EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Compact Propagation and Morphology-Based EEG Features for Real-Time Seizure Detection Using Machine Learning

Dhanushka Wijesinghe, Ivan T. Lima

Journal of Interdisciplinary Research Applied to Medicine · 12.05.2026 · 6 (2) · 8

DOI: 10.3390/jdream6020008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Interdisciplinary Research Applied to Medicine, online erschienen am 12.05.2026. Verfasst von Dhanushka Wijesinghe und 1 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NDSU Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and efficient seizure detection remains a major challenge for portable EEG-based monitoring systems, where computational and power limitations restrict the use of deep learning approaches. We introduce a compact set of fourteen propagation-based EEG features that quantify spike directionality, propagation velocity, and spatial coherence across channels. These physiologically interpretable features were evaluated using a gradient-boosted XGBoost classifier on the TUH Seizure Corpus under a leave-one-subject-out cross-validation framework. The proposed model achieved 97.8% accuracy, 98.7% specificity, 93.6% sensitivity, and a weighted F1 score of 97.8% using 2 s epochs and eight electrodes. The framework remained robust across generalized, focal, and complex partial seizure types and maintained consistent short-window performance. The compact 14-feature representation enables efficient, accurate, and interpretable seizure detection with strong potential for real-time wearable EEG-based applications. The proposed gradient-boosting approach demonstrates that shallow, interpretable architectures can achieve performance comparable to deep learning methods while offering improved computational efficiency, making them promising for low-power embedded implementations.

Förderung

  • NDSU Foundation

Zitieren

APA

Wijesinghe, D., & Lima, I. T. (2026). Compact Propagation and Morphology-Based EEG Features for Real-Time Seizure Detection Using Machine Learning. Journal of Interdisciplinary Research Applied to Medicine, 6(2), 8. https://doi.org/10.3390/jdream6020008

Vancouver

Wijesinghe D, Lima IT. Compact Propagation and Morphology-Based EEG Features for Real-Time Seizure Detection Using Machine Learning. Journal of Interdisciplinary Research Applied to Medicine. 2026;6(2):8. doi:10.3390/jdream6020008

BibTeX
@article{Wijesinghe2026,
  author = {Wijesinghe, Dhanushka and Lima, Ivan T.},
  title = {Compact Propagation and Morphology-Based EEG Features for Real-Time Seizure Detection Using Machine Learning},
  journal = {Journal of Interdisciplinary Research Applied to Medicine},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {8},
  doi = {10.3390/jdream6020008}
}
Kostenlos starten →