EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mental Workload Classification Using a Hybrid Model Based on EEG Brain Connectivity and Graph Convolutional Attention Networks

Mohammadreza Safari, Shaqayeq Rohelahi, Sara Bagherzadeh, Reza Shalbaf, Ahmad Shalbaf

IEEE Access · 2026 · 14 · 104966-104976

DOI: 10.1109/access.2026.3708784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Mohammadreza Safari und 4 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable and explainable detection of mental workload from EEG can advance both scientific understanding and practical monitoring. This study presents a compact pipeline that 1) employs directed effective connectivity (dDTF) across standard frequency bands to capture information flow, 2) encodes each time window as a $14\times 14$ directed adjacency graph, and 3) classifies workload using a hybrid Graph Convolutional + Graph Attention network with residual connections and dual global pooling. Hyperparameters were optimized automatically via Optuna, and model performance was assessed with cross-validation. Targeted ablation experiments and post-hoc interpretation using GNNExplainer were conducted to probe model behavior. The approach achieves strong within-dataset performance on STEW (90.1% accuracy, 87.5% precision, 93.6% recall, F1 score 90.43%). Ablations show that the attention layer, residual connections, and max-pooling each contribute measurable gains, while interpretability maps consistently highlight fronto-parietal and fronto-temporal connections as key discriminative features. These results link improved classification with neuroscience-aligned explanations.

Zitieren

APA

Safari, M., Rohelahi, S., Bagherzadeh, S., Shalbaf, R., & Shalbaf, A. (2026). Mental Workload Classification Using a Hybrid Model Based on EEG Brain Connectivity and Graph Convolutional Attention Networks. IEEE Access, 14, 104966-104976. https://doi.org/10.1109/access.2026.3708784

Vancouver

Safari M, Rohelahi S, Bagherzadeh S, Shalbaf R, Shalbaf A. Mental Workload Classification Using a Hybrid Model Based on EEG Brain Connectivity and Graph Convolutional Attention Networks. IEEE Access. 2026;14:104966-104976. doi:10.1109/access.2026.3708784

BibTeX
@article{Safari2026,
  author = {Safari, Mohammadreza and Rohelahi, Shaqayeq and Bagherzadeh, Sara and Shalbaf, Reza and Shalbaf, Ahmad},
  title = {Mental Workload Classification Using a Hybrid Model Based on EEG Brain Connectivity and Graph Convolutional Attention Networks},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {104966--104976},
  doi = {10.1109/access.2026.3708784}
}
Kostenlos starten →