Multimodal characterization of mental fatigue on professional drivers

Giorgi, Andrea; Ronca, Vincenzo; Vozzi, Alessia; Aricò, Pietro; Borghini, Gianluca; Tamborra, Luca; Simonetti, Ilaria; Sportiello, Simone; Petrelli, Marco; Varga, Rodrigo; Van Gasteren, Marteyn; Babiloni, Fabio; Di Flumeri, Gianluca · 2023 · Crossref

DOI: 10.54941/ahfe1003009

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the critical safety issue of mental fatigue among professional drivers, which contributes to approximately 20% of car accidents. Current on-board detection systems often fail to identify drowsiness before it becomes dangerous, resulting in high false-positive rates and driver mistrust. The research aims to develop a multimodal methodology capable of detecting the initial phases of mental fatigue before they manifest in driving behavior, thereby enabling earlier intervention. The experimental protocol involved ten professional drivers who participated in a simulated driving study conducted in the afternoon to maximize fatigue susceptibility. The design consisted of two sequential tasks: a 15-minute high-demand circuit race to induce initial fatigue, followed by a 45-minute monotonous driving task in a low-traffic environment. During the monotonous phase, participants performed a secondary reaction task involving responses to simulated engine alarms. Data collection was multimodal, utilizing Electroencephalography (EEG) and Electrooculography (EOG) for neurophysiological assessment, reaction times for behavioral assessment, and subjective questionnaires (Karolinska Sleepiness Scale, Chalder Fatigue Scale, and Driver Activity Load Index) for self-reported fatigue and workload. The results demonstrated that subjective measures significantly increased after the monotonous driving task, confirming the induction of mental fatigue. Neurophysiologically, the Mental Drowsiness Index (MDrow), derived from increased alpha-band activity in the parietal region, showed a significant rise during the final segment of the monotonous task compared to the initial segment. Crucially, this EEG-based index detected fatigue progression before any significant changes appeared in behavioral metrics. Reaction times to the secondary task and Eyeblink Rate (EBR) did not show statistically significant variations throughout the experiment, despite a visible tendency for EBR to increase. The study concludes that EEG-based metrics, specifically the MDrow index, are more sensitive than traditional behavioral or oculographic measures for detecting the early onset of mental fatigue. While drivers reported feeling fatigued and exhibited corresponding cortical changes, their reaction times and blink rates remained within normal ranges, suggesting that behavioral degradation occurs later in the fatigue process. These findings imply that relying solely on EBR or reaction time for fatigue detection may be insufficient for preventing accidents. Integrating EEG-based monitoring could provide a more reliable and timely warning system, enhancing road safety for professional drivers by identifying risk before performance impairment becomes evident.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms
• drowsiness
• workload measurement
• time on task
• truck driver fatigue
• vigilance

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: physiological data
• Methodological Resource: validation psychometrics, tool software