Social Sensing for Epidemiological Behavior Change

6.8.2010 

PRESENTER:
Anmol Madan, SM, PhD Candidate, Human Dynamics Group, MIT Media Lab

 

 

MODERATOR:
Frank Moss, PhD, Director, MIT Media Lab; Professor of the Practice of Media Arts and Sciences and Jerome B. Wiesner Professorship of Media Technology

 

Video not available.

Forum Abstract

Anmol Madan will propose a novel healthcare application of ubiquitous computing. Madan's team uses mobile phone based co-location and communication sensing to measure characteristic behavior changes in symptomatic individuals, reflected in their total communication, interactions with respect to time of day (e.g. late night, early morning), diversity and entropy of face-to-face interactions and movement. Using these extracted mobile features, it is possible to predict the health status of an individual, without having actual health measurements from the subject. The team uses signal processing approaches to understand the temporal information flux between physical symptoms, behavior changes and mental health. In related analysis, they use similar data to study the link between BMI change and exposure to other individuals that are obese, overweight, physically inactive, and have unhealthy eating habits.

Post a Comment