org/images/papers/jitai/boruvka033117.pdf}
}
Bulling A, Cakmakci O, Kunze K and Rehg JM (2016), "Eyewear Computing – Augmenting the Human with Head-mounted Wearable Assistants (Dagstuhl Seminar 16042)", Dagstuhl Reports. Dagstuhl, Germany Vol. 6(1), pp. 160-206. Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik.
BibTeX:
@article{bulling_et_al:DR:2016:5820,
  author = {Andreas Bulling and Ozan Cakmakci and Kai Kunze and James M. Rehg},
  editor = {Andreas Bulling and Ozan Cakmakci and Kai Kunze and James M. Rehg},
  title = {Eyewear Computing – Augmenting the Human with Head-mounted Wearable Assistants (Dagstuhl Seminar 16042)},
  journal = {Dagstuhl Reports},
  publisher = {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  year = {2016},
  volume = {6},
  number = {1},
  pages = {160--206},
  url = {http://drops.dagstuhl.de/opus/volltexte/2016/5820/pdf/dagrep_v006_i001_p160_s16042.pdf},
  doi = {10.4230/DagRep.6.1.160}
}
Bush T, Lovejoy J, Javitz H, Magnusson B, Torres AJ, Mahuna S, Benedict C, Wassum K and Spring B (2016), "Comparative effectiveness of adding weight control simultaneously or sequentially to smoking cessation quitlines: study protocol of a randomized controlled trial", BMC Public Health. Vol. 16(1), pp. 1. BioMed Central.
BibTeX:
@article{bush2016comparative,
  author = {Terry Bush and Jennifer Lovejoy and Harold Javitz and Brooke Magnusson and Alula Jimenez Torres and Stacey Mahuna and Cody Benedict and Ken Wassum and Bonnie Spring},
  title = {Comparative effectiveness of adding weight control simultaneously or sequentially to smoking cessation quitlines: study protocol of a randomized controlled trial},
  journal = {BMC Public Health},
  publisher = {BioMed Central},
  year = {2016},
  volume = {16},
  number = {1},
  pages = {1},
  url = {http://bmcpublichealth.biomedcentral.com/articles/10.1186/s12889-016-3231-6}
}
Chatterjee S, Hovsepian K, Sarker H, Saleheen N, al’Absi M, Atluri G, Ertin E, Lam C, Lemieux A, Nakajima M, Spring B, Wetter DW and Kumar S (2016), "mCrave: Continuous Estimation of Craving During Smoking Cessation", In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York, NY USA , pp. 863-874. ACM.
Abstract: Craving usually precedes a lapse for impulsive behaviors such as overeating, drinking, smoking, and drug use. Passive estimation of craving from sensor data in the natural environment can be used to assist users in coping with craving. In this paper, we take the first steps towards developing a computational model to estimate cigarette craving (during smoking abstinence) at the minute-level using mobile sensor data. We use 2,012 hours of sensor data and 1,812 craving self-reports from 61 participants in a smoking cessation study. To estimate craving, we first obtain a continuous measure of stress from sensor data. We find that during hours of day when craving is high, stress associated with self-reported high craving is greater than stress associated with low craving. We use this and other insights to develop feature functions, and encode them as pattern detectors in a Conditional Random Field (CRF) based model to infer craving probabilities.
BibTeX:
@inproceedings{Chatterjee2016Crave,
  author = {Soujanya Chatterjee and Karen Hovsepian and Hillol Sarker and Nazir Saleheen and Mustafa al’Absi and Gowtham Atluri and Emre Ertin and Cho Lam and Andrine Lemieux and Motohiro Nakajima and Bonnie Spring and David W. Wetter and Santosh Kumar},
  title = {mCrave: Continuous Estimation of Craving During Smoking Cessation},
  booktitle = {Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2016},
  pages = {863-874},
  url = {http://doi.acm.org/10.1145/2971648.2971672},
  doi = {10.1145/2971648.2971672}
}
Costanzo MR, Stevenson LW, Adamson PB, Desai AS, Heywood JT, Bourge RC, Bauman J and Abraham WT (2016), "Interventions linked to decreased heart failure hospitalizations during ambulatory pulmonary artery pressure monitoring", JACC: Heart Failure. Vol. 4(5), pp. 333-344. Journal of the American College of Cardiology.
BibTeX:
@article{costanzo2016interventions,
  author = {Maria R Costanzo and Lynne W Stevenson and Philip B Adamson and Ashkay S Desai and J Thomas Heywood and Robert C Bourge and Jordan Bauman and William T Abraham},
  title = {Interventions linked to decreased heart failure hospitalizations during ambulatory pulmonary artery pressure monitoring},
  journal = {JACC: Heart Failure},
  publisher = {Journal of the American College of Cardiology},
  year = {2016},
  volume = {4},
  number = {5},
  pages = {333--344},
  url = {http://heartfailure.onlinejacc.org/article.aspx?articleid=2491371}
}
Dadkhahi H, Saleheen N, Kumar S and Marlin BM (2016), "Learning Shallow Detection Cascades for Wearable Sensor-Based Mobile Health Applications", Proceedings of the 33rd International Conference on Machine Learning, 2016., In Proceedings of the 33rd International Conference on Machine Learning, 2016.
Abstract: The field of mobile health aims to leverage recent advances in wearable on-body sensing technol-ogy and smart phone computing capabilities to develop systems that can monitor health states and deliver just-in-time adaptive interventions. How-ever, existing work has largely focused on analyz-ing collected data in the off-line setting. In this paper, we propose a novel approach to learning shallow detection cascades developed explicitly for use in a real-time wearable-phone or wearable-phone-cloud systems. We apply our approach to the problem of cigarette smoking detection from a combination of wrist-worn actigraphy data and respiration chest band data using two and three stage cascades.
BibTeX:
@inproceedings{dadkhahi2016learning,
  author = {Hamid Dadkhahi and Nazir Saleheen and Santosh Kumar and Benjamin M Marlin},
  title = {Learning Shallow Detection Cascades for Wearable Sensor-Based Mobile Health Applications},
  booktitle = {Proceedings of the 33rd International Conference on Machine Learning, 2016},
  journal = {Proceedings of the 33rd International Conference on Machine Learning, 2016},
  year = {2016},
  url = {https://md2k.org/images/papers/methods/Shallow-Detection-Cascades_Marlin16.pdf}
}
Desai AS, Vaduganathan M, Ginn G, Abraham WT, Adamson PB, Costanzo MR, Heywood JT and Stevenson LW (2016), "Benefit of Longitudinal Pulmonary Artery Pressure Monitoring to Reduce Heart Failure Hospitalization Extends to Obese Patients", Journal of Cardiac Failure. Vol. 22(8), pp. S54. Elsevier.
BibTeX:
@article{desai2016benefit,
  author = {Ashkay S Desai and Muthiah Vaduganathan and Greg Ginn and William T Abraham and Philip B Adamson and Maria Rosa Costanzo and J THomas Heywood and Lynne W Stevenson},
  title = {Benefit of Longitudinal Pulmonary Artery Pressure Monitoring to Reduce Heart Failure Hospitalization Extends to Obese Patients},
  journal = {Journal of Cardiac Failure},
  publisher = {Elsevier},
  year = {2016},
  volume = {22},
  number = {8},
  pages = {S54}
}
Gulzari MA, Interlandi M, Yoo S, Tetali SD, Condie T, Millstein T and Kim M (2016), "BigDebug: Debugging Primitives for Interactive Big Data Processing in Spark", In Proceedings of the 38th International Conference on Software Engineering. Austin, Texas , pp. 784-795. ACM.
Abstract: Developers use cloud computing platforms to process a large quantity of data in parallel when developing big data analytics. Debugging the massive parallel computations that run in today's datacenters is time consuming and error-prone. To address this challenge, we design a set of interactive, real-time debugging primitives for big data processing in Apache Spark, the next generation data-intensive scalable cloud computing platform. This requires rethinking the notion of step-through debugging in a traditional debugger such as gdb, because pausing the entire computation across distributed worker nodes causes significant delay and naively inspecting millions of records using a watchpoint is too time consuming for an end user. First, BigDebug's simulated breakpoints and on-demand watchpoints allow users to selectively examine distributed, intermediate data on the cloud with little overhead. Second, a user can also pinpoint a crash-inducing record and selectively resume relevant sub-computations after a quick fix. Third, a user can determine the root causes of errors (or delays) at the level of individual records through a fine-grained data provenance capability. Our evaluation shows that BigDebug scales to terabytes and its record-level tracing incurs less than 25% overhead on average. It determines crash culprits orders of magnitude more accurately and provides up to 100% time saving compared to the baseline replay debugger. The results show that BigDebug supports debugging at interactive speeds with minimal performance impact.
BibTeX:
@inproceedings{Gulzar:2016:BDP:2884781.2884813,
  author = {Muhammad Ali Gulzari and Matteo Interlandi and Seunghyun Yoo and Sai Deep Tetali and Tyson Condie and Todd Millstein and Miryung Kim},
  title = {BigDebug: Debugging Primitives for Interactive Big Data Processing in Spark},
  booktitle = {Proceedings of the 38th International Conference on Software Engineering},
  publisher = {ACM},
  year = {2016},
  pages = {784--795},
  url = {https://md2k.org/images/papers/software/p784-gulzar_bigdebug16.pdf},
  doi = {10.1145/2884781.2884813}
}
Hiatt L, Adams RJ and Marlin BM (2016), "An Improved Data Representation for Smoking Detection with Wearable Respiration Sensors", In Healthcare Informatics (ICHI), 2016 IEEE International Conference on. , pp. 409-409.
