EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive GCN and Bi-GRU-Based Dual Branch for Motor Imagery EEG Decoding

Yelan Wu iD, Pugang Cao iD, Meng Xu, Yue Zhang, Xiaoqin Lian, Chongchong Yu iD

Sensors · 13.02.2025 · 25 (4) · 1147

DOI: 10.3390/s25041147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.02.2025. Verfasst von Yelan Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China. Hauptthemen laut MEDLINE: Electroencephalography. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Industrial Internet identification analysis System.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decoding motor imagery electroencephalography (MI-EEG) signals presents significant challenges due to the difficulty in capturing the complex functional connectivity between channels and the temporal dependencies of EEG signals across different periods. These challenges are exacerbated by the low spatial resolution and high signal redundancy inherent in EEG signals, which traditional linear models struggle to address. To overcome these issues, we propose a novel dual-branch framework that integrates an adaptive graph convolutional network (Adaptive GCN) and bidirectional gated recurrent units (Bi-GRUs) to enhance the decoding performance of MI-EEG signals by effectively modeling both channel correlations and temporal dependencies. The Chebyshev Type II filter decomposes the signal into multiple sub-bands giving the model frequency domain insights. The Adaptive GCN, specifically designed for the MI-EEG context, captures functional connectivity between channels more effectively than conventional GCN models, enabling accurate spatial–spectral feature extraction. Furthermore, combining Bi-GRU and Multi-Head Attention (MHA) captures the temporal dependencies across different time segments to extract deep time–spectral features. Finally, feature fusion is performed to generate the final prediction results. Experimental results demonstrate that our method achieves an average classification accuracy of 80.38% on the BCI-IV Dataset 2a and 87.49% on the BCI-I Dataset 3a, outperforming other state-of-the-art decoding approaches. This approach lays the foundation for future exploration of personalized and adaptive brain–computer interface (BCI) systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyHumansBrain-Computer InterfacesSignal Processing, Computer-AssistedAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

adaptive graph convolutional network (Adaptive GCN)attention modulebrain–computer interface (BCI)channel correlationelectroencephalography (EEG)motor imagery (MI)temporal dependence

Autor:innen und Institutionen

  • School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China.

ORCID-Profile: Yelan Wu, Pugang Cao, Chongchong Yu

Förderung

  • Industrial Internet identification analysis System

Zitieren

APA

Wu, Y., Cao, P., Xu, M., Zhang, Y., Lian, X., & Yu, C. (2025). Adaptive GCN and Bi-GRU-Based Dual Branch for Motor Imagery EEG Decoding. Sensors, 25(4), 1147. https://doi.org/10.3390/s25041147

Vancouver

Wu Y, Cao P, Xu M, Zhang Y, Lian X, Yu C. Adaptive GCN and Bi-GRU-Based Dual Branch for Motor Imagery EEG Decoding. Sensors. 2025;25(4):1147. doi:10.3390/s25041147

BibTeX
@article{Wu2025,
  author = {Wu, Yelan and Cao, Pugang and Xu, Meng and Zhang, Yue and Lian, Xiaoqin and Yu, Chongchong},
  title = {Adaptive GCN and Bi-GRU-Based Dual Branch for Motor Imagery EEG Decoding},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {4},
  pages = {1147},
  doi = {10.3390/s25041147}
}
Kostenlos starten →