EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Frequency Coupling-Enhanced Graph-Transformer Network for Epileptic EEG Classification

Guanghui Yan, Jincheng Guo, Wenwen Chang, Yajun Wang, Yu Ma

Electronics · 02.11.2026 · 15 (21) · 5070

DOI: 10.3390/electronics15215070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 02.11.2026. Verfasst von Guanghui Yan und 4 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Gansu Province, Major science and technology projects of Gansu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a cross-frequency coupling (CFC)-enhanced Graph-Transformer Network for multichannel EEG seizure/non-seizure classification. The architecture combines PAC/PPC descriptors, a residual convolutional encoder, learnable graph attention over post-CNN temporal nodes, and a lightweight Transformer encoder. Evaluation on the CHB-MIT scalp EEG database comprises a random window split and case-wise five-fold cross-validation. The case-wise protocol yielded 67.16 ± 5.58% accuracy, 0.617 ± 0.214 recall, 0.630 ± 0.132 F1-score, and 0.748 ± 0.067 AUROC. Its mean AUROC was numerically higher than those of protocol-matched CNN-BiLSTM and EEGNet-like baselines (0.731 and 0.693, respectively). The random 70%/15%/15% split yielded 99.38% accuracy and 99.93% AUROC; an overlap diagnostic found shared raw samples in 91.0% of test windows, defining these scores as within-protocol reference results. Random-window ablation rankings are supplementary observations; the held-out-case comparisons provide the principal comparative results. CFC sensitivity analysis found an EMG-proxy-adjusted theta-to-low-gamma PAC association with class labels, while the circular-shift surrogate-corrected contrast was not significant. Continuous-event evaluation yielded 1.000 sensitivity and 22.39 false alarms per hour, and zero-shot Siena evaluation yielded 47.73% balanced accuracy and 0.427 AUROC. The study provides an integrated EEG representation framework and a protocol-specific performance profile. The five-fold results concern held-out case identifiers, with chb01 and chb21 retained in separate folds; they are distinguished from subject-grouped evaluation.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Gansu Province
  • Major science and technology projects of Gansu Province
  • Gansu Province young doctor support project

Zitieren

APA

Yan, G., Guo, J., Chang, W., Wang, Y., & Ma, Y. (2026). Cross-Frequency Coupling-Enhanced Graph-Transformer Network for Epileptic EEG Classification. Electronics, 15(21), 5070. https://doi.org/10.3390/electronics15215070

Vancouver

Yan G, Guo J, Chang W, Wang Y, Ma Y. Cross-Frequency Coupling-Enhanced Graph-Transformer Network for Epileptic EEG Classification. Electronics. 2026;15(21):5070. doi:10.3390/electronics15215070

BibTeX
@article{Yan2026,
  author = {Yan, Guanghui and Guo, Jincheng and Chang, Wenwen and Wang, Yajun and Ma, Yu},
  title = {Cross-Frequency Coupling-Enhanced Graph-Transformer Network for Epileptic EEG Classification},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5070},
  doi = {10.3390/electronics15215070}
}
Kostenlos starten →