MSDA ‐Net: Multiscale Spatiotemporal Dual‐Attention Network for EEG ‐Based Driver Fatigue Detection
Journal of Sleep Research · 2026
DOI: 10.1111/jsr.70230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Sleep Research, 2026. Verfasst von Isah Bello und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Tianjin University, Tianjin, China. Hauptthemen laut MEDLINE: Electroencephalography, Fatigue, Attention, Automobile Driving. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Foundation of Tianjin Municipality.
Abstract (Originalsprache)
Driver fatigue poses a severe risk to road safety, contributing to approximately 20% of fatal accidents worldwide. While EEG signals are the gold standard for detecting fatigue, existing methods struggle to capture the complex spatiotemporal patterns in EEG data. We propose MSDA‐Net, a multiscale spatiotemporal dual‐attention network that integrates multiscale CNNs, GRUs and dual‐attention mechanisms to dynamically prioritise spatial channels and temporal segments, which are critical for fatigue detection. The model processes EEG data through three blocks: a multidimensional signal encoding block, which transforms raw signals into 4D differential entropy features; a multiscale spatial attention block, which extracts local and global spatial patterns; and a temporal modelling block, featuring a GRU and temporal attention. Finally, a fully connected layer and sigmoid activation are used to classify fatigue states. Evaluated on the SEED‐VIG dataset, MSDA‐Net achieves state‐of‐the‐art performance, significantly outperforming existing methods. This study can provide new insights into brain fatigue research and play a significant role in advancing the field's development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
- School of Automation Science and Electrical Engineering, Beihang University, Beijing, China.
- Department of Informatics and Information Technology, Sokoine University of Agriculture, Morogoro, Tanzania.
- Department of Physics, Faculty of Physical Sciences, Bayero University Kano, Kano, Nigeria.
ORCID-Profile: Isah Bello, Weidong Dang, Yunusa Haruna, Jamal F Banzi, Zhongke Gao
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Natural Science Foundation of Tianjin Municipality
- Taishan Industry Leading Talents
Zitieren
APA
Bello, I., Sehnan, M., Dang, W., Haruna, Y., Banzi, J. F., Aminu, S., & Gao, Z. (2026). MSDA ‐Net: Multiscale Spatiotemporal Dual‐Attention Network for EEG ‐Based Driver Fatigue Detection. Journal of Sleep Research. https://doi.org/10.1111/jsr.70230
Vancouver
Bello I, Sehnan M, Dang W, Haruna Y, Banzi JF, Aminu S, et al. MSDA ‐Net: Multiscale Spatiotemporal Dual‐Attention Network for EEG ‐Based Driver Fatigue Detection. Journal of Sleep Research. 2026. doi:10.1111/jsr.70230
BibTeX
@article{Bello2026,
author = {Bello, Isah and Sehnan, Moeed and Dang, Weidong and Haruna, Yunusa and Banzi, Jamal F and Aminu, Sha'awanatu and Gao, Zhongke},
title = {MSDA ‐Net: Multiscale Spatiotemporal Dual‐Attention Network for EEG ‐Based Driver Fatigue Detection},
journal = {Journal of Sleep Research},
year = {2026},
doi = {10.1111/jsr.70230}
}
EUVIMED