EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Hybrid Approach for Drowsiness Detection Using EEG Scalograms to Overcome Inter-Subject Variability

Aymen Zayed, Nidhameddine Belhadj, Khaled Ben Khalifa iD, Carlos Valderrama iD, Mohamed Hedi Bedoui iD

Sensors · 2025

DOI: 10.3390/s25175530 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Aymen Zayed und 4 weiteren Autor:innen. Beteiligte Einrichtung: Service d'électronique et de Microélectronique, University of Mons, 7000 Mons, Belgium. Hauptthemen laut MEDLINE: Electroencephalography, Sleep Stages. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drowsiness constitutes a significant risk factor in diverse occupational settings, including healthcare, industry, construction, and transportation, contributing to accidents, injuries, and fatalities. Electroencephalography (EEG) signals, offering direct measurements of brain activity, have emerged as a promising modality for drowsiness detection. However, the inherent non-stationary nature of EEG signals, coupled with substantial inter-subject variability, presents considerable challenges for reliable drowsiness detection. To address these challenges, this paper proposes a hybrid approach combining convolutional neural networks (CNNs), which excel at feature extraction, and support vector machines (SVMs) for drowsiness detection. The framework consists of two modules: a CNN for feature extraction from EEG scalograms generated by the Continuous Wavelet Transform (CWT), and an SVM for classification. The proposed approach is compared with 1D CNNs (using raw EEG signals) and transfer learning models such as VGG16 and ResNet50 to identify the most effective method for minimizing inter-subject variability and improving detection accuracy. Experimental evaluations, conducted on the publicly available DROZY EEG dataset, show that the CNN-SVM model, utilizing 2D scalograms, achieves an accuracy of 98.33%, outperforming both 1D CNNs and transfer learning models. These findings highlight the effectiveness of the hybrid CNN-SVM approach for robust and accurate drowsiness detection using EEG, offering significant potential for enhancing safety in high-risk work environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySleep StagesHumansSupport Vector MachineNeural Networks, ComputerWavelet AnalysisAlgorithmsSignal Processing, Computer-AssistedBrain

Stichwörter der Autor:innen

CNNEEGdeep learningdrowsinessscalogramtransfer learning

Autor:innen und Institutionen

  • Service d'électronique et de Microélectronique, University of Mons, 7000 Mons, Belgium.
  • Research Laboratory of Technology and Medical Imaging-LTIM-LR12ES06, Faculty of Medicine of Monastir, Monastir 5000, Tunisia.
  • National Engineering School of Sousse, University of Sousse, Sousse 4054, Tunisia.
  • Laboratory of Electronics and Microelectronics, Faculty of Sciences of Monastir, Monastir 5019, Tunisia.
  • Higher Institute of Applied Science and Technology of Sousse, Sousse 4003, Tunisia.

ORCID-Profile: Khaled Ben Khalifa, Carlos Valderrama, Mohamed Hedi Bedoui

Zitieren

APA

Zayed, A., Belhadj, N., Ben Khalifa, K., Valderrama, C., & Bedoui, M. H. (2025). A Novel Hybrid Approach for Drowsiness Detection Using EEG Scalograms to Overcome Inter-Subject Variability. Sensors. https://doi.org/10.3390/s25175530

Vancouver

Zayed A, Belhadj N, Ben Khalifa K, Valderrama C, Bedoui MH. A Novel Hybrid Approach for Drowsiness Detection Using EEG Scalograms to Overcome Inter-Subject Variability. Sensors. 2025. doi:10.3390/s25175530

BibTeX
@article{Zayed2025,
  author = {Zayed, Aymen and Belhadj, Nidhameddine and Ben Khalifa, Khaled and Valderrama, Carlos and Bedoui, Mohamed Hedi},
  title = {A Novel Hybrid Approach for Drowsiness Detection Using EEG Scalograms to Overcome Inter-Subject Variability},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25175530}
}
Kostenlos starten →