Multimodal Estimation of Change Points of Physiological Arousal in Drivers

TL;DR

This paper presents a multimodal physiological data analysis framework to detect change points in drivers' arousal states, aiming to improve safety interventions during driving.

Contribution

It introduces a novel approach combining multiple physiological signals to accurately identify arousal change points in drivers, validated across public datasets.

Findings

Physiological measures reliably indicate arousal change points.

The framework performs robustly across different datasets.

Time-series segmentation effectively captures driver state changes.

Abstract

Detecting unsafe driving states, such as stress, drowsiness, and fatigue, is an important component of ensuring driving safety and an essential prerequisite for automatic intervention systems in vehicles. These concerning conditions are primarily connected to the driver's low or high arousal levels. In this study, we describe a framework for processing multimodal physiological time-series from wearable sensors during driving and locating points of prominent change in drivers' physiological arousal state. These points of change could potentially indicate events that require just-in-time intervention. We apply time-series segmentation on heart rate and breathing rate measurements and quantify their robustness in capturing change points in electrodermal activity, treated as a reference index for arousal, as well as on self-reported stress ratings, using three public datasets. Our experiments demonstrate that physiological measures are veritable indicators of change points of arousal and perform robustly across an extensive ablation study.