Psychophysiology of Monotonous Driving, Fatigue and Sleepiness in Train and Non-Professional Drivers: Driver Safety Implications

Abstract

Fatigue and sleepiness are complex bodily states associated with monotony as well as physical and cognitive impairment, accidents, injury, and illness. Moreover, these states are often characteristic of professional driving. However, most existing work has focused on motor vehicle drivers, and research examining train drivers remains limited. As such, the present study psychophysiologically examined monotonous driving, fatigue, and sleepiness in a group of passenger train drivers and a group of non-professional drivers. Sixty-three train drivers and thirty non-professional drivers participated in the present study, which captured 32-lead electroencephalogram (EEG) data during a monotonous driving task. Fatigue and sleepiness were self-evaluated using the Pittsburgh Sleep Quality Index, the Epworth Sleepiness Scale, the Karolinksa Sleepiness Scale, and the Checklist of Individual Strength. Unexpectedly, fatigue and sleepiness scores did not significantly differ between the groups; however, train drivers generally scored lower than non-professional drivers, which may be indicative of individual and/or industry attempts to reduce fatigue. Across both groups, fatigue and sleepiness scores were negatively correlated with theta, alpha, and beta EEG variables clustered towards the fronto-central and temporal regions. Broadly, these associations may reflect a monotony-associated blunting of neural activity that is associated with a self-reported fatigue state.

A Novel Approach for Automatic Detection of Driver Fatigue Using EEG Signals Based on Graph Convolutional Networks

“…Finally, these researchers achieved a high accuracy of 99% for the classification of two classes, normal and fatigue. Lee et al [ 15 ] presented a statistical model using fatigue evaluation criteria, including the Epworth sleepiness scale and Carolina sleepiness scale, in order to evaluate driver fatigue. In this research, they used 32 channels of EEG signals.…”

“…Fouad et al[13] Hand-Crafted Features-SVM 98Kumar et al [14] ELM-SVM 98Lee et al[15] PSD 95Ha et al[16] Fuzzy delay index-SVM…”