Project Description
Title: mCerebrum: Enabling Sense-Analyze-Act on Mobile Phones
About the webinar:
mCerebrum is a general-purpose software platform that supports discovery and validation of digital mHealth biomarkers and sensor-triggered interventions. It supports data collection from multiple sensors in phones and wearables (e.g., wrist- and chest-worn sensors, smart toothbrushes, as well as weight and blood pressure monitors). mCerebrum supports high-frequency raw sensor data collection in excess of 70+ million samples/day, along with their curation, analysis, storage (2GB/day), and secure upload to the cloud.
Built-in privacy controls allow participants to suspend/resume data collection from specific sensors. The entire pipeline of mobile sensor big data – collection, curation, feature extraction, biomarker computation, time series pattern mining, and micro-randomization – has been developed and fully-implemented on the phone to support real-time, biomarker-triggered notifications and interventions.
Built from the ground up by MD2K, mCerebrum comprises of 23+ apps in an ecosystem to allow mix-and-match to specific study requirements. It is being deployed concurrently in field studies at 10+ sites, processing and storing more than 100,000 person-days or 4.7 trillion data points. Data science research using this platform has resulted in identification of ten mHealth biomarkers, including stress, smoking, craving, eating, activity, and drug (cocaine) use.
“mCerebrum: Enabling Sense-Analyze-Act on Mobile Phones,” will be presented by Dr. Timothy W. Hnat, Chief Software Architect for MD2K, and Syed Monowar Hossain, Lead Software Engineer for MD2K.
This first webinar in a series focuses on introducing mCerebrum and will provide an overview of the platform to both data science and health science researchers, discusses the design decisions necessary for real-time biomarker generation, and demonstrates the platform’s various capabilities.
Future webinar topics will include instruction on setting up mCerebrum to run a field study, and analyzing data with Cerebral Cortex, mCerebrum’s Big Data counterpart, for mHealth biomarker discovery.
About the presenters:
Dr. Timothy W. Hnat is Chief Software Architect for the MD2K Center. He previously served as Assistant Professor of Computer Science at the University of Memphis. His research interests cover several areas of the construction and evaluation of distributed systems, including compilers, programming languages, networking, and wireless sensor networks. He seeks to harness the potential of distributed systems to affect and interact with the physical world to address mHealth issues.
Monowar Hossain is Lead Software Engineer for the MD2K Center. He will receive his Ph.D. in Computer Science in May from the University of Memphis. He has 4+ years of experience in designing, implementing, integrating, testing and supporting mHealth applications to conduct research studies using wearable sensors for mobile devices on the Android platform. His research interest is on real time inference of different user behavior and context from physiological measurements collected from body-worn sensors.
