Advancing Cognitive Load Detection in Simulated Driving Scenarios Through Deep Learning and fNIRS Data
Sensors · 2025
DOI: 10.3390/s25164921 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Mehshan Ahmed Khan und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC 3216, Australia. Hauptthemen laut MEDLINE: Automobile Driving, Deep Learning, Cognition. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council (ARC).
Abstract (Originalsprache)
The shift from manual to conditionally automated driving, supported by Advanced Driving Assistance Systems (ADASs), introduces challenges, particularly increased crash risks due to human factors like cognitive overload. Driving simulators provide a safe and controlled setting to study these human factors under complex conditions. This study leverages Functional Near-Infrared Spectroscopy (fNIRS) to dynamically assess cognitive load in a realistic driving simulator during a challenging night-time-rain scenario. Thirty-eight participants performed an auditory n-back task (0-, 1-, and 2-back) while driving, simulating multitasking demands. A sliding window approach was applied to the time-series fNIRS data to capture short-term fluctuations in brain activation. The data were analyzed using EEGNet, a deep learning model, with both overlapping and non-overlapping temporal segmentation strategies. Results revealed that classification performance is significantly influenced by the learning rate and windowing method. Notably, a learning rate of 0.001 yielded the highest performance, with 100% accuracy using overlapping windows and 97% accuracy with non-overlapping windows. These findings highlight the potential of combining fNIRS and deep learning for real-time cognitive load monitoring in simulated driving scenarios and demonstrate the importance of temporal modeling in physiological signal analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC 3216, Australia.
- College of Science and Engineering, James Cook University, Townsville, QLD 4814, Australia.
- Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, Australia.
- Hermann-Hesse Str. 17, 72221 Haiterbach, Germany.
- Building Controls GmbH, Schießmauer 18, 92283 Lauterhofen, Germany.
- Swinburne Research, Swinburne University of Technology, Hawthorn, Melbourne, VIC 3122, Australia.
ORCID-Profile: Mehshan Ahmed Khan, Mohammad Reza Chalak Qazani, Ghazal Bargshady, Thuong Hoang, Ghazal Rahimzadeh, Lei Wei
Förderung
- Australian Research Council (ARC)
Zitieren
APA
Khan, M. A., Asadi, H., Qazani, M. R. C., Bargshady, G., Oladazimi, S., Hoang, T., Rahimzadeh, G., Najdovski, Z., Wei, L., Moradi, H., & Nahavandi, S. (2025). Advancing Cognitive Load Detection in Simulated Driving Scenarios Through Deep Learning and fNIRS Data. Sensors. https://doi.org/10.3390/s25164921
Vancouver
Khan MA, Asadi H, Qazani MRC, Bargshady G, Oladazimi S, Hoang T, et al. Advancing Cognitive Load Detection in Simulated Driving Scenarios Through Deep Learning and fNIRS Data. Sensors. 2025. doi:10.3390/s25164921
BibTeX
@article{Khan2025,
author = {Khan, Mehshan Ahmed and Asadi, Houshyar and Qazani, Mohammad Reza Chalak and Bargshady, Ghazal and Oladazimi, Sam and Hoang, Thuong and Rahimzadeh, Ghazal and Najdovski, Zoran and Wei, Lei and Moradi, Hirash and Nahavandi, Saeid},
title = {Advancing Cognitive Load Detection in Simulated Driving Scenarios Through Deep Learning and fNIRS Data},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25164921}
}
EUVIMED