Methodology and initial analysis results for development of non-invasive and hybrid driver drowsiness detection systems

Abstract

Application of piezofilm movement sensors integrated into the car seat, seat belt and steering wheel was proposed for development of a noninvasive and hybrid systems for detecting driver drowsiness. A car simulator study was designed to collect physiological data for validation of this technology. Methodology for analysis of physiological data, independent assessment of driver drowsiness and development of drowsiness detection algorithm by means of sequential fitting and selection of regression models is presented. Statistical analysis shows that during the episodes of transitions to dangerous levels of drowsiness movement variations recorded by the seat sensors are decreasing.