BibTeX:
@inproceedings{hiatt2016improved,
  author = {Laura Hiatt and Roy J Adams and Benjamin M Marlin},
  title = {An Improved Data Representation for Smoking Detection with Wearable Respiration Sensors},
  booktitle = {Healthcare Informatics (ICHI), 2016 IEEE International Conference on},
  year = {2016},
  pages = {409--409}
}
Hu P, Zhang P, Rostami M and Ganesan D (2016), "Braidio: An Integrated Active-Passive Radio for Mobile Devices with Asymmetric Energy Budgets", In Proceedings of the 2016 Conference on ACM SIGCOMM 2016 Conference. Florianopolis, Brazil , pp. 384-397. ACM.
Abstract: While many radio technologies are available for mobile devices, one of them are designed to deal with asymmetric available energy. Battery capacities of mobile devices vary by up to three orders of magnitude between laptops and wearables, and our inability to deal with such asymmetry has limited the lifetime of constrained portable devices. This paper presents a radically new design for low-power radios — one that is capable of dynamically splitting the power burden of communication between the transmitter and receiver in proportion to the available energy on the two devices. We achieve this with a novel carrier offload method that dynamically moves carrier generation across end points. While such a design might raise the specter of a high-power, large form-factor radio, we show that this integration can be achieved with no more than a BLE-style active radio augmented with a few additional components. Our design, Braidio is a low-power, tightly integrated, low-cost radio capable of
operating as an active and passive transceiver. When these modes operate in an interleaved (braided) manner, the end result is a power-proportional low-power radio that is able to achieve 1:2546 to 3546:1 power consumption ratios between a transmitter and a receiver, all while operating at low power.
BibTeX:
@inproceedings{Hu:2016:BIA:2934872.2934902,
  author = {Pan Hu and Pengyu Zhang and Mohammad Rostami and Deepak Ganesan},
  title = {Braidio: An Integrated Active-Passive Radio for Mobile Devices with Asymmetric Energy Budgets},
  booktitle = {Proceedings of the 2016 Conference on ACM SIGCOMM 2016 Conference},
  publisher = {ACM},
  year = {2016},
  pages = {384--397},
  url = {https://md2k.org/images/papers/SSENSORS/p384-hu.pdf},
  doi = {10.1145/2934872.2934902}
}
Kotz D, Gunter CA, Kumar S and Weiner JP (2016), "Privacy and Security in Mobile Health: A Research Agenda", Computer. Vol. 49(6), pp. 22-30.
Abstract: Mobile health technology has great potential to increase healthcare quality, expand access to services, reduce costs, and improve personal wellness and public health. However, mHealth also raises significant privacy and security challenges.
BibTeX:
@article{Kotz2016,
  author = {David Kotz and Carl A Gunter and Santosh Kumar and Jonathan P Weiner},
  title = {Privacy and Security in Mobile Health: A Research Agenda},
  journal = {Computer},
  year = {2016},
  volume = {49},
  number = {6},
  pages = {22-30},
  url = {https://www.computer.org/csdl/mags/co/2016/06/mco2016060022-abs.html},
  doi = {10.1109/MC.2016.185}
}
Mayberry A, Tun Y, Hu P, Smith-Freedman D, Marlin B, Salthouse C and Ganesan D (2016), "CIDER: Enhancing the Performance of Computational Eyeglasses", In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research &amp; Applications. Charleston, South Carolina , pp. 313-314. ACM.
Abstract: The human eye offers a fascinating window into an individual's health, cognitive attention, and decision making, but we lack the ability to continually measure these parameters in the natural environment. We demonstrate CIDER, a system that operates in a highly optimized low-power mode under indoor settings by using a fast Search-Refine controller to track the eye, but detects when the environment switches to more challenging outdoor sunlight and switches models to operate robustly under this condition. Our design is holistic and tackles a) power consumption in digitizing pixels, estimating pupillary parameters, and illuminating the eye via near-infrared and b) error in estimating pupil center and pupil dilation. We demonstrate that CIDER can estimate pupil center with error less than two pixels (0.6°), and pupil diameter with error of one pixel (0.22mm). Our end-to-end results show that we can operate at power levels of roughly 7mW at a 4Hz eye tracking rate, or roughly 32mW at rates upwards of 250Hz.
BibTeX:
@inproceedings{Mayberry:2016:CEP:2857491.2884063,
  author = {Addison Mayberry and Yamin Tun and Pan Hu and Duncan Smith-Freedman and Benjamin Marlin and Christopher Salthouse and Deepak Ganesan},
  title = {CIDER: Enhancing the Performance of Computational Eyeglasses},
  booktitle = {Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research &amp; Applications},
  publisher = {ACM},
  year = {2016},
  pages = {313--314},
  url = {https://md2k.org/images/papers/sensors/p313-mayberry.pdf},
  doi = {10.1145/2857491.2884063}
}
Mayberry A, Tun Y, Hu P, Smith-Freedman D, Ganesan D, Marlin BM and Salthouse C (2016), "THE "I" IN THE EYE", GetMobile: Mobile Comp. and Comm.. New York, NY, USA, October, 2016. Vol. 20(2), pp. 27-30. ACM.
Abstract: Excerpted from "CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass," from Proceedings of the 21st Annual ACM International Conference on Mobile Computing and Networking with permission. http://dl.acm.org/citation.cfm?id=2790096 © ACM 2015.

The eye is a truly unique and fascinating piece of physiology. Through it, organisms take in massive amounts of sensory data; through it, they also communicate emotion and intent both consciously and unconsciously. It is so tightly coupled with the operation of the brain that even slight mental blocks like being tired are measurable through eye movements. Eye-related research has long worn out the cliche "the eyes are the window to the soul," and this is largely because there is a deeper truth behind this phrase that has come to light in the last several decades of psychology and neurology research. In short, we now understand that the eyes are the best window to the mind. (Kahneman 2011).
BibTeX:
@article{Mayberry:2016:IE:3009808.3009818,
  author = {Mayberry, Addison and Tun, Yamin and Hu, Pan and Smith-Freedman, Duncan and Ganesan, Deepak and Marlin, Benjamin M. and Salthouse, Christopher},
  title = {THE "I" IN THE EYE},
  journal = {GetMobile: Mobile Comp. and Comm.},
  publisher = {ACM},
  year = {2016},
  volume = {20},
  number = {2},
  pages = {27--30},
  url = {http://doi.acm.org/10.1145/3009808.3009818},
  doi = {10.1145/3009808.3009818}
}
Nahum-Shani I, Smith SN, Spring BJ, Collins LM, Witkiewitz K, Tewari A and Murphy SA (2016), "Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support", Annals of Behavioral Medicine. , pp. 1-17.
Abstract: Background. The just-in-time adaptive intervention (JITAI) is an intervention design aiming to provide the right type/amount of support, at the right time, by adapting to an individual’s changing internal and contextual state. The availability of increasingly powerful mobile and sensing technologies underpins the use of JITAIs to support health behavior, as in such a setting an individual’s state can change rapidly, unexpectedly, and in his/her natural environment.

Purpose. Despite the increasing use and appeal of JITAIs, a major gap exists between the growing technological capabilities for delivering JITAIs and research on the development and evaluation of these interventions. Many JITAIs have been developed with minimal use of empirical evidence, theory, or accepted treatment guidelines. Here, we take an essential first step towards bridging this gap.

Methods. Building on health behavior theories and the extant literature on JITAIs, we clarify the scientific motivation for JITAIs, define their fundamental components, and highlight design principles related to these components. Examples of JITAIs from various domains of health behavior research are used for illustration.

Conclusion. As we enter a new era of technological capacity for delivering JITAIs, it is critical that researchers develop sophisticated and nuanced health behavior theories capable of guiding the construction of such interventions. Particular attention has to be given to better understanding the implica-tions of providing timely and ecologically sound support for intervention adherence and retention.
BibTeX:
@article{Nahum-Shani2016,
  author = {Inbal Nahum-Shani and Shawna N. Smith and Bonnie J. Spring and Linda M. Collins and Katie Witkiewitz and Ambuj Tewari and Susan A. Murphy},
  title = {Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support},
  journal = {Annals of Behavioral Medicine},
  year = {2016},
  pages = {1--17},
  url = {https://md2k.org/images/papers/jitai/BehavMed_Nahum-Shani16.pdf},
  doi = {10.1007/s12160-016-9830-8}
}
Natarajan A, Angarita G, Gaiser E, Malison R, Ganesan D and Marlin BM (2016), "Domain Adaptation Methods for Improving Lab-to-field Generalization of Cocaine Detection Using Wearable ECG", In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Heidelberg, Germany , pp. 875-885. ACM.
Abstract: Mobile health research on illicit drug use detection typically involves a two-stage study design where data to learn detectors is first collected in lab-based trials, followed by a deployment to subjects in a free-living environment to assess detector performance. While recent work has demonstrated the feasibility of wearable sensors for illicit drug use detection in the lab setting, several key problems can limit lab-to-field generalization performance. For example, lab-based data collection often has low ecological validity, the ground-truth event labels collected in the lab may not be available at the same level of temporal granularity in the field, and there can be significant variability between subjects. In this paper, we present domain adaptation methods for assessing and mitigating potential sources of performance loss in lab-to-field generalization and apply them to the problem of cocaine use detection from wearable electrocardiogram sensor data.
BibTeX:
@inproceedings{Natarajan:2016:DAM:2971648.2971666b,
  author = {Annamalai Natarajan and Gustavo Angarita and Edward Gaiser and Robert Malison and Deepak Ganesan and Benjamin M. Marlin},
  title = {Domain Adaptation Methods for Improving Lab-to-field Generalization of Cocaine Detection Using Wearable ECG},
  booktitle = {Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2016},
  pages = {875--885},
  url = {https://md2k.org/images/papers/methods/nihms835285_Marlin.pdf},
  doi = {10.1145/2971648.2971666}
}
O'Kane AA, Hurst A, Niezen G, Marquardt N, Bird J and Abowd G (2016), "Advances in DIY Health and Wellbeing", In Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems. Santa Clara, California, USA , pp. 3453-3460. ACM.
