Dual-Stage Improvement with Domain Adaptation for Cross-Subject Epileptic Seizure Prediction
International Journal of Neural Systems · 2026-10 · 36 (10)
DOI: 10.1142/s0129065726500322 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 23.05.2026. Verfasst von Chenchen Cheng und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Harbin University of Science and Technology, Harbin 150080, P. R. China. Hauptthemen laut MEDLINE: Electroencephalography, Seizures, Epilepsy, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, Heilongjiang Provincial Outstanding Young Teachers Basic Research Support Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Electroencephalogram (EEG)-based epileptic seizure prediction is a critical adjunctive treatment strategy for drug-resistant epilepsy. To mitigate cross-subject EEG variability and improve generalization performance, existing methods use domain adaptation (DA) to minimize distribution discrepancy between source and target domains. However, these methods overlook the joint impact of data imbalance and noisy pseudo-labels. This results in biased attention toward imbalanced source samples and degraded understanding of the true target distribution, thereby impairing the model’s generalization performance. To address these issues, a cross-subject seizure prediction method based on DA with dual-stage improvement is proposed to integrate data balancing and pseudo-label optimization. Specifically, a global context-aware generative network is introduced to generate preictal samples with global contextual consistency to rectify class imbalance between preictal and interictal samples in the source domain. A common spatial pattern clustering filter is then introduced, which uses a confidence-guided covariance weighting strategy to integrate classification confidence from source-domain labels and target-domain pseudo-labels, optimizing spatial filters to maximize inter-class discrimination. To mitigate the accumulation and propagation of noisy pseudo-labels during training, a dual-filtering mechanism iteratively eliminates them. Experimental evaluation on the CHB-MIT dataset demonstrates the effectiveness of the proposed method in mitigating interpatient domain discrepancies and achieving superior performance over recent leading approaches.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, Harbin University of Science and Technology, Harbin 150080, P. R. China.
- Post-doctoral Mobile Station for Instrumental Science and Technology, the School of Measurement-Control Technology and Communications Engineering, Harbin University of Science and Technology, Harbin 150080, P. R. China.
- Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration, Harbin University of Science and Technology, Harbin 150080, P. R. China.
- College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, P. R. China.
ORCID-Profile: Chenchen Cheng, Wanjin Song, Bo You, Haichao Wu, Yan Liu
Förderung
- China Postdoctoral Science Foundation
- Heilongjiang Provincial Outstanding Young Teachers Basic Research Support Program
- National Natural Science Foundation of China
Zitieren
APA
Cheng, C., Song, W., You, B., Wu, H., & Liu, Y. (2026). Dual-Stage Improvement with Domain Adaptation for Cross-Subject Epileptic Seizure Prediction. International Journal of Neural Systems, 36(10). https://doi.org/10.1142/s0129065726500322
Vancouver
Cheng C, Song W, You B, Wu H, Liu Y. Dual-Stage Improvement with Domain Adaptation for Cross-Subject Epileptic Seizure Prediction. International Journal of Neural Systems. 2026;36(10). doi:10.1142/s0129065726500322
BibTeX
@article{Cheng2026,
author = {Cheng, Chenchen and Song, Wanjin and You, Bo and Wu, Haichao and Liu, Yan},
title = {Dual-Stage Improvement with Domain Adaptation for Cross-Subject Epileptic Seizure Prediction},
journal = {International Journal of Neural Systems},
year = {2026},
volume = {36},
number = {10},
doi = {10.1142/s0129065726500322}
}
EUVIMED