EUVIMEDEUVIMED entdecken
Crossref

A transformer-based network with second-order pooling for motor imagery EEG classification

Jing Jin iD, Wei Liang iD, Ren Xu, Weijie Chen iD, Ruitian Xu, Xingyu Wang, Andrzej Cichocki iD

Journal of Neural Engineering · 01.08.2025 · 22 (4) · 046011

DOI: 10.1088/1741-2552/adeae8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 10.07.2025. Verfasst von Jing Jin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 20…. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Imagination, Neural Networks, Computer. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Project of Jiangsu Province Science and Technology Plan Special Fund in 2022, STI 2030-major projects, Shanghai Municipal Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . Electroencephalography (EEG) signals can reflect motor intention signals in the brain. In recent years, motor imagery (MI) based brain–computer interfaces (BCIs) have attracted the attention of neuroinformatics researchers. Numerous deep learning models have been developed to decode EEG signals. Although deep learning models, particularly those based on convolutional neural networks, have shown promise in decoding EEG signals, most existing methods focus on attention mechanisms while neglecting high-order statistical dependencies that are critical for accurately capturing the complex structure of EEG data. Approach . To address this limitation, we propose a neural network integrating a transpose-attention mechanism and second-order pooling (SecTNet). The proposed model tackles two fundamental challenges in EEG decoding. It metrics the covariance structure of EEG signals using Riemannian geometry on symmetric positive definite (SPD) matrices, and it enhances the discriminability of these SPD features by introducing attention mechanisms that adaptively model inter-channel dependencies. Specifically, SecTNet is composed of three key components. First, a multi-scale spatial-temporal convolution module extracts detailed local features. Second, a transpose-attention mechanism captures dependency information from the internal interactions between channels. Lastly, a second-order pooling layer captures high-order statistical correlations in the EEG feature space. Main results . SecTNet is evaluated on two publicly available EEG datasets, namely BCI competition IV 2a dataset and OpenBMI dataset. It achieves an average accuracy of 86.88% on the BCI competition IV dataset 2a and 74.99% on the OpenBMI dataset. Moreover, results show that SecTNet maintains competitive performance even when trained on only 50% of the data, demonstrating strong generalization under limited data conditions. Significance . These results demonstrate the broad applicability and effectiveness of SecTNet in enhancing MI-BCI performance. SecTNet provides a robust and generalizable framework for EEG decoding, supporting the development of BCI applications across diverse real-world scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesImaginationNeural Networks, ComputerHumansDeep LearningBrain

Stichwörter der Autor:innen

attention mechanismbrain–computer interfaceelectroencephalographymotor imagerysecond-order pooling

Autor:innen und Institutionen

  • Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, People's Republic of China.
  • School of Mathematics, East China University of Science and Technology, Shanghai 200237, People's Republic of China.
  • g.tec medical engineering GmbH, 4521 Schiedlberg, Austria.
  • Systems Research Institute, Polish Academy of Science, 01-447 Warsaw, Poland.
  • RIKEN Advanced Intelligence Project, Tokyo 103-0027, Japan.
  • Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan.

ORCID-Profile: Jing Jin, Wei Liang, Weijie Chen, Andrzej Cichocki

Förderung

  • Project of Jiangsu Province Science and Technology Plan Special Fund in 2022
  • STI 2030-major projects
  • Shanghai Municipal Science and Technology Major Project
  • Grant National Natural Science Foundation of China

Zitieren

APA

Jin, J., Liang, W., Xu, R., Chen, W., Xu, R., Wang, X., & Cichocki, A. (2025). A transformer-based network with second-order pooling for motor imagery EEG classification. Journal of Neural Engineering, 22(4), 046011. https://doi.org/10.1088/1741-2552/adeae8

Vancouver

Jin J, Liang W, Xu R, Chen W, Xu R, Wang X, et al. A transformer-based network with second-order pooling for motor imagery EEG classification. Journal of Neural Engineering. 2025;22(4):046011. doi:10.1088/1741-2552/adeae8

BibTeX
@article{Jin2025,
  author = {Jin, Jing and Liang, Wei and Xu, Ren and Chen, Weijie and Xu, Ruitian and Wang, Xingyu and Cichocki, Andrzej},
  title = {A transformer-based network with second-order pooling for motor imagery EEG classification},
  journal = {Journal of Neural Engineering},
  year = {2025},
  volume = {22},
  number = {4},
  pages = {046011},
  doi = {10.1088/1741-2552/adeae8}
}
Kostenlos starten →