BibTeX:
@inproceedings{O'Kane:2016:ADH:2851581.2856467,
  author = {Aisling Ann O'Kane and Amy Hurst and Gerrit Niezen and Nicolai Marquardt and Jon Bird and Gregory Abowd},
  title = {Advances in DIY Health and Wellbeing},
  booktitle = {Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems},
  publisher = {ACM},
  year = {2016},
  pages = {3453--3460},
  url = {http://doi.acm.org/10.1145/2851581.2856467},
  doi = {10.1145/2851581.2856467}
}
Patrick K, Hekler EB, Estrin D, Mohr DC, Riper H, Crane D, Godino J and Riley WT (2016), "The Pace of Technologic Change: Implications for Digital Health Behavior Intervention Research", American Journal of Preventive Medicine. Vol. 51(5), pp. 816 - 824.
Abstract: This paper addresses the rapid pace of change in the technologies that support digital interventions; the complexity of the health problems they aim to address; and the adaptation of scientific methods to accommodate the volume, velocity, and variety of data and interventions possible from these technologies. Information, communication, and computing technologies are now part of every societal domain and support essentially every facet of human activity. Ubiquitous computing, a vision articulated fewer than 30 years ago, has now arrived. Simultaneously, there is a global crisis in health through the combination of lifestyle and age-related chronic disease and multiple comorbidities. Computationally intensive health behavior interventions may be one of the most powerful methods to reduce the consequences of this crisis, but new methods are needed for health research and practice, and evidence is needed to support their widespread use. The challenges are many, including a reluctance to abandon timeworn theories and models of health behavior—and health interventions more broadly—that emerged in an era of self-reported data; medical models of prevention, diagnosis, and treatment; and scientific methods grounded in sparse and expensive data. There are also many challenges inherent in demonstrating that newer approaches are, indeed, effective. Potential solutions may be found in leveraging methods of research that have been shown to be successful in other domains, particularly engineering. A more “agile science� may be needed that streamlines the methods through which elements of health interventions are shown to work or not, and to more rapidly deploy and iteratively improve those that do. There is much to do to advance the issues discussed in this paper, and the papers in this theme issue. It remains an open question whether interventions based in these new models and methods are, in fact, equally if not more efficacious as what is available currently. Economic analyses of these new approaches are needed because assumptions of net worth compared to other approaches are just that, assumptions. Human-centered design research is needed to ensure that users ultimately benefit. Finally, a translational research agenda will be needed, as the status quo will likely be resistant to change.
BibTeX:
@article{Patrick2016816,
  author = {Kevin Patrick and Eric B. Hekler and Deborah Estrin and David C. Mohr and Heleen Riper and David Crane and Job Godino and William T. Riley},
  title = {The Pace of Technologic Change: Implications for Digital Health Behavior Intervention Research},
  journal = {American Journal of Preventive Medicine},
  year = {2016},
  volume = {51},
  number = {5},
  pages = {816 - 824},
  url = {https://md2k.org/images/papers/jitai/AmJPrevMed_Patrick2016.pdf},
  doi = {10.1016/j.amepre.2016.05.001}
}
Pfammatter A, Spring B, Saligram N, Dav'e R, Gowda A, Blais L, Arora M, Ranjani H, Ganda O, Hedeker D and others (2016), "mHealth Intervention to Improve Diabetes Risk Behaviors in India: A Prospective, Parallel Group Cohort Study", Journal of Medical Internet Research. Vol. 18(8), pp. e207. JMIR Publications Inc., Toronto, Canada.
BibTeX:
@article{pfammatter2016mhealth,
  author = {Angela Pfammatter and Bonnie Spring and Nalini Saligram and Raj Dav'e and Arun Gowda and Linelle Blais and Monika Arora and Harish Ranjani and Om Ganda and Donald Hedeker and others},
  title = {mHealth Intervention to Improve Diabetes Risk Behaviors in India: A Prospective, Parallel Group Cohort Study},
  journal = {Journal of Medical Internet Research},
  publisher = {JMIR Publications Inc., Toronto, Canada},
  year = {2016},
  volume = {18},
  number = {8},
  pages = {e207},
  url = {http://www.jmir.org/2016/8/e207/}
}
Pienta R, Tamersoy A, Endert A, Navathe S, Tong H and Chau DH (2016), "VISAGE: Interactive Visual Graph Querying", In Proceedings of the International Working Conference on Advanced Visual Interfaces. Bari, Italy , pp. 272-279. ACM.
BibTeX:
@inproceedings{Pienta:2016:VIV:2909132.2909246,
  author = {Pienta, Robert and Tamersoy, Acar and Endert, Alex and Navathe, Shamkant and Tong, Hanghang and Chau, Duen Horng},
  title = {VISAGE: Interactive Visual Graph Querying},
  booktitle = {Proceedings of the International Working Conference on Advanced Visual Interfaces},
  publisher = {ACM},
  year = {2016},
  pages = {272--279},
  url = {http://doi.acm.org/10.1145/2909132.2909246},
  doi = {10.1145/2909132.2909246}
}
Reyes G, Zhang D, Ghosh S, Shah P, Wu J, Parnami A, Bercik B, Starner T, Abowd GD and Edwards WK (2016), "Whoosh: Non-Voice Acoustics for Low-Cost, Hands-Free, and Rapid Input on Smartwatches", In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (to appear).
Abstract: We present an alternate approach to smartwatch interactions using non-voice acoustic input captured by the device’s microphone to complement touch and speech. Whoosh is an interaction
technique that recognizes the type and length of acoustic events performed by the user to enable low-cost, hands-free, and rapid input on smartwatches. We build a recognition system capable of detecting non-voice events directed at and around the watch, including blows, sip-and-puff, and directional air swipes, without hardware modifications to the device. Further, inspired by the design of musical instruments, we develop a custom modification of the physical structure of the watch case to passively alter the acoustic response of events around the bezel; this physical redesign expands our input vocabulary with no additional electronics. We evaluate our technique across 8 users with 10 events exhibiting up to 90.5% ten-fold cross validation accuracy on an unmodified watch, and 14 events with 91.3% ten-fold cross validation accuracy with an instrumental watch case. Finally, we share a number of demonstration applications, including multi-device interactions,
to highlight our technique with a real-time recognizer running on the watch.
BibTeX:
@inproceedings{Reyes2016,
  author = {Gabriel Reyes and Dingtian Zhang and Sarthak Ghosh and Pratik Shah and Jason Wu and Aman Parnami and Bailey Bercik and Thad Starner and Gregory D. Abowd and W. Keith Edwards},
  title = {Whoosh: Non-Voice Acoustics for Low-Cost, Hands-Free, and Rapid Input on Smartwatches},
  booktitle = {Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (to appear)},
  year = {2016},
  url = {https://md2k.org/images/papers/software/p120-reyes_whoosh.pdf}
}
Saleheen N, Chakraborty S, Ali N, Rahman MM, Hossain SM, Bari R, Buder E, Srivastava M and Kumar S (2016), "mSieve: Differential Behavioral Privacy in Time Series of Mobile Sensor Data", In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York, NY USA , pp. 706-717. ACM.
Abstract: Differential privacy concepts have been successfully used to protect anonymity of individuals in population-scale analyis.
Sharing of mobile sensor data, especially physiological data, raise different privacy challenges, that of protecting private behaviors that can be revealed from time series of sensor data. Existing privacy mechanisms rely on noise addition and data perturbation. But the accuracy requirement on inferences drawn from physiological data, together with well-established limits within which these data values occur, render traditional privacy mechanisms inapplicable. In this work, we define a new behavioral privacy metric based on differential privacy and propose a novel data substitution mechanism to protect behavioral privacy. We evaluate the efficacy of our scheme using 660 hours of ECG, respiration, and activity data collected from 43 participants and demonstrate that it is possible to retain meaningful utility, in terms of inference accuracy (90%), while simultaneously preserving the privacy of sensitive behaviors.
BibTeX:
@inproceedings{Saleheen:2016:MDB:2971648.2971753b,
  author = {Nazir Saleheen and Supriyo Chakraborty and Nasir Ali and Md Mahbubur Rahman and Syed Monowar Hossain and Rummana Bari and Eugene Buder and Mani Srivastava and Santosh Kumar},
  title = {mSieve: Differential Behavioral Privacy in Time Series of Mobile Sensor Data},
  booktitle = {Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},
  publisher = {ACM},
  year = {2016},
  pages = {706-717},
  url = {https://md2k.org/images/papers/privacy/mSieve-UbiComp-2016.pdf},
  doi = {10.1145/2971648.2971753}
}
Sarker H, Tyburski M, Rahman MM, Hovsepian K, Sharmin M, Epstein DH, Preston KL, Furr-Holden CD, Milam A, Nahum-Shani I, al'Absi M and Kumar S (2016), "Finding Significant Stress Episodes in a Discontinuous Time Series of Rapidly Varying Mobile Sensor Data", In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems. Santa Clara, California, USA , pp. 4489-4501. ACM.
Abstract: Management of daily stress can be greatly improved by de- livering sensor-triggered just-in-time interventions (JITIs) on mobile devices. The success of such JITIs critically depends on being able to mine the time series of noisy sensor data to find the most opportune moments. In this paper, we propose a time series pattern mining method to detect significant stress episodes in a time series of discontinuous and rapidly varying stress data. We apply our model to 4 weeks of physiological, GPS, and activity data collected from 38 users in their natu-ral environment to discover patterns of stress in real-life. We find that the duration of a prior stress episode predicts the du-ration of the next stress episode and stress in mornings and evenings is lower than during the day. We then analyze the relationship between stress and objectively rated disorder in the surrounding neighborhood and develop a model to predict stressful episodes.
