Beyond the time-on-task: an EEG-driven approach for effective physiological assessment of mental fatigue in simulated and real driving

Giorgi, Andrea; Ronca, Vincenzo; Capotorto, Rossella; Vozzi, Alessia; Rossi, Dario; Aricò, Pietro; Borghini, Gianluca; Van Gasteren, Marteyn; Melus, Javier; Petrelli, Marco; Sportiello, Simone; Polidori, Carlo; Picardi, Manuel; Babiloni, Fabio; Di Flumeri, Gianluca · 2025 · Crossref

DOI: 10.3389/fbioe.2025.1682103

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 limitations of the traditional Time-on-Task (ToT) method for assessing mental fatigue in driving, which assumes uniform fatigue onset across individuals and often fails to capture individual variability. The authors propose an EEG-driven labeling approach to more accurately identify fatigue onset by leveraging physiological markers rather than arbitrary time intervals. The research aims to compare the efficacy of ToT-driven versus EEG-driven methods in detecting physiological correlates of fatigue and to examine differences in fatigue manifestation between simulated and real driving environments. The experimental design involved 14 professional male drivers who participated in both simulated and real-world driving conditions, separated by several months. The protocol included a high-demanding driving task followed by a 45-minute low-demanding, monotonous task designed to induce fatigue. Physiological data were collected using electroencephalography (EEG), electrooculography (EOG), and photoplethysmography (PPG) to monitor brain activity, ocular dynamics, and heart rate variability. Two labeling strategies were applied to define low and high fatigue periods: the traditional ToT method, which designated the beginning and end of the task as low and high fatigue, respectively, and a novel EEG-driven method that used an EEG-derived drowsiness index to identify individual-specific fatigue onset. Subjective assessments were also collected using the Karolinska Sleepiness Scale and Chalder Fatigue Scale. The results demonstrated that the ToT-driven approach failed to reveal significant differences in physiological responses between low and high fatigue periods in either simulated or real driving conditions. In contrast, the EEG-driven labeling method successfully identified clear physiological changes associated with fatigue onset, including significant alterations in ocular activity (blink rate and duration) and heart activity. These findings indicate that physiology-based labeling is more sensitive to the individual dynamics of fatigue development than time-based assumptions. The study also explored differences between simulated and real driving, noting that while the EEG-driven method was effective in both contexts, the specific physiological manifestations varied, highlighting the importance of validating simulator data against real-world conditions. The significance of this research lies in its demonstration that the method used to define fatigue substantially influences the detection of its physiological correlates. By validating an EEG-driven approach, the study provides a more robust, objective, and individualized tool for assessing mental fatigue. This has important implications for the development of Advanced Driver Assistance Systems (ADAS) and other safety technologies, as it allows for more accurate detection of fatigue onset, potentially enabling earlier interventions. Furthermore, the findings underscore the need for careful consideration of experimental settings when studying driving fatigue, as simulated environments may not fully replicate the physiological responses observed in real-world driving.

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
• time on task
• drowsiness
• workload measurement
• neuro workload indices
• truck driver fatigue

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