Smartphone apps with self-monitoring and sensing capabilities can help in disease prevention; however, such context-aware applications are difficult to develop, due to the complexities of sensor data acquisition, context modeling, and data management. To ease the development of mHealth and Telemedicine apps, we developed the Mobile Sensing Framework (MSF), which dynamically installs device appropriate context sensing plug-ins that provide a wealth of information about users’ mental and physical states. Our approach uses our Dynamix Framework, which enables the MSF to discover, download and install sensing plug-ins during runtime. The MSF automatically collects information about incoming/outgoing/missed calls; apps usage; sound pressure levels; light sensor values; movement data (e.g., step count); location; heart rate; etc. The MSF includes a searchable object-based persistence layer, which is capable of rapidly serializing and de-serializing detected context data. Collected data are stored securely in the phone’s database, where they can be retrieved by applications for local analysis, remote monitoring, and alert generation.
Links: Paper, MobileMed 2013, Gabor Novak, Darren Carlson, Stan Jarzabek. This work was sponsored by the Department of Computer Science at the National University of Singapore and Microsoft Research Asia.
Paper Accepted at MobileMed 2013