EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Epilepsy detection based on multi-head self-attention mechanism

Yandong Ru, Gaoyang An iD, Zheng Wei, Hongming Chen

PLOS ONE · 11.06.2024 · 19 (6) · e0305166

DOI: 10.1371/journal.pone.0305166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 11.06.2024. Verfasst von Yandong Ru und 3 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province, Zhoushan, China. Hauptthemen laut MEDLINE: Epilepsy, Neural Networks, Computer, Electroencephalography. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Ocean University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CNN has demonstrated remarkable performance in EEG signal detection, yet it still faces limitations in terms of global perception. Additionally, due to individual differences in EEG signals, the generalization ability of epilepsy detection models is week. To address this issue, this paper presents a cross-patient epilepsy detection method utilizing a multi-head self-attention mechanism. This method first utilizes Short-Time Fourier Transform (STFT) to transform the original EEG signals into time-frequency features, then models local information using Convolutional Neural Network (CNN), subsequently captures global dependency relationships between features using the multi-head self-attention mechanism of Transformer, and finally performs epilepsy detection using these features. Meanwhile, this model employs a light multi-head attention mechanism module with an alternating structure, which can comprehensively extract multi-scale features while significantly reducing computational costs. Experimental results on the CHB-MIT dataset show that the proposed model achieves accuracy, sensitivity, specificity, F1 score, and AUC of 92.89%, 96.17%, 92.99%, 94.41%, and 96.77%, respectively. Compared to the existing methods, the method proposed in this paper obtains better performance along with better generalization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EpilepsyNeural Networks, ComputerElectroencephalographyHumansFourier AnalysisSignal Processing, Computer-AssistedAlgorithms

Autor:innen und Institutionen

  • Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province, Zhoushan, China.
  • School of Information Engineering, Zhejiang Ocean University, Zhoushan, China.
  • Heilongjiang University of Science and Technology, Harbin, China.

ORCID-Profile: Gaoyang An

Förderung

  • Zhejiang Ocean University

Zitieren

APA

Ru, Y., An, G., Wei, Z., & Chen, H. (2024). Epilepsy detection based on multi-head self-attention mechanism. PLOS ONE, 19(6), e0305166. https://doi.org/10.1371/journal.pone.0305166

Vancouver

Ru Y, An G, Wei Z, Chen H. Epilepsy detection based on multi-head self-attention mechanism. PLOS ONE. 2024;19(6):e0305166. doi:10.1371/journal.pone.0305166

BibTeX
@article{Ru2024,
  author = {Ru, Yandong and An, Gaoyang and Wei, Zheng and Chen, Hongming},
  title = {Epilepsy detection based on multi-head self-attention mechanism},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {6},
  pages = {e0305166},
  doi = {10.1371/journal.pone.0305166}
}
Kostenlos starten →