University of Michigan
105 Jordan Hall
Refreshments will be provided from 3:30 - 4:00 PM in the Jordan Hall Galleria
Supervised learning of health-related secret codes from wearable device data
Wearable devices are becoming a popular mini-robot to collect real-time information on well-being from a device user. One primary goal is to extract and validate features relevant to personal health conditions from massive high-frequency time-series measurements, so that each device user can utilize personal secret codes to guide personal health management. In this talk, I will introduce three smart personal wearables, Empatica E4, ActiGraph GTX and YONO Earbud, that have been used in various public health research projects, and then demonstrate how data collected from these devices may be used to solve some important health-related questions such as sleep health, physical activities, and reproductive health. I will give an overview on the application of different supervised learning techniques to process wearable device data and build tailored AI-systems to assist people with health-related decision making.