Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion
International Journal of Neural Systems · 2025
DOI: 10.1142/s0129065724500692 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, 2025. Verfasst von Fangzhou Xu und 8 weiteren Autor:innen. Beteiligte Einrichtung: International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, P. R. China. Hauptthemen laut MEDLINE: Electroencephalography, Imagination, Brain-Computer Interfaces, Neural Networks, Computer. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
Stroke, an abrupt cerebrovascular ailment resulting in brain tissue damage, has prompted the adoption of motor imagery (MI)-based brain–computer interface (BCI) systems in stroke rehabilitation. However, analyzing electroencephalogram (EEG) signals from stroke patients poses challenges. To address the issues of low accuracy and efficiency in EEG classification, particularly involving MI, the study proposes a residual graph convolutional network (M-ResGCN) framework based on the modified S-transform (MST), and introduces the self-attention mechanism into residual graph convolutional network (ResGCN). This study uses MST to extract EEG time-frequency domain features, derives spatial EEG features by calculating the absolute Pearson correlation coefficient (aPcc) between channels, and devises a method to construct the adjacency matrix of the brain network using aPcc to measure the strength of the connection between channels. Experimental results involving 16 stroke patients and 16 healthy subjects demonstrate significant improvements in classification quality and robustness across tests and subjects. The highest classification accuracy reached 94.91% and a Kappa coefficient of 0.8918. The average accuracy and F1 scores from 10 times 10-fold cross-validation are 94.38% and 94.36%, respectively. By validating the feasibility and applicability of brain networks constructed using the aPcc in EEG signal analysis and feature encoding, it was established that the aPcc effectively reflects overall brain activity. The proposed method presents a novel approach to exploring channel relationships in MI-EEG and improving classification performance. It holds promise for real-time applications in MI-based BCI systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, P. R. China.
- Rehabilitation Center, Qilu Hospital of Shandong University, Jinan 250012, P. R. China.
- Rehabilitation and Physical Therapy Department, Shandong University of Traditional Chinese Medicine Affiliated Hospital, Jinan 250011, P. R. China.
- Swartz Center for Computational Neuroscience, Institute of Neural Computation, University of California, San Diego, La Jolla, CA, USA.
ORCID-Profile: Fangzhou Xu, Weiyou Shi, Chengyan Lv, Yuan Sun, Shuai Guo, Chao Feng, Yang Zhang, Tzyy-Ping Jung, Jiancai Leng
Zitieren
APA
Xu, F., Shi, W., Lv, C., Sun, Y., Guo, S., Feng, C., Zhang, Y., Jung, T. P., & Leng, J. (2025). Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion. International Journal of Neural Systems. https://doi.org/10.1142/s0129065724500692
Vancouver
Xu F, Shi W, Lv C, Sun Y, Guo S, Feng C, et al. Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion. International Journal of Neural Systems. 2025. doi:10.1142/s0129065724500692
BibTeX
@article{Xu2025,
author = {Xu, Fangzhou and Shi, Weiyou and Lv, Chengyan and Sun, Yuan and Guo, Shuai and Feng, Chao and Zhang, Yang and Jung, Tzyy-Ping and Leng, Jiancai},
title = {Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion},
journal = {International Journal of Neural Systems},
year = {2025},
doi = {10.1142/s0129065724500692}
}
EUVIMED