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

• Published in: Journal of neuroscience methods Vol. 420; p. 110483
• Main Authors: Xie, Chengqiang, Wang, Li, Yang, Jiafeng, Guo, Jiaying
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.08.2025
• Subjects: Brain - physiology; Brain-computer interface (BCI); Brain-Computer Interfaces; Deep Learning; Deep Learning (DL); Electroencephalogram (EEG); Electroencephalography - methods; Humans; Imagination - physiology; Motor Activity - physiology; Motor imagery (MI); Neural Networks, Computer; Signal Processing, Computer-Assisted; Transfer learning (TL); Motor imagery (MI); Brain-computer interface (BCI); Transfer learning (TL); Electroencephalogram (EEG); Deep Learning (DL)
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2025.110483

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. 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 Convolution-attention-temporal (CAT) classifier to classify the transferred features. 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. 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. 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. •a subject transfer neural network that combines the Generator with the EA (ST-GENN) is proposed.•The combination of the EA and Generator is utilized to minimize the disparity between the source and target domains.•A golden subject is selected as the source domain, while concurrently utilizing data from target users to train the Generator.•The practical application of BCIs can be enhanced by our proposed model.