Psychophysiological Computational Modeling for Stress Management in VR Driving Simulation

Stress detection and management are vital for enhancing individual well-being and ensuring safe driving in high-pressure environments. In this study, we investigate the use of physiological indicators-specifically electrodermal activity (EDA), heart rate variability (HRV), and body temperature-to assess stress levels during virtual reality (VR) driving simulations. We propose a novel weighted aggregation approach that integrates refined metrics for EDA, HRV, and temperaturerelated stress factors, offering a comprehensive method for stress evaluation. While conventional machine learning (ML) and deep learning (DL) models are employed as analytical tools to support our framework, our primary contribution lies in establishing a robust methodology for stress detection. This work not only deepens the understanding of the complex interplay between physiological responses and stress but also lays a foundation for future research into adaptive stress management strategies and real-time monitoring solutions.