Research interests

Computationally detecting and modeling health-related behavior using interactive systems; combining wearable sensing and user interface systems to support preventive medicine and personal, behavioral informatics; novel technologies and algorithms for real-time and longitudinal measurement of behavior; persuasive user interfaces for motivating behavior change; sensor-enabled mobile health technologies; context-aware ecological momentary assessment; experimental ubiquitous and mobile computing; active transportation (via bicycle).

I am exploring the development and evaluation of personal, behavioral health informatics – how sensor data acquired throughout everyday life from smartwatches, smartphones, wearable monitors, and in-home sensors might be used to improve wellness via novel human-computer interfaces. This research involves merging ideas from the computer science subfields of human-computer interaction, applied pattern recognition and machine learning, and computational sensing and artificial intelligence with ideas from behavioral science, behavioral medicine, social psychology, and preventive medicine. I am particularly interested in how algorithms that reliably recognize everyday activities and habits can drive the development of interactive preventive health tools that could ultimately be applied at the population scale in a cost-effect manner. Within computer science, this requires developing new user-driven activity detection algorithms that use context and common-sense information, without requiring large training sets; a focus is on person-in-the-loop interactive, explanatory behavior recognition interfaces. Within preventive medicine, this requires building and deploying pilot systems and demonstrating that the technology has a meaningful impact on health outcomes; a focus is on demonstrating that technology can support long-term engagement with behavior change and maintenance. As part of this work, my research group has worked to create new tools that can be used to both measure and motivate behavior change using novel sensor-based technologies.