Faculty Recruiting Support CICS

Enabling Scalable Sleep Monitoring with Mobile Sensing and Machine Learning

07 Apr
Friday, 04/07/2023 10:30am to 12:30pm
Hybrid - LGRC A310 and Zoom
PhD Dissertation Proposal Defense

Abstract: Sleep is a critical component for the overall health of a human being. Despite its importance, a majority of the population is sleep deprived, leading to several physical and mental health issues. Traditional methods of sleep monitoring are expensive and not scalable, limiting access to important health information. The advent of the Internet of Things and mobile sensing devices provides an opportunity for more accessible and scalable sleep monitoring. Community-scale sensing has the potential to enable aggregate public health monitoring and informed decision-making for individuals. However, scaling mobile health sensing technologies to the community level presents several challenges, including data availability, model generalizability, robustness, etc. 

This thesis focuses on addressing the challenges of sleep monitoring at the community level by developing non-intrusive, scalable, personalizable, and robust sleep detection techniques. The first technique, called Wisleep, a system that utilizes an unsupervised machine-learning approach that detects sleep durations from the WiFi activity of mobile devices. WiSleep leverages the strong correlation between a phone's network activity and sleep periods and uses an ensemble of Bayesian models designed to handle irregular sleep patterns. The second technique, called SleepLess, is a semi-supervised machine learning approach that enables personalized sleep estimations for users without labeled data. Finally, I propose an approach combining uncertainty quantification with explainability to handle prediction inaccuracies from sleep prediction models. Overall, this thesis aims to provide innovative solutions to the challenges of mobile sleep monitoring and contribute to the broader field of mobile health sensing.

Advisor: Prashant Shenoy

Join via Zoom