BibTeX:
@inproceedings{Sarker:2016:FSS:2858036.2858218,
  author = {Sarker, Hillol and Tyburski, Matthew and Rahman, Md Mahbubur and Hovsepian, Karen and Sharmin, Moushumi and Epstein, David H. and Preston, Kenzie L. and Furr-Holden, C. Debra and Milam, Adam and Nahum-Shani, Inbal and al'Absi, Mustafa and Kumar, Santosh},
  title = {Finding Significant Stress Episodes in a Discontinuous Time Series of Rapidly Varying Mobile Sensor Data},
  booktitle = {Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems},
  publisher = {ACM},
  year = {2016},
  pages = {4489--4501},
  url = {http://doi.acm.org/10.1145/2858036.2858218},
  doi = {10.1145/2858036.2858218}
}
Sim I (2016), "Two Ways of Knowing: Big Data and Evidence-Based Medicine", Annals of internal medicine. Vol. 164(8), pp. 562-563. American College of Physicians.
BibTeX:
@article{sim2016two,
  author = {Ida Sim},
  title = {Two Ways of Knowing: Big Data and Evidence-Based Medicine},
  journal = {Annals of internal medicine},
  publisher = {American College of Physicians},
  year = {2016},
  volume = {164},
  number = {8},
  pages = {562--563},
  url = {http://annals.org/article.aspx?articleid=2484291}
}
Sugavanam N, Baskar S and Ertin E (2016), "Recovery guarantees for high resolution radar sensing with compressive illumination", In Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa), 2016 4th International Workshop on. , pp. 252-256.
Abstract: We present a compressive radar design that combines multitone linear frequency modulated (LFM) waveforms on transmit with classical stretch processor and sub-Nyquist sampling on receive. The proposed compressive illumination scheme has much fewer random elements compared to previously proposed compressive radar designs based on stochastic waveforms, resulting in reduced storage and complexity for implementation. We present bounds on the operator norm and mutual coherence of the sensing matrix of the proposed scheme and show that for sufficiently large number of modulating tones, high resolution range recovery is guaranteed for a sparse scene using sampling rates that scale linearly with the scene sparsity. Simulation results are presented to study recovery performance as a function of system parameters for targets both on and off the grid. In addition, we present experimental results using a high speed digital waveform generator and a custom designed analog stretch processor.
BibTeX:
@inproceedings{sugavanam2016recovery,
  author = {Nithin Sugavanam and Siddharth Baskar and Emre Ertin},
  title = {Recovery guarantees for high resolution radar sensing with compressive illumination},
  booktitle = {Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa), 2016 4th International Workshop on},
  year = {2016},
  pages = {252--256}
}
Yardley L, Spring BJ, Riper H, Crane LGMDH, Curtis K, Merchant GC, Naughton F and Blandford A (2016), "Understanding and promoting effective engagement with digital behavior change interventions", American Journal of Preventive Medicine. Vol. 51(5), pp. 833-842. Elsevier.
Abstract: This paper is one in a series developed through a process of expert consensus to provide an overview of questions of current importance in research into engagement with digital behavior change interventions, identifying guidance based on research to date and priority topics for future research. The first part of this paper critically reflects on current approaches to conceptualizing and measuring engagement. Next, issues relevant to promoting effective engagement are discussed, including how best to tailor to individual needs and combine digital and human support. A key conclusion with regard to conceptualizing engagement is that it is important to understand the relationship between engagement with the digital intervention and the desired behavior change. This paper argues that it may be more valuable to establish and promote “effective engagement,” rather than simply more engagement, with “effective engagement” defined empirically as sufficient engagement with the intervention to achieve intended outcomes. Appraisal of the value and limitations of methods of assessing different aspects of engagement highlights the need to identify valid and efficient combinations of measures to develop and test multidimensional models of engagement. The final section of the paper reflects on how interventions can be designed to fit the user and their specific needs and context. Despite many unresolved questions posed by novel and rapidly changing technologies, there is widespread consensus that successful intervention design demands a user-centered and iterative approach to development, using mixed methods and in-depth qualitative research to progressively refine the intervention to meet user requirements.
BibTeX:
@article{yardley2016understanding,
  author = {Lucy Yardley and Bonnie J Spring and Heleen Riper and Leanne G Morrisonand David H Crane and Kristina Curtis and Gina C Merchant and Felix Naughton and Ann Blandford},
  title = {Understanding and promoting effective engagement with digital behavior change interventions},
  journal = {American Journal of Preventive Medicine},
  publisher = {Elsevier},
  year = {2016},
  volume = {51},
  number = {5},
  pages = {833--842},
  url = {https://md2k.org/images/papers/jitai/AmJPrevMed_Spring2016.pdf}
}
Zhang P, Rostami M, Hu P and Ganesan D (2016), "Enabling Practical Backscatter Communication for On-body Sensors", In Proceedings of the 2016 Conference on ACM SIGCOMM 2016 Conference. Florianopolis, Brazil , pp. 370-383. ACM.
BibTeX:
@inproceedings{ZHANG:2016:EPB:2934872.2934901,
  author = {Pengyu Zhang and Muhammad Rostami and Pan Hu and Deepak Ganesan},
  title = {Enabling Practical Backscatter Communication for On-body Sensors},
  booktitle = {Proceedings of the 2016 Conference on ACM SIGCOMM 2016 Conference},
  publisher = {ACM},
  year = {2016},
  pages = {370--383},
  url = {http://doi.acm.org/10.1145/2934872.2934901},
  doi = {10.1145/2934872.2934901}
}
Kumar S, Abowd G, Abraham WT, al'Absi M, Chau DH, Ertin E, Estrin D, Ganesan D, Hnat T, Hossain SM, Ives Z, Kerr J, Marlin BM, Murphy S, Rehg JM, Nahum-Shani I, Shetty V, Sim I, Spring B, Srivastava M and Wetter D (2017), "Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K)", IEEE Pervasive Computing. Vol. 16(2), pp. 18-22.
Abstract: The National Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) was established in October 2014 with a grant from the National Institutes of Health under the Big Data-to-Knowledge (BD2K) program. Among the 11 centers of excellence originally funded, MD2K's unique contribution is to develop innovative tools to make it easier to gather, analyze, interpret, and capitalize on high-frequency data from mobile sensors. It seeks to facilitate the monitoring of health states and quantify the temporal dynamics of key physical, biological, behavioral, psychological, social, and environmental factors that contribute to the health and disease risks of individuals. MD2K's overarching goal is to reduce the burden that complex chronic disorders place on health and healthcare by making it feasible to detect and predict person-specific disease risk factors ahead of the onset of adverse clinical events, supporting sensor-driven just-in-time interventions.

To demonstrate the utility and wide generalizability of the research and tools developed by MD2K, we initially targeted two biomedical applications—improving the success rate for smoking cessation and reducing the number of rehospitalizations in congestive heart failure (CHF). Our two chosen biomedical applications are at the opposite ends of the temporal spectrum of mortality. Smoking is the leading cause of mortality, causing 1 in 5 deaths, but its mortality risk is far in the future. On the other hand, CHF, which is the leading cause of preventable rehospitalization with a readmission rate of 27 percent, has an immediate mortality risk. The first (of three) iterations of these two studies with 75 participants each is currently underway. In addition, the biomedical applications addressed by MD2K have expanded to managing stress, reducing overeating, reducing cocaine use, and improving oral health.
BibTeX:
@article{7891193,
  author = {S. Kumar and G. Abowd and W. T. Abraham and M. al'Absi and D. H. Chau and E. Ertin and D. Estrin and D. Ganesan and T. Hnat and S. M. Hossain and Z. Ives and J. Kerr and B. M. Marlin and S. Murphy and J. M. Rehg and I. Nahum-Shani and V. Shetty and I. Sim and B. Spring and M. Srivastava and D. Wetter},
  title = {Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K)},
  journal = {IEEE Pervasive Computing},
  year = {2017},
  volume = {16},
  number = {2},
  pages = {18-22},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7891193},
  doi = {10.1109/MPRV.2017.29}
}
Adams RJ and Marlin BM (2017), "Learning Time Series Detection Models from Temporally Imprecise Labels", In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics.
Abstract: In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels. In this problem, the data consist of a set of input time series, and supervision is provided by a sequence of noisy time stamps corresponding to the occurrence of positive class events. Such temporally imprecise labels commonly occur in areas like mobile health research where human annotators are tasked with labeling the occurrence of very short duration events. We propose a general learning framework for this problem that can accommodate different base classifiers and noise models. We present results on real mobile health data showing that the proposed framework significantly outperforms a number of alternatives including assuming that the label time stamps are noise-free, transforming the problem into the multiple instance learning framework, and learning on labels that were manually re-aligned.
BibTeX:
@inproceedings{adams17,
  author = {Roy J. Adams and Benjamin M. Marlin},
  title = {Learning Time Series Detection Models from Temporally Imprecise Labels},
  booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics},
  year = {2017},
  url = {https://md2k.org/images/papers/methods/adams17a.pdf}
}
al'Absi M, Nahum-Shani I, Lemieux A, Wetter DW, Swendsen J and Ertin E (2017), "Harnessing mHealth Technology to Advance Intervention Research on Stress, Addiction, and Mental Health Disorders", In PSYCHOSOMATIC MEDICINE. Vol. 79(4), pp. A149-A150.
BibTeX:
@inproceedings{al2017harnessing,
  author = {Mustafa al'Absi and Inbal Nahum-Shani and Andrine Lemieux and David W Wetter and Joel Swendsen and Emre Ertin},
  title = {Harnessing mHealth Technology to Advance Intervention Research on Stress, Addiction, and Mental Health Disorders},
  booktitle = {PSYCHOSOMATIC MEDICINE},
  year = {2017},
  volume = {79},
  number = {4},
  pages = {A149--A150}
}
Alzantot M, Wang Y, Ren Z and Srivastava MB (2017), "RSTensorFlow: GPU Enabled TensorFlow for Deep Learning on Commodity Android Devices", In Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications.
Abstract: Mobile devices have become an essential part of our daily lives. By virtue of both their increasing computing power and the recent progress made in AI, mobile devices evolved to act as intelligent assistants in many tasks rather than a mere way of making phone calls. However, popular and commonly used tools and frameworks for machine intelli-gence are still lacking the ability to make proper use of the available heterogeneous computing resources on mobile devices. In this paper, we study the benefits of utilizing the heterogeneous (CPU and GPU) computing resources available on commodity android devices while running deep learning models. We leveraged the heterogeneous comput-ing framework RenderScript to accelerate the execution of deep learning models on commodity Android devices. Our system is implemented as an extension to the popular open-source framework TensorFlow. By integrating our acceler-ation framework tightly into TensorFlow, machine learning engineers can now easily make benefit of the heterogeneous computing resources on mobile devices without the need of any extra tools. We evaluate our system on different android phones models to study the trade-offs of running different neural network operations on the GPU. We also compare the performance of running different models architectures such as convolutional and recurrent neural networks on CPU only vs using heterogeneous computing resources. Our result shows that although GPUs on the phones are capable of of-fering substantial performance gain in matrix multiplication on mobile devices. Therefore, models that involve multi-plication of large matrices can run much faster (approx. 3 times faster in our experiments) due to GPU support.
BibTeX:
@inproceedings{alzantot17,
  author = {Moustafa Alzantot and Yingnan Wang and Zhengshuang Ren and Mani B. Srivastava},
  title = {RSTensorFlow: GPU Enabled TensorFlow for Deep Learning on Commodity Android Devices},
  booktitle = {Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications},
  year = {2017},
  url = {https://md2k.org/images/papers/methods/p7-alzantot.pdf},
  doi = {10.1145/3089801.3089805}
}
Alzantot M, Chakraborty S and Srivastava MB (2017), "SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation", IEEE BICA'17 (co-located with IEEE Percom 2017). IEEE.
Abstract: Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real data segments – that are sensitive to the user – thus protecting privacy and resulting in improved analytics. However, increasingly adversarial roles taken by data recipients such as mobile apps, or other cloud-based analytics services, mandate that the synthetic data, in addition to preserving statistical properties, should also be “difficult to distinguish from the real data. Typically, visual
inspection has been used as a test to distinguish between datasets. But more recently, sophisticated classifier models (discriminators), corresponding to a set of events, have also been employed to distinguish between synthesized and real data. The model operates on both datasets and the respective event outputs are compared for consistency. Prior work on data synthesis have often focused on classifiers that are built for features explicitly preserved by the synthetic data. This suggests that an adversary can build classifiers that can exploit a potentially disjoint set of features for differentiating between the two datasets. In this paper, we take a step towards generating sensory data that can pass a deep learning based discriminator model test, and make two specific contributions: first, we present a deep learning based architecture for synthesizing sensory data. This architecture comprises of a generator model, which is a stack of multiple Long-Short-Term-Memory (LSTM) networks and a Mixture Density Network (MDN); second, we use another LSTM network based discriminator model for distinguishing between the true and the synthesized data.
Using a dataset of accelerometer traces, collected using smartphones of users doing their daily activities, we show that the deep learning based discriminator model can only distinguish between the real and synthesized traces with an accuracy in the neighborhood of 50%.
BibTeX:
@article{alzantot2017sensegen,
  author = {Moustafa Alzantot and Supriyo Chakraborty and Mani B. Srivastava},
  title = {SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation},
  journal = {IEEE BICA'17 (co-located with IEEE Percom 2017)},
  publisher = {IEEE},
  year = {2017},
  url = {https://md2k.org/images/papers/privacy/SenseGen_Alzantot.pdf},
  doi = {https://arxiv.org/abs/1701.08886v1}
}
Bedri A, Li R, Haynes M, Kosaraju RP, Grover I, Prioleau T, Beh MY, Goel M, Starner T and Abowd G (2017), "EarBit: Using Wearable Sensors to Detect Eating Episodes in Unconstrained Environments", Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.. New York, NY, USA, September, 2017. Vol. 1(3), pp. 37:1-37:20. ACM.
Abstract: Chronic and widespread diseases such as obesity, diabetes, and hypercholesterolemia require patients to monitor their food intake, and food journaling is currently the most common method for doing so. However, food journaling is subject to self-bias and recall errors, and is poorly adhered to by patients. In this paper, we propose an alternative by introducing EarBit, a wearable system that detects eating moments. We evaluate the performance of inertial, optical, and acoustic sensing modalities and focus on inertial sensing, by virtue of its recognition and usability performance. Using data collected in a simulated home setting with minimum restrictions on participants’ behavior, we build our models and evaluate them with an unconstrained outside-the-lab study. For both studies, we obtained video footage as ground truth for participants activities. Using leave-one-user-out validation, EarBit recognized all the eating episodes in the semi-controlled lab study, and achieved an accuracy of 90.1% and an F1-score of 90.9% in detecting chewing instances. In the unconstrained, outside-the-lab evaluation, EarBit obtained an accuracy of 93% and an F1-score of 80.1% in detecting chewing instances. It also accurately recognized all but one recorded eating episodes. These episodes ranged from a 2 minute snack to a 30 minute meal.
BibTeX:
@article{Bedri:2017:EUW:3139486.3130902,
  author = {Bedri, Abdelkareem and Li, Richard and Haynes, Malcolm and Kosaraju, Raj Prateek and Grover, Ishaan and Prioleau, Temiloluwa and Beh, Min Yan and Goel, Mayank and Starner, Thad and Abowd, Gregory},
  title = {EarBit: Using Wearable Sensors to Detect Eating Episodes in Unconstrained Environments},
  journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
  publisher = {ACM},
  year = {2017},
  volume = {1},
  number = {3},
  pages = {37:1--37:20},
  url = {https://md2k.org/images/papers/biomarkers/a37-bedri.pdf},
  doi = {10.1145/3130902}
}
Dadkhahi H and Marlin B (2017), "Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices", 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining., 2017., In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
Abstract: In this paper, we present a new approach to learning cascaded classifiers for use in computing environments that involve networks of heterogeneous and resource-constrained, low-power embedded compute and sensing nodes. We present a generalization of the classical linear detection cascade to the case of tree-structured cascades where different branches of the tree execute on different physical compute nodes in the network. Different nodes have access to different features, as well as access to potentially different computation and energy resources. We concentrate on the problem of jointly learning the parameters for all of the classifiers in the cascade given a fixed cascade architecture and a known set of costs required to carry out the computation at each node. To accomplish the objective of joint learning of all detectors, we propose a novel approach to combining classifier outputs during training that better matches the hard cascade setting in which the learned system will be deployed. This work is motivated by research in the area of mobile health where energy efficient real time detectors integrating information from multiple wireless on-body sensors and a smart phone are needed for real-time monitoring and the delivery of just-in-time adaptive interventions. We evaluate our framework on mobile sensor-based human activity recognition and mobile health detector learning problems.
BibTeX:
@inproceedings{Dadkhahi17,
  author = {Hamid Dadkhahi and Benjamin Marlin},
  title = {Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices},
  booktitle = {Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  journal = {23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining., 2017},
  year = {2017},
  url = {https://md2k.org/images/papers/methods/p1773-dadkhahi.pdf}
}
Fang D, Hohman F, Polack P, Sarker H, Kahng M, Sharmin M, al'Absi M and Chau DH (2017), "mHealth Visual Discovery Dashboard", In Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. New York, NY, USA , pp. 237-240. ACM.
Abstract: We present Discovery Dashboard, a visual analytics system for exploring large volumes of time series data from mobile medical field studies. Discovery Dashboard offers interactive exploration tools and a data mining motif discovery algorithm to help researchers formulate hypotheses, discover trends and patterns, and ultimately gain a deeper understanding of their data. Discovery Dashboard emphasizes user freedom and flexibility during the data exploration process and enables researchers to do things previously challenging or impossible to do --- in the web-browser and in real time. We demonstrate our system visualizing data from a mobile sensor study conducted at the University of Minnesota that included 52 participants who were trying to quit smoking.
BibTeX:
@inproceedings{Fang:2017:MVD:3123024.3123170,
  author = {Fang, Dezhi and Hohman, Fred and Polack, Peter and Sarker, Hillol and Kahng, Minsuk and Sharmin, Moushumi and al'Absi, Mustafa and Chau, Duen Horng},
  title = {mHealth Visual Discovery Dashboard},
  booktitle = {Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers},
  publisher = {ACM},
  year = {2017},
  pages = {237--240},
  url = {https://md2k.org/images/papers/methods/p237-fang.pdf},
  doi = {10.1145/3123024.3123170}
}
Gao J, Baskar S, Teng D, al'Absi M, Kumar S and Ertin E (2017), "A New Direction for Biosensing: RF Sensors for Monitoring Cardio-Pulmonary Function", In Mobile Health: Sensors, Analytic Methods, and Applications. Cham , pp. 289-312. Springer International Publishing.
Abstract: Long-term monitoring of physiology at large-scale can help determine potential causes and early biomarkers of chronic diseases. Physiological monitoring today, however, requires wearing of sensors such as electrodes for ECG and belt around lungs for respiration, and is unsuitable for monitoring of patients and healthy adults over multiple years. In this chapter, we review advances in a novel sensing modality using radio frequency (RF) waves that can provide physiological measurements without skin contact in both lab and field environments. This chapter presents fundamentals of RF biosensing with experimental results of a new experimental bioradar platform illustrating the concepts. The focus is on new approaches to monitor heart motion and respiratory effort. Experimental results using both an articulated heart phantom and human subjects show that RF sensing modality can match the performance of state-of-the-art physiological monitoring devices in terms of retrieving features and statistics of clinical significance.
BibTeX:
@inbook{Gao2017,
  author = {Gao, Ju and Baskar, Siddharth and Teng, Diyan and al'Absi, Mustafa and Kumar, Santosh and Ertin, Emre},
  editor = {Rehg, James M. and Murphy, Susan A. and Kumar, Santosh},
  title = {A New Direction for Biosensing: RF Sensors for Monitoring Cardio-Pulmonary Function},
  booktitle = {Mobile Health: Sensors, Analytic Methods, and Applications},
  publisher = {Springer International Publishing},
  year = {2017},
  pages = {289--312},
  url = {https://doi.org/10.1007/978-3-319-51394-2_15},
  doi = {10.1007/978-3-319-51394-2_15}
}
Gulzar MA, Interlandi M, Han X, Li M, Condie T and Kim M (2017), "Automated Debugging in Data-intensive Scalable Computing", In Proceedings of the 2017 Symposium on Cloud Computing. New York, NY, USA , pp. 520-534. ACM.
Abstract: Developing Big Data Analytics workloads often involves trial and error debugging, due to the unclean nature of datasets or wrong assumptions made about data. When errors (e.g., program crash, outlier results, etc.) arise, developers are often interested in identifying a subset of the input data that is able to reproduce the problem. BigSift is a new faulty data localization approach that combines insights from automated fault isolation in software engineering and data provenance in database systems to find a minimum set of failure-inducing inputs. BigSift redefines data provenance for the purpose of debugging using a test oracle function and implements several unique optimizations, specifically geared towards the iterative nature of automated debugging workloads. BigSift improves the accuracy of fault localizability by several orders-of-magnitude (∼103 to 107×) compared to Titian data provenance, and improves performance by up to 66× compared to Delta Debugging, an automated fault-isolation technique. For each faulty output, BigSift is able to localize fault-inducing data within 62% of the original job running time.
BibTeX:
@inproceedings{Gulzar:2017:ADD:3127479.3131624,
  author = {Gulzar, Muhammad Ali and Interlandi, Matteo and Han, Xueyuan and Li, Mingda and Condie, Tyson and Kim, Miryung},
  title = {Automated Debugging in Data-intensive Scalable Computing},
  booktitle = {Proceedings of the 2017 Symposium on Cloud Computing},
  publisher = {ACM},
  year = {2017},
  pages = {520--534},
  url = {https://md2k.org/images/papers/methods/p520-gulzar.pdf},
  doi = {10.1145/3127479.3131624}
}
Gulzar MA, Interlandi M, Condie T and Kim M (2017), "Debugging Big Data Analytics in Spark with BigDebug", In Proceedings of the 2017 ACM International Conference on Management of Data. , pp. 1627-1630.
Abstract: Developing Big Data Analytics workloads often involves trial and error debugging, due to the unclean nature of datasets or wrong assumptions made about data. When errors (e.g., program crash, outlier results, etc.) arise, developers are often interested in identify-ing a subset of the input data that is able to reproduce the problem. BIGSIFT is a new faulty data localization approach that combines insights from automated fault isolation in software engineering and data provenance in database systems to find a minimum set of failure-inducing inputs. BIGSIFT redefines data provenance for the purpose of debugging using a test oracle function and implements several unique optimizations, specifically geared towards the iterative nature of automated debugging workloads. BIGSIFT improves the accu-racy of fault localizability by several orders-of-magnitude (∼103 to 107×) compared to Titian data provenance, and improves perfor-mance by up to 66× compared to Delta Debugging, an automated fault-isolation technique. For each faulty output, BIGSIFT is able to localize fault-inducing data within 62% of the original job running time.
BibTeX:
@inproceedings{gulzar2017debugging,
  author = {Muhammad Ali Gulzar and Matteo Interlandi and Tyson Condie and Miryung Kim},
  title = {Debugging Big Data Analytics in Spark with BigDebug},
  booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data},
  year = {2017},
  pages = {1627--1630}
}
Hnat T, Hossain S, Ali N, Carini S, Condie T, Sim I, Srivastava M and Kumar S (2017), "mCerebrum and Cerebral Cortex: A Real-time Collection, Analytic, and Intervention Platform for High-frequency Mobile Sensor Data", In AMIA (American Medical Informatics Association) 2017 Annual Symposium.
Abstract: The Center of Excellence for Mobile Sensor Data to Knowledge (MD2K)1 has developed two open-source software platforms2 (for mobile phones and the cloud) that enables the collection of high-frequency raw sensor data (at 800+ Hz for 70+ million samples/day), curation, analytics, storage ( 2GB/day) and secure uploads to a cloud. mCere-brum supports concurrent collection of streaming data from multiple devices (including wearables: Microsoft Band, research-grade MotionSenseHRV, EasySense, and AutoSense), phone sensors (e.g., GPS), Omron scale and blood pressure monitors and a smart toothbrush. mCerebrum continuously assesses data quality to detect issues of sensor detachment or placement on the body so they can be addressed. Data science research conducted by MD2K has resulted in 10 mHealth biomarkers: stress likelihood, smoking via hand gestures, nicotine craving, eating, lung con-gestion, heart motion, location, physical activity, driving, and drug use. Several of these biomarkers are computed in real-time on the phone to support biomarker-triggered Just-in-Time Adaptive Interventions (JITAI).
Cerebral Cortex is the big data companion of mCerebrum designed to support population-scale data analysis, visu-alization, and model development. It currently supports thousands of concurrent mCerebrum instances and provides machine-learning model development capabilities on population-scale data sets. Cerebral Cortex supports the same mHealth biomarkers that our phone platform computes, but does so on the entire dataset using an Apache Spark pow-ered abstraction that is designed for batch-mode computations as well as near real-time analysis via a data science dashboard. The MD2K platform uses Open mHealth mobile data exchange standards that are being harmonized with FHIR for EHR data exchange. All MD2K software is available under the BSD 2-Clause license3.
By collecting and storing high-frequency raw sensor data, our approach enables external validation of computed biomarkers as well as computation of new biomarkers in the future. This benefit is akin to how biomedical stud-ies archive biospecimens in biobanks so that they can be reprocessed to take advantage of future improvements in assays and support discoveries not possible at the time of data collection. Our platform addresses the challenges of high frequency, large volume, rapid variability and battery life limitations to enable long-lasting digital biobanks or digibanks as research utilities for mobile-driven translational research.
This demonstration will showcase data collection and visualization from multiple wearable sensor platforms and just-in-time user engagement will demonstrate how the platform can react in real-time to biomarker events. The demon-stration will show how Cerebral Cortex’s capabilities for near real-time visualization of mCerebrum data are currently utilized to manage multiple concurrent clinical study participants at several sites across the United States. Finally, we will explore the interactive data science interface and showcase biomarker generation and model evaluation.
BibTeX:
@inproceedings{hnat2017mcerebrum,
  author = {Timothy Hnat and Syed Hossain and Nasir Ali and Simona Carini and Tyson Condie and Ida Sim and Mani Srivastava and Santosh Kumar},
  title = {mCerebrum and Cerebral Cortex: A Real-time Collection, Analytic, and Intervention Platform for High-frequency Mobile Sensor Data},
  booktitle = {AMIA (American Medical Informatics Association) 2017 Annual Symposium},
  year = {2017}
}
Ho B-J, Balaji B, Nikzad N and Srivastava M (2017), "Emu: Engagement Modeling for User Studies", In UbiTtention 2017: 2nd International Workshop on Smart &amp; Ambient Notification and Attention Management.
Abstract: Mobile technologies that drive just-in-time ecological momentary assessments and interventions provide an unprecedented view into user behaviors and opportunities to manage chronic conditions. The success of these methods rely on engaging the user at the appropriate moment, so as to maximize questionnaire and task completion rates. However, mobile operating systems provide little support to precisely specify the contextual conditions in which to notify and engage the user, and study designers often lack the expertise to build context-aware software themselves. To address this problem, we have developed Emu, a framework that eases the development of context-aware study applications by providing a concise and powerful interface for specifying temporal- and contextual-constraints for task notifications. In this paper we present the design of the Emu API and demonstrate its use in capturing a range of scenarios common to smartphone-based study applications.
BibTeX:
@inproceedings{ho2017emu,
  author = {Bo-Jhang Ho and Bharathan Balaji and Nima Nikzad and Mani Srivastava},
  title = {Emu: Engagement Modeling for User Studies},
  booktitle = {UbiTtention 2017: 2nd International Workshop on Smart &amp; Ambient Notification and Attention Management},
  year = {2017},
  url = {https://md2k.org/images/papers/software/UbiTtention2-13.pdf}
}
Hohman F, Hodas N and Chau DH (2017), "ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation", In Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems. Denver, Colorado, USA , pp. 1694-1699. ACM.
Abstract: Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as “black-boxes” due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user’s data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers
BibTeX:
@inproceedings{Hohman:2017:STU:3027063.3053103,
  author = {Fred Hohman and Nathan Hodas and Duen Horng Chau},
  title = {ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation},
  booktitle = {Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems},
  publisher = {ACM},
  year = {2017},
  pages = {1694--1699},
  url = {https://md2k.org/images/papers/methods/ea1694-hohman.pdf},
  doi = {10.1145/3027063.3053103}
}
Hossain SM, Hnat T, Saleheen N, Nasrin NJ, Noor J, Ho B-J, Condie T, Srivastava M and Kumar S (2017), "mCerebrum: An mHealth Software Platform for Development and Validation of Digital Biomarkers and Interventions", In The ACM Conference on Embedded Networked Sensor Systems (SenSys).
Abstract: The development and validation studies of new multisensory biomark-ers and sensor-triggered interventions requires collecting raw sen-sor data with associated labels in the natural field environment. Unlike platforms for traditional mHealth apps, a software platform for such studies needs to not only support high-rate data ingestion, but also share raw high-rate sensor data with researchers, while supporting high-rate sense-analyze-act functionality in real-time. We present mCerebrum, a realization of such a platform, which supports high-rate data collections from multiple sensors with real-time assessment of data quality. A scalable storage architecture (with near optimal performance) ensures quick response despite rapidly growing data volume. Micro-batching and efficient sharing of data among multiple source and sink apps allows reuse of com-putations to enable real-time computation of multiple biomarkers without saturating the CPU or memory. Finally, it has a reconfig-urable scheduler which manages all prompts to participants that is burden- and context-aware. With a modular design currently span-ning 23+ apps, mCerebrum provides a comprehensive ecosystem of system services and utility apps. The design of mCerebrum has evolved during its concurrent use in scientific field studies at ten sites spanning 106,806 person days. Evaluations show that com-pared with other platforms, mCerebrum’s architecture and design choices support 1.5 times higher data rates and 4.3 times higher storage throughput, while causing 8.4 times lower CPU usage.
BibTeX:
@inproceedings{hossain2017mcerebrum,
  author = {Syed Monowar Hossain and Timothy Hnat and Nazir Saleheen and Nusrat Jahan Nasrin and Joseph Noor and Bo-Jhang Ho and Tyson Condie and Mani Srivastava and Santosh Kumar},
  title = {mCerebrum: An mHealth Software Platform for Development and Validation of Digital Biomarkers and Interventions},
  booktitle = {The ACM Conference on Embedded Networked Sensor Systems (SenSys)},
  year = {2017}
}
Interlandi M, Ekmekji A, Shah K, Gulzar MA, Tetali SD, Kim M, Millstein T and Condie T (2017), "Adding data provenance support to Apache Spark", The VLDB Journal. , pp. 1-21. Springer Berlin Heidelberg.
Abstract: Debugging data processing logic in data-intensive scalable computing (DISC) systems is a difficult and time-consuming effort. Today’s DISC systems offer very little
tooling for debugging programs, and as a result, programmers spend countless hours collecting evidence (e.g., from log files) and performing trial-and-error debugging. To aid this effort, we built Titian, a library that enables data provenance—tracking data through transformations—in Apache Spark. Data scientists using the Titian Spark extension will be able to quickly identify the input data at the root cause of a potential bug or outlier result. Titian is built directly into the Spark platform and offers data provenance support at interactive speeds—orders of magnitude faster than alternative solutions—while minimally impacting Spark job performance; observed overheads for capturing data lineage rarely exceed 30% above the baseline job execution time.
BibTeX:
@article{interlandi2017adding,
  author = {Matteo Interlandi and Ari Ekmekji and Kshitij Shah and Muhammad Ali Gulzar and Sai Deep Tetali and Miryung Kim and Todd Millstein and Tyson Condie},
  title = {Adding data provenance support to Apache Spark},
  journal = {The VLDB Journal},
  publisher = {Springer Berlin Heidelberg},
  year = {2017},
  pages = {1--21}
}
Lemieux A, Nakajima M, Chatterjee S, Sarker H, Saleheen N, Ertin E, Kumar S and al'Absi M (2017), "Unobtrusive Measurement of Stress and Smoking Psychophysiological Markers in the Natural Environment", In PSYCHOSOMATIC MEDICINE. Vol. 79(4), pp. A150-A150.
BibTeX:
@inproceedings{lemieux2017unobtrusive,
  author = {Andrine Lemieux and Motohiro Nakajima and Soujanya Chatterjee and Hillol Sarker and Nazir Saleheen and Emre Ertin and Santosh Kumar and Mustafa al'Absi},
  title = {Unobtrusive Measurement of Stress and Smoking Psychophysiological Markers in the Natural Environment},
  booktitle = {PSYCHOSOMATIC MEDICINE},
  year = {2017},
  volume = {79},
  number = {4},
  pages = {A150--A150}
}
Liu Y-Y, Moreno A, Li S, Li F, Song L and Rehg JM (2017), "Learning Continuous-Time Hidden Markov Models for Event Data", In Mobile Health: Sensors, Analytic Methods, and Applications. Cham , pp. 361-387. Springer International Publishing.
Abstract: The Continuous-Time Hidden Markov Model (CT-HMM) is an attractive modeling tool for mHealth data that takes the form of events occurring at irregularly-distributed continuous time points. However, the lack of an efficient parameter learning algorithm for CT-HMM has prevented its widespread use, necessitating the use of very small models or unrealistic constraints on the state transitions. In this paper, we describe recent advances in the development of efficient EM-based learning methods for CT-HMM models. We first review the structure of the learning problem, demonstrating that it consists of two challenges: (1) the estimation of posterior state probabilities and (2) the computation of end-state conditioned expectations. The first challenge can be addressed by reformulating the estimation problem in terms of an equivalent discrete time-inhomogeneous hidden Markov model. The second challenge is addressed by exploiting computational methods traditionally used for continuous-time Markov chains and adapting them to the CT-HMM domain. We describe three computational approaches and analyze the tradeoffs between them. We evaluate the resulting parameter learning methods in simulation and demonstrate the use of models with more than 100 states to analyze disease progression using glaucoma and Alzheimer's Disease datasets.
BibTeX:
@inbook{Liu2017,
  author = {Liu, Yu-Ying and Moreno, Alexander and Li, Shuang and Li, Fuxin and Song, Le and Rehg, James M.},
  editor = {Rehg, James M. and Murphy, Susan A. and Kumar, Santosh},
  title = {Learning Continuous-Time Hidden Markov Models for Event Data},
  booktitle = {Mobile Health: Sensors, Analytic Methods, and Applications},
  publisher = {Springer International Publishing},
  year = {2017},
  pages = {361--387},
  url = {https://md2k.org/images/papers/methods/LearningC-THMM.pdf},
  doi = {10.1007/978-3-319-51394-2_19}
}
Naderiparizi S, Zhang P, Philipose M, Priyantha B, Liu J and Ganesan D (2017), "Glimpse: A programmable early-discard camera architecture for continuous mobile vision", In Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services. , pp. 292-305.
BibTeX:
@inproceedings{naderiparizi2017glimpse,
  author = {Saman Naderiparizi and Pengyu Zhang and Matthai Philipose and Bodhi Priyantha and Jie Liu and Deepak Ganesan},
  title = {Glimpse: A programmable early-discard camera architecture for continuous mobile vision},
  booktitle = {Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services},
  year = {2017},
  pages = {292--305}
}
Nilsen W, Ertin E, Hekler EB, Kumar S, Lee I, Mangharam R, Pavel M, Rehg JM, Riley W, Rivera DE and Spruijt-Metz D (2017), "Modeling Opportunities in mHealth Cyber-Physical Systems", In Mobile Health: Sensors, Analytic Methods, and Applications. Cham , pp. 443-453. Springer International Publishing.
Abstract: Cyber-physical systems, with their focus on creating closed-loop systems, have transformed a wide range of areas (e.g., flight systems, industrial plants, robotics, etc.). However, even after a century of health research we still lack dynamic computational models of human health and its interactions with the environment, let alone a full closed-loop cyber-physical system. A major hurdle to developing cyber-physical systems in the medical and health fields has been the lack of high-resolution data on changes in both outcomes and predictive variables in the natural environment. There are many public and private initiatives addressing these measurement issues and the health research community is witnessing rapid progress in this area. Consequently, there is an emerging opportunity to develop cyber-physical systems for mobile health (mHealth). This chapter describes research challenges in developing cyber-physical system models to build effective and safe mHealth interventions. Doing so involves significant advances in modeling of health, biology, and behavior and their interactions with the environment and response of humans to the mHealth interventions.
BibTeX:
@inbook{Nilsen2017,
  author = {Nilsen, Wendy and Ertin, Emre and Hekler, Eric B. and Kumar, Santosh and Lee, Insup and Mangharam, Rahul and Pavel, Misha and Rehg, James M. and Riley, William and Rivera, Daniel E. and Spruijt-Metz, Donna},
  editor = {Rehg, James M. and Murphy, Susan A. and Kumar, Santosh},
  title = {Modeling Opportunities in mHealth Cyber-Physical Systems},
  booktitle = {Mobile Health: Sensors, Analytic Methods, and Applications},
  publisher = {Springer International Publishing},
  year = {2017},
  pages = {443--453},
  url = {https://doi.org/10.1007/978-3-319-51394-2_23},
  doi = {10.1007/978-3-319-51394-2_23}
}
Parate A and Ganesan D (2017), "Detecting Eating and Smoking Behaviors Using Smartwatches", In Mobile Health: Sensors, Analytic Methods, and Applications. Cham , pp. 175-201. Springer International Publishing.
Abstract: Inertial sensors embedded in commercial smartwatches and fitness bands are among the most informative and valuable on-body sensors for monitoring human behavior. This is because humans perform a variety of daily activities that impacts their health, and many of these activities involve using hands and have some characteristic hand gesture associated with it. For example, activities like eating food or smoking a cigarette require the direct use of hands and have a set of distinct hand gesture characteristics. However, recognizing these behaviors is a challenging task because the hand gestures associated with these activities occur only sporadically over the course of a day, and need to be separated from a large number of irrelevant hand gestures. In this chapter, we will look at approaches designed to detect behaviors involving sporadic hand gestures. These approaches involve two main stages: (1) spotting the relevant hand gestures in a continuous stream of sensor data, and (2) recognizing the high-level activity from the sequence of recognized hand gestures. We will describe and discuss the various categories of approaches used for each of these two stages, and conclude with a discussion about open questions that remain to be addressed.
BibTeX:
@inbook{Parate2017,
  author = {Parate, Abhinav and Ganesan, Deepak},
  editor = {Rehg, James M. and Murphy, Susan A. and Kumar, Santosh},
  title = {Detecting Eating and Smoking Behaviors Using Smartwatches},
  booktitle = {Mobile Health: Sensors, Analytic Methods, and Applications},
  publisher = {Springer International Publishing},
  year = {2017},
  pages = {175--201},
  url = {https://doi.org/10.1007/978-3-319-51394-2_10},
  doi = {10.1007/978-3-319-51394-2_10}
}
Pienta R, Kahng M, Lin Z, Vreeken J, Talukdar P, Abello J, Parameswaran G and Chau DH (2017), "Facets: Adaptive Local Exploration of Large Graphs", In 17th SIAM International Conference on Data Mining.
BibTeX:
@inproceedings{pienta2017adaptive,
  author = {Robert Pienta and Minsuk Kahng and Zhang Lin and Jilles Vreeken and Partha Talukdar and James Abello and Ganesh Parameswaran and Duen Horng Chau},
  title = {Facets: Adaptive Local Exploration of Large Graphs},
  booktitle = {17th SIAM International Conference on Data Mining},
  year = {2017},
  url = {http://eda.mmci.uni-saarland.de/pubs/2017/facets-pienta,etal.pdf}
}
Dempsey WH, Moreno A, Scott CK, Dennis ML, Gustafson DH, Murphy SA and Rehg JM (2017), "iSurvive: An Interpretable, Event-time Prediction Model for mHealth", In Proceedings of the 34th International Conference on Machine Learning. International Convention Centre, Sydney, Australia, 06--11 Aug, 2017. Vol. 70, pp. 970-979. PMLR.
Abstract: An important mobile health (mHealth) task is the use of multimodal data, such as sensor streams and self-report, to construct interpretable time-to-event predictions of, for example, lapse to alcohol or illicit drug use. Interpretability of the prediction model is important for acceptance and adoption by domain scientists, enabling model outputs and parameters to inform theory and guide intervention design. Temporal latent state models are therefore attractive, and so we adopt the continuous time hidden Markov model (CT-HMM) due to its ability to describe irregular arrival times of event data. Standard CT-HMMs, however, are not specialized for predicting the time to a future event, the key variable for mHealth interventions. Also, standard emission models lack a sufficiently rich structure to describe multimodal data and incorporate domain knowledge. We present iSurvive, an extension of classical survival analysis to a CT-HMM. We present a parameter learning method for GLM emissions and survival model fitting, and present promising results on both synthetic data and an mHealth drug use dataset.
BibTeX:
@inproceedings{pmlr-v70-dempsey17a,
  author = {Walter H. Dempsey and Alexander Moreno and Christy K. Scott and Michael L. Dennis and David H. Gustafson and Susan A. Murphy and James M. Rehg},
  editor = {Doina Precup and Yee Whye Teh},
  title = {iSurvive: An Interpretable, Event-time Prediction Model for mHealth},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning},
  publisher = {PMLR},
  year = {2017},
  volume = {70},
  pages = {970--979},
  url = {https://md2k.org/images/papers/jitai/dempsey17a.pdf},
  doi = {http://proceedings.mlr.press/v70/dempsey17a.html}
}
Rabbi M, Philyaw-Kotov M, Lee J, Mansour A, Dent L, Wang X, Cunningham R, Bonar E, Nahum-Shani I, Klasnja P, Walton M and Murphy S (2017), "SARA: A Mobile App to Engage Users in Health Data Collection", In Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. New York, NY, USA , pp. 781-789. ACM.
Abstract: Despite the recent progress in sensor technologies, many relevant health data can be only captured with manual input (e.g., food intake, stress appraisal, subjective emotion, substance use). A common problem of manual logging is that users often disengage within a short time because of high burden. In this work, we propose SARA, a novel app to engage users with ongoing tracking using timely rewards thereby reinforcing users for data input. SARA is developed for adolescents and emerging adults at risk for substance abuse. The rewards in SARA are designed to be developmentally and culturally appropriate to the target demographic and are theoretically grounded in the behavioral science literature. In this paper, we describe SARA and its rewards to increase data collection. We also briefly discuss future plans to evaluate SARA and develop just in time adaptive interventions for engagement and behavior change.
BibTeX:
@inproceedings{Rabbi:2017:SMA:3123024.3125611,
  author = {Rabbi, Mashfiqui and Philyaw-Kotov, Meredith and Lee, Jinseok and Mansour, Anthony and Dent, Laura and Wang, Xiaolei and Cunningham, Rebecca and Bonar, Erin and Nahum-Shani, Inbal and Klasnja, Predrag and Walton, Maureen and Murphy, Susan},
  title = {SARA: A Mobile App to Engage Users in Health Data Collection},
  booktitle = {Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers},
  publisher = {ACM},
  year = {2017},
  pages = {781--789},
  url = {https://md2k.org/images/papers/jitai/sara-rabbi.pdf},
  doi = {10.1145/3123024.3125611}
}
Soha R, Addison M, Deepak G, Benjamin M and Jeremy G (2017), "iLid: Low-power Sensing of Fatigue and Drowsiness Measures on a Computational Eyeglass", Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. New York, NY, USA Vol. 1(2), pp. 23:1-23:26. ACM.
Abstract: The ability to monitor eye closures and blink patterns has long been known to enable accurate assessment of fatigue and drowsiness in individuals. Many measures of the eye are known to be correlated with fatigue including coarse-grained measures like the rate of blinks as well as #ne-grained measures like the duration of blinks and the extent of eye closures. Despite a plethora of research validating these measures, we lack wearable devices that can continually and reliably monitor them in the natural environment. In this work, we present a low-power system, iLid, that can continually sense fine-grained measures such as blink duration and Percentage of Eye Closures (PERCLOS) at high frame rates of 100fps. We present a complete solution including design of the sensing, signal processing, and machine learning pipeline; implementation on a prototype computational eyeglass platform; and extensive evaluation under many conditions including illumination changes, eyeglass shifts, and mobility. Our results are very encouraging, showing that we can detect blinks, blink duration, eyelid location, and fatigue-related metrics such as PERCLOS with less than a few percent error.
BibTeX:
@article{Soha:2017:ILS:3120957.3090088,
  author = {Soha, Rostaminia and Addison, Mayberry and Deepak, Ganesan and Benjamin, Marlin and Jeremy, Gummeson},
  title = {iLid: Low-power Sensing of Fatigue and Drowsiness Measures on a Computational Eyeglass},
  journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
  publisher = {ACM},
  year = {2017},
  volume = {1},
  number = {2},
  pages = {23:1--23:26},
  url = {https://md2k.org/images/papers/biomarkers/Ubicomp17-iLid.pdf},
  doi = {10.1145/3090088}
}
Spring B, Pfammatter A and Alshurafa N (2017), "First steps into the brave new transdiscipline of mobile health", JAMA Cardiology. Vol. 2(1), pp. 76-78.
BibTeX:
@article{Spring2017,
  author = {B Spring and A Pfammatter and N Alshurafa},
  title = {First steps into the brave new transdiscipline of mobile health},
  journal = {JAMA Cardiology},
  year = {2017},
  volume = {2},
  number = {1},
  pages = {76-78},
  url = {+ http://dx.doi.org/10.1001/jamacardio.2016.4440},
  doi = {10.1001/jamacardio.2016.4440}
}
Thomaz E, Bedri A, Prioleau T, Essa I and Abowd GD (2017), "Exploring Symmetric and Asymmetric Bimanual Eating Detection with Inertial Sensors on the Wrist", In Proceedings of the 1st Workshop on Digital Biomarkers. New York, NY, USA , pp. 21-26. ACM.
Abstract: Motivated by health applications, eating detection with off-the-shelf devices has been an active area of research. A common approach has been to recognize and model individual intake gestures with wrist-mounted inertial sensors. Despite promising results, this approach is limiting as it requires the sensing device to be worn on the hand performing the intake gesture, which cannot be guaranteed in practice. Through a study with 14 participants comparing eating detection performance when gestural data is recorded with a wrist-mounted device on (1) both hands, (2) only the dominant hand, and (3) only the non-dominant hand, we provide evidence that a larger set of arm and hand movement patterns beyond food intake gestures are predictive of eating activities when L1 or L2 normalization is applied to the data. Our results are supported by the theory of asymmetric bimanual action and contribute to the field of automated dietary monitoring. In particular, it shines light on a new direction for eating activity recognition with consumer wearables in realistic settings.
BibTeX:
@inproceedings{Thomaz:2017:ESA:3089341.3089345,
  author = {Thomaz, Edison and Bedri, Abdelkareem and Prioleau, Temiloluwa and Essa, Irfan and Abowd, Gregory D.},
  title = {Exploring Symmetric and Asymmetric Bimanual Eating Detection with Inertial Sensors on the Wrist},
  booktitle = {Proceedings of the 1st Workshop on Digital Biomarkers},
  publisher = {ACM},
  year = {2017},
  pages = {21--26},
  url = {https://md2k.org/images/papers/biomarkers/p21-thomaz.pdf},
  doi = {10.1145/3089341.3089345}
}
Wagner III B, Liu E, Shaw SD, Iakovlev G, Zhou L, Harrington C, Abowd G, Yoon C, Kumar S, Murphy S, Spring B and Nahum-Shani I (2017), "eWrapper: Operationalizing Engagement Strategies in mHealth", In Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. New York, NY, USA , pp. 790-798. ACM.
Abstract: The advancement of digital technologies particularly in the domain of mobile health (mHealth) holds great promise in the promotion of health behavior. However, keeping users engaged remains a central challenge. This paper proposes a novel approach to address this issue by supplementing existing and future mHealth applications with an engagement wrapper - a collection of engagement strategies integrated into a single, coherent model. The engagement wrapper is operationalized within the format of an ambient display on the lock screen of mobile devices.
BibTeX:
@inproceedings{Wagner:2017:EWO:3123024.3125612,
  author = {Wagner,III, Blake and Liu, Elaine and Shaw, Steven D. and Iakovlev, Gleb and Zhou, Linlu and Harrington, Christina and Abowd, Gregory and Yoon, Carolyn and Kumar, Santosh and Murphy, Susan and Spring, Bonnie and Nahum-Shani, Inbal},
  title = {eWrapper: Operationalizing Engagement Strategies in mHealth},
  booktitle = {Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers},
  publisher = {ACM},
  year = {2017},
  pages = {790--798},
  url = {https://md2k.org/images/papers/jitai/ewrapper-wagner.pdf},
  doi = {10.1145/3123024.3125612}
}