基于MC-TANet的运动想象脑电信号分类研究

doi:10.3969/j.issn.0258-8021.2026.03.005

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (14569 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To address challenges in motor imagery EEG (MI-EEG) classification caused by low signal-to-noise ratio, non-stationarity, and significant individual differences, a classification model based on a multi-branch convolution and temporal attention network (MC-TANet) was proposed in this work. The model employed a multi-branch convolution module to extract temporal features in parallel using convolutional kernels of different scales. After that, the model integrated spatial and temporal information through depthwise spatial convolution and spatio-temporal convolution. After sliding window processing, a multi-head self-attention layer focuses on key features, and a temporal convolutional network mines deep spatio-temporal dependencies. These features were then fused via average fusion and fed into the classifier, where a fully connected layer and SoftMax perform the final probability prediction for the MI classification task. Experimental results on the BCI-2a and BCI-2b datasets showed that in subject-dependent experiments, the model achieved average accuracies of 87.9% and 90.8%, and Kappa coefficients of 0.838 and 0.816, respectively. In cross-subject experiments, accuracies of 69.6% and 80.3% and Kappa coefficients of 0.602 and 0.606 were achieved. It was confirmed that the model effectively captured mu and beta rhythms features, thereby enhancing inter-class separability.

Key words： electroencephalogram motor imagery multi-branch convolution temporal convolutional network feature fusion

Received: 20 December 2025

PACS:

R318

Corresponding Authors: ^*E-mail:xjzhang@njupt.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhang Xuejun
	Song Zhongchen

Cite this article:

Zhang Xuejun,Song Zhongchen. Classification of Motor Imagery EEG Signals Based on MC-TANet[J]. Chinese Journal of Biomedical Engineering, 2026, 45(3): 299-311.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2026.03.005 OR http://cjbme.csbme.org/EN/Y2026/V45/I3/299

[1] 徐慧, 何宏, 张慧敏, 等. 黎曼流形切平面空间中运动想象脑电信号的迁移学习 [J]. 中国生物医学工程学报, 2023, 42(6): 659-667.
[2] 高云园, 薛云峰, 张聪睿, 等. 基于集成式张量域自适应的运动想象脑电分类 [J]. 中国生物医学工程学报, 2024, 43(4): 399-407.
[3] Altaheri H, Muhammad G, Alsulaiman M, et al. Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review [J]. Neural Comput, 2023. 35 (20):14681-14722.
[4] Du Yushan, Sui Jiaxin, Wang Shiwei, et al. Motor intent recognition of multi-feature fusion EEG signals by UMAP algorithm [J]. Medical & Biological Engineering & Computing, 2023, 61(10): 2665-2676.
[5] Jiang Aimin, Shang Jing, Liu Xiaofeng, et al. Efficient CSP algorithm with spatio-temporal filtering for motor imagery classification [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020, 28(4): 1006-1016.
[6] Luo Tianjian. Parallel genetic algorithm based common spatial patterns selection on time-frequency decomposed EEG signals for motor imagery brain-computer interface [J]. Biomedical Signal Processing and Control, 2023, 80: 104397.
[7] Sun Yuchao, Kintak U. CNN-based scheme on EEG hand-motion recognition without signal preprocessing [C]//2022 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR). Toyama: IEEE, 2022: 72-76.
[8] Sun Biao, Zhao Xing, Zhang Han, et al. EEG motor imagery classification with sparse spectrotemporal decomposition and deep learning [J]. IEEE Transactions on Automation Science and Engineering, 2021, 18(2): 541-551.
[9] Cao Ning, Wen Xin, Hao Yanrong, et al. A lightweight end-to-end three-domain feature fusion network for motor imagery decoding [C]//2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Lisbon: IEEE, 2024: 1830-1837.
[10] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas:IEEE,2016: 770-778.
[11] Jia Ziyu, Lin Youfang, Wang Jing, et al. MMCNN: A multi-branch multi-scale convolutional neural network for motor imagery classification [M]//Hutter F, Kersting K, Lijffijt J, et al. Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science. Cham: Springer, 2021, 12459: 1-16.
[12] Singh K, Singha N, Jaswal G, et al. A novel CNN with sliding window technique for enhanced classification of MI-EEG sensor data [J]. IEEE Sensors Journal, 2025, 25(3): 4777-4786.
[13] Zhao Xingqiao, Zhang Hongmiao, Zhu Guilin, et al. A multi-branch 3D convolutional neural network for eeg-based motor imagery classification [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(10): 2164-2177.
[14] Wang Huiyang, Jiang Jiuchuan, Gan JQ, et al. Motor imagery EEG classification based on a weighted multi-branch structure suitable for multisubject data [J]. IEEE Transactions on Biomedical Engineering, 2023, 70(11): 3040-3051.
[15] Miao Yutao, Li Kaijie, Zhao Wenhao, et al. EA-EEG: a novel model for efficient motor imagery EEG classification with whitening and multi-scale feature integration [J]. Cognitive Neurodynamics, 2025, 19: 94.
[16] Liu Ke, Yang Mingzhao, Yu Zhuliang, et al. FBMSNet: A filter-bank multi-scale convolutional neural network for EEG-based motor imagery decoding [J]. IEEE Transactions on Biomedical Engineering, 2023, 70(2): 436-445.
[17] Huang Qianfeng, Yang Yuanpo, Li Jun, et al. AMFTCNet: a multi-level attention-based multi-scale fusion temporal convolutional network for decoding MI-EEG signals [J]. Biomedical Signal Processing and Control, 2025, 108: 107916.
[18] Ma Shuaishuai, Lv Jidong, Li Wenjie, et al. FBATCNet: a temporal convolutional network with frequency band attention for decoding motor imagery EEG [J]. IEEE Access, 2025, 13: 11265-11279.
[19] Altaheri H, Muhammad G, Alsulaiman M. Physics-informed attention temporal convolutional network for EEG-based motor imagery classification [J]. IEEE Transactions on Industrial Informatics, 2023, 19(2): 2249-2258.
[20] Song Yonghao, Zheng Qingqing, Liu Bingchuan, et al. EEG Conformer: convolutional transformer for EEG decoding and visualization [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 710-719.
[21] Luo Jingjing, Cheng Qiying, Wang Hongbo, et al. MI-MBFT: superior motor imagery decoding of raw EEG Data based on a multibranch and fusion transformer framework [J]. IEEE Sensors Journal, 2024, 24(21): 34879-34891.
[22] Liang Guangjin, Cao Dianguo, Wang Jinqiang, et al. EISATC-Fusion: Inception self-attention temporal convolutional network fusion for motor imagery EEG decoding [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32: 1535-1545.
[23] Deng Xin, Huo Huaxiang, Ai Lijiao, et al. A novel 3D approach with a CNN and Swin transformer for decoding EEG-based motor imagery classification [J]. Sensors, 2025, 25(9): 2922.
[24] Altuwaijri G A, Muhammad G, Altaheri H, et al. A multi-branch convolutional neural network with squeeze-and-excitation attention blocks for EEG-based motor imagery signals classification [J]. Diagnostics, 2022, 12(4): 995.
[25] Lawhern VJ, Solon AJ, Waytowich NR, et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces [J]. Journal of Neural Engineering, 2018, 