Towards Generalizable Drowsiness Monitoring with Physiological Sensors: A Preliminary Study

TL;DR

This study analyzes physiological signals like ECG, EDA, and RESP across multiple datasets to identify key features associated with drowsiness, revealing that different inducers cause distinct responses and objective assessments are more sensitive.

Contribution

It provides a comparative analysis of physiological metrics across diverse datasets, highlighting factors influencing drowsiness detection and informing future generalizable monitoring methods.

Findings

Increased heart rate stability correlates with drowsiness.

Reduced respiratory amplitude is associated with drowsiness.

Decreased tonic EDA indicates higher drowsiness levels.

Abstract

Accurately detecting drowsiness is vital to driving safety. Among all measures, physiological-signal-based drowsiness monitoring can be more privacy-preserving than a camera-based approach. However, conflicts exist regarding how physiological metrics are associated with different drowsiness labels across datasets. Thus, we analyzed key features from electrocardiograms (ECG), electrodermal activity (EDA), and respiratory (RESP) signals across four datasets, where different drowsiness inducers (such as fatigue and low arousal) and assessment methods (subjective vs. objective) were used. Binary logistic regression models were built to identify the physiological metrics that are associated with drowsiness. Findings indicate that distinct different drowsiness inducers can lead to different physiological responses, and objective assessments were more sensitive than subjective ones in detecting drowsiness. Further, the increased heart rate stability, reduced respiratory amplitude, and decreased tonic EDA are robustly associated with increased drowsiness. The results enhance understanding of drowsiness detection and can inform future generalizable monitoring designs.