Assessment of Driver Stress from Physiological Signals collected under Real-Time Semi-Urban Driving Scenarios

Abstract

Designing a wearable driver assist system requires extraction of relevant features from physiological signals like galvanic skin response and photoplethysmogram collected from automotive drivers during real-time driving. In the discussed case, four stress-classes were identified using cascade forward neural network (CASFNN) which performed consistently with minimal intra- and inter-subject variability. Task-induced stress-trends were tracked using Triggs’ Tracking Variable-based regression model with CASFNN configuration. The proposed framework will enable proactive initiation of rescue and relaxation procedures during accidents and emergencies.

Keywords

• Wearable Driver Assist Systems
• Physiological Signals
• Affective State
• Stress-Trends
• Neural Networks