RMETNet: A cross-subject motor imagery EEG signal classification model based on TSLANet and riemannian geometry features
PLOS One · 2026
DOI: 10.1371/journal.pone.0347671 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Yun Zhao und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Smart Health, Chongqing Polytechnic University of Electronic Technology, Chongqing, China. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Signal Processing, Computer-Assisted, Imagination. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Research Program of the Chongqing Education Commission, Natural Science Foundation of Chongqing.
Abstract (Originalsprache)
Motor imagery electroencephalogram (MI-EEG) analysis is essential for natural interaction and autonomous control in brain-computer interfaces (BCIs). However, deep learning models often struggle with inter-subject variability, which limits their ability to generalize across subjects. This study proposes RMETNet, a novel framework that integrates TSLANet, a spatio-temporal convolution module, and a multi-scale Riemannian geometry feature module. TSLANet suppresses noise and captures complex temporal patterns for preliminary signal decoding, while the spatio-temporal convolution module extracts higher-order representations. The Riemannian branch learns geometry-based distribution features across subjects, and the fused features are used for classification. To address inter-subject distribution shifts, RMETNet incorporates Maximum Mean Discrepancy (MMD) loss for domain adaptation, aligning feature distributions between source and target domains. Experiments show that on the four-class BCI Competition IV 2a (BCICIV2a) dataset, RMETNet achieved accuracies of 71.39% in the cross-subject setting and 80.71% in the subject-dependent setting; on the two-class BCI Competition IV 2b (BCICIV2b) dataset, it achieved 80.93% and 86.76%, respectively. The model consistently outperformed baseline algorithms. Ablation and visualization analyses further validated its effectiveness in reducing inter-subject feature distribution disparities and enhancing MI-EEG decoding. The code is available at: https://github.com/rokanfeermecer486/RMETNet .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Smart Health, Chongqing Polytechnic University of Electronic Technology, Chongqing, China.
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China.
- College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China.
ORCID-Profile: Bin Jiang
Förderung
- Scientific and Technological Research Program of the Chongqing Education Commission
- Natural Science Foundation of Chongqing
Zitieren
APA
Zhao, Y., He, D., Ren, F., Xia, Q., Xu, L., Xie, G., Zhang, X., Yang, R., Zou, S., & Jiang, B. (2026). RMETNet: A cross-subject motor imagery EEG signal classification model based on TSLANet and riemannian geometry features. PLOS One. https://doi.org/10.1371/journal.pone.0347671
Vancouver
Zhao Y, He D, Ren F, Xia Q, Xu L, Xie G, et al. RMETNet: A cross-subject motor imagery EEG signal classification model based on TSLANet and riemannian geometry features. PLOS One. 2026. doi:10.1371/journal.pone.0347671
BibTeX
@article{Zhao2026,
author = {Zhao, Yun and He, Dongyi and Ren, Fudai and Xia, Qingling and Xu, Linhao and Xie, Guanghui and Zhang, Xiaoling and Yang, Renqiang and Zou, Shuaidong and Jiang, Bin},
title = {RMETNet: A cross-subject motor imagery EEG signal classification model based on TSLANet and riemannian geometry features},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0347671}
}
EUVIMED