EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid deep learning for mental workload classification using EEG with enhanced preprocessing and interpretability

Osama Abdelrahman iD, Chew XinYing iD, Esraa Faisal Malik, Khaw Khai Wah, Cheong Zhi Lin iD, Teoh Wei Lin iD

PLOS One · 26.06.2026 · 21 (6) · e0352882

DOI: 10.1371/journal.pone.0352882 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 26.06.2026. Verfasst von Osama Abdelrahman und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Sciences, Universiti Sains Malaysia, Gelugor, Penang, Malaysia. Hauptthemen laut MEDLINE: Deep Learning, Electroencephalography, Workload. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universiti Sains Malaysia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mental workload classification is critical in safety-sensitive fields such as healthcare and aviation. However, electroencephalography-based approaches still face challenges with generalizability, noise robustness, and interpretability. In this study, we propose an integrated hybrid deep learning framework to address these limitations and enable robust, interpretable electroencephalography-based mental workload classification. The proposed approach uses a Variational Autoencoder to enhance noise reduction and feature extraction from band-wise topographical videos, a Convolutional Block Attention Module to adaptively focus on important spatial-channel Electroencephalogram features, and a Bidirectional Long Short-Term Memory network to capture complex temporal dependencies under leave-one-subject-out cross-validation. We conducted ablation studies to identify each architecture component’s contribution and sensitivity analyses to determine the optimal parameters. The model achieved the highest overall accuracy among the baselines and reached an average accuracy of 83.9% across subjects for classifying four mental workload levels. Ablation studies confirmed the added value of all three architecture components for improving performance. Sensitivity analyses identified optimal parameters, including a 10-second window length that balances temporal context and specificity. For better interpretability and neurophysiological insight, we used Gradient-weighted Class Activation Mapping to visualize key frontal-parietal brain regions and frequency bands associated with workload dynamics. Future research could explore adaptive windowing strategies, multimodal data integration, cross-dataset benchmarking, and evaluation against transformer-based and graph neural network architectures under consistent subject-independent evaluation settings to further enhance model generalizability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElectroencephalographyWorkloadHumansAutoencoderLong Short Term MemorySignal Processing, Computer-Assisted

Autor:innen und Institutionen

  • School of Computer Sciences, Universiti Sains Malaysia, Gelugor, Penang, Malaysia.
  • Department of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates.
  • School of Management, Universiti Sains Malaysia, Gelugor, Penang, Malaysia.
  • Faculty of Engineering and Green Technology, Department of Electronic Engineering, UTAR Kampar Campus, Kampar, Perak, Malaysia.
  • School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia.

ORCID-Profile: Osama Abdelrahman, Chew XinYing, Cheong Zhi Lin, Teoh Wei Lin

Förderung

  • Universiti Sains Malaysia

Zitieren

APA

Abdelrahman, O., XinYing, C., Malik, E. F., Wah, K. K., Lin, C. Z., & Lin, T. W. (2026). Hybrid deep learning for mental workload classification using EEG with enhanced preprocessing and interpretability. PLOS One, 21(6), e0352882. https://doi.org/10.1371/journal.pone.0352882

Vancouver

Abdelrahman O, XinYing C, Malik EF, Wah KK, Lin CZ, Lin TW. Hybrid deep learning for mental workload classification using EEG with enhanced preprocessing and interpretability. PLOS One. 2026;21(6):e0352882. doi:10.1371/journal.pone.0352882

BibTeX
@article{Abdelrahman2026,
  author = {Abdelrahman, Osama and XinYing, Chew and Malik, Esraa Faisal and Wah, Khaw Khai and Lin, Cheong Zhi and Lin, Teoh Wei},
  title = {Hybrid deep learning for mental workload classification using EEG with enhanced preprocessing and interpretability},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0352882},
  doi = {10.1371/journal.pone.0352882}
}
Kostenlos starten →