Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier

https://orcid.org/0000-0003-0404-2729

AccessType

Open Access Dissertation

Document Type

dissertation

Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded

2022

Month Degree Awarded

September

First Advisor

Prof. Deepak Ganesan

Subject Categories

Biomedical | Biomedical Devices and Instrumentation | Hardware Systems | Other Computer Sciences | Signal Processing

Abstract

Research studies show that sleep deprivation causes severe fatigue, impairs attention and decision making, and affects our emotional interpretation of events, which makes it a big threat to public safety, and mental and physical well-being. Hence, it would be most desired if we could continuously measure one’s drowsiness and fatigue level, their emotion while making decisions, and assess their sleep quality in order to provide personalized feedback or actionable behavioral suggestions to modulate sleep pattern and alertness levels with the aim of enhancing performance, well-being, and quality of life. While there have been decades of studies on wearable devices, we still lack good instruments to measure an individual’s cognitive state in natural settings. In this thesis, we propose novel eyewear solutions in order to track various cognitive states, with the focus of being low-power, unobtrusive, and robust to confounders present in everyday scenarios. We propose the following contributions: i) design and implementation of a system, iLid, that is able to extract key features of fatigue and drowsiness at low power and high frame rate from a wearable eye tracker in natural settings, ii) design of a privacy-sensitive system, W!NCE, for detecting various facial expressions and pain instances, by leveraging only three small dry electrodes on the nose-bridge of a normal looking pair of glasses, and iii) design of a comfortable, unobtrusive, and accurate sleep monitoring system, PhyMask that can be worn continuously during long duration of wear without impacting sleep. We introduce novel fabric-based sensing elements to measure various physiological signals such as brain activity, eye movement patterns, heart rate, and breathing rate as well as head posture and body motions during sleep.

DOI

https://doi.org/10.7275/30112309

Download

Share

COinS