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 has been decades of studies on wearable devices, we still lack good instruments to measure 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.
Advisor: Deepak Ganesan