I'm a Ph.D. Candidate at CMU - SCS - HCII developing mobile health interventions that change dynamically with the patient's context, disease progression and preferences. My mision is to improve people's health and wellness by reimagining traditional health interventions making them interactive and smart by harnessing sensor data, human-feedback and artificial intelligence. I draw heavily from behavior change and health models and theories to inform the design and implementation of mobile health interventions.
My work has resulted in over 880+ citations and 19 publications at top venues (CHI, IMWUT(Ubicomp), PERCOM). I have received multiple distinctions like: the 2019 Microsoft Dissertation Grant, The 2017 Digital Health Fellowship by the CMU Center of Machine Learning and Health, a best paper award in Ubicomp-2016 and I was a finalist for the 2016 Facebook Fellowship.
I'm advised by Anind Dey and Mayank Goel.
I started my research developing sensing and machine learning techniques to detect basic human behavior like walking and sitting, then I move on to identify people's state of mind like stress and interruptibility. Currently, I use those basic sensing techniques to inform mobile health interventions. I use reinforcement learning and human feedback to adapt interventions that maximize adherence and health outcomes.
Arrows indicate how some projects informed or are follow up work on the same area. This diagram was inspired by Gierad Laput's Research overview map.
Reinforcement learning methods that adapt mobile health interventions autonomously to the user using sensor data and human-feedback.
Detection of stress episodes from physiological signals (e.g., heart rate, breathing rate) while stationary or exercising (e.g., walking, running, cycling) at different effort levels.
Based on Creative template