EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on the Prediction of Driver Fatigue Degree Based on EEG Signals

Zhanyang Wang iD, Xin Du iD, Chengbin Jiang, Junyang Sun

Sensors · 01.12.2025 · 25 (23) · 7316

DOI: 10.3390/s25237316 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.12.2025. Verfasst von Zhanyang Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China. Hauptthemen laut MEDLINE: Automobile Driver Examination, Electroencephalography, Fatigue, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective: Predicting driver fatigue degree is crucial for traffic safety. This study proposes a deep learning model utilizing electroencephalography (EEG) signals and multi-step temporal data to predict the next time-step fatigue degree indicator percentage of eyelid closure (PERCLOS) while exploring the impact of different EEG features on prediction performance. Approach: A CTL-ResFNet model integrating CNN, Transformer Encoder, LSTM, and residual connections is proposed. Its effectiveness is validated through two experimental paradigms, Leave-One-Out Cross-Validation (LOOCV) and pretraining–finetuning, with comparisons against baseline models. Additionally, the performance of four EEG features—differential entropy, α/β band power ratio, wavelet entropy, and Hurst exponent—is evaluated, using RMSE and MAE as metrics. Main Results: The combined input of EEG and PERCLOS significantly outperforms using PERCLOS alone validated by LSTM, and CTL-ResFNet surpasses baseline models under both experimental paradigms. In LOOCV experiments, the α/β band power ratio performs best, whereas differential entropy excels in pretraining–finetuning. Significance: This study presents a high-performance hybrid deep learning framework for predicting driver fatigue degree and reveals the applicability differences in EEG features across experimental paradigms, offering guidance for feature selection and model deployment in practical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile Driver ExaminationElectroencephalographyFatigueDeep LearningHumansEyelidsPrognosisEye MovementsConvolutional Neural Networks

Stichwörter der Autor:innen

CTL-ResFNetPERCLOSdeep learningdriver fatigue predictionelectroencephalogram

Autor:innen und Institutionen

  • School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China.

ORCID-Profile: Zhanyang Wang, Xin Du

Zitieren

APA

Wang, Z., Du, X., Jiang, C., & Sun, J. (2025). Research on the Prediction of Driver Fatigue Degree Based on EEG Signals. Sensors, 25(23), 7316. https://doi.org/10.3390/s25237316

Vancouver

Wang Z, Du X, Jiang C, Sun J. Research on the Prediction of Driver Fatigue Degree Based on EEG Signals. Sensors. 2025;25(23):7316. doi:10.3390/s25237316

BibTeX
@article{Wang2025,
  author = {Wang, Zhanyang and Du, Xin and Jiang, Chengbin and Sun, Junyang},
  title = {Research on the Prediction of Driver Fatigue Degree Based on EEG Signals},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {23},
  pages = {7316},
  doi = {10.3390/s25237316}
}
Kostenlos starten →