A subject transfer neural network fuses Generator and Euclidean alignment for EEG-based motor imagery classification

被引:0
作者
Xie, Chengqiang [1 ]
Wang, Li [1 ]
Yang, Jiafeng [1 ]
Guo, Jiaying [1 ]
机构
[1] Guangzhou Univ, Sch Elect & Commun Engn, Guangzhou 510006, Peoples R China
关键词
Brain-computer interface (BCI); Transfer learning (TL); Motor imagery (MI); Electroencephalogram (EEG); Deep Learning (DL); BRAIN-COMPUTER INTERFACES; COMMON SPATIAL-PATTERN; NEUROPLASTICITY; COMMUNICATION; TRIAL; BCI;
D O I
10.1016/j.jneumeth.2025.110483
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Background: Brain-computer interface (BCI) facilitates the connection between human brain and computer, enabling individuals to control external devices indirectly through cognitive processes. Although it has great development prospects, the significant difference in EEG signals among individuals hinders users from further utilizing the BCI system. New method: Addressing this difference and improving BCI classification accuracy remain key challenges. In this paper, we propose a transfer learning model based on deep learning to transfer the data distribution from the source domain to the target domain, named a subject transfer neural network combining the Generator with Euclidean alignment (ST-GENN). It consists of three parts: 1) Align the original EEG signals in the Euclidean space; 2) Send the aligned data to the Generator to obtain the transferred features; 3) Utilize the Convolutionattention-temporal (CAT) classifier to classify the transferred features. Results: The model is validated on BCI competition IV 2a, BCI competition IV 2b and SHU datasets to evaluate its classification performance, and the results are 82.85 %, 86.28 % and 67.2 % for the three datasets, respectively. Comparison with existing methods: The results have been shown to be robust to subject variability, with the average accuracy of the proposed method outperforming baseline algorithms by ranging from 2.03 % to 15.43 % on the 2a dataset, from 0.86 % to 10.16 % on the 2b dataset and from 3.3 % to 17.9 % on the SHU dataset. Conclusions for research articles: The advantage of our model lies in its ability to effectively transfer the experience and knowledge of the source domain data to the target domain, thus bridging the gap between them. Our method can improve the practicability of MI-BCI systems.
引用
收藏
页数:18
相关论文
共 68 条
[11]   Inter-Subject Transfer Learning Using Euclidean Alignment and Transfer Component Analysis for Motor Imagery-Based BCI [J].
Demsy, Orvin ;
Achanccaray, David ;
Hayashibe, Mitsuhiro .
2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2021, :3176-3181
[12]   Neuroplasticity in the context of motor rehabilitation after stroke [J].
Dimyan, Michael A. ;
Cohen, Leonardo G. .
NATURE REVIEWS NEUROLOGY, 2011, 7 (02) :76-85
[13]  
Djamal E.C, 2017, Journal of Telecommunication. Electron. Comput. Eng. (JTEC), V9, P71
[14]   A novel end-to-end deep learning scheme for classifying multi-class motor imagery electroencephalography signals [J].
Hassanpour, Ahmad ;
Moradikia, Majid ;
Adeli, Hojjat ;
Khayami, Seyed Raouf ;
Shamsinejadbabaki, Pirooz .
EXPERT SYSTEMS, 2019, 36 (06)
[15]   Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach [J].
He, He ;
Wu, Dongrui .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2020, 67 (02) :399-410
[16]   MSATNet: multi-scale adaptive transformer network for motor imagery classification [J].
Hu, Lingyan ;
Hong, Weijie ;
Liu, Lingyu .
FRONTIERS IN NEUROSCIENCE, 2023, 17
[17]   Mental practice with motor imagery in stroke recovery: randomized controlled trial of efficacy [J].
Ietswaart, Magdalena ;
Johnston, Marie ;
Dijkerman, H. Chris ;
Joice, Sara ;
Scott, Clare L. ;
MacWalter, Ronald S. ;
Hamilton, Steven J. C. .
BRAIN, 2011, 134 :1373-1386
[18]  
Ingolfsson TM, 2020, IEEE SYS MAN CYBERN, P2958
[19]  
Ioffe Sergey, 2015, Proceedings of Machine Learning Research, V37, P448, DOI DOI 10.48550/ARXIV.1502.03167
[20]   Multiscale Spatial-Temporal Feature Fusion Neural Network for Motor Imagery Brain-Computer Interfaces [J].
Jin, Jing ;
Chen, Weijie ;
Xu, Ren ;
Liang, Wei ;
Wu, Xiao ;
He, Xinjie ;
Wang, Xingyu ;
Cichocki, Andrzej .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2025, 29 (01) :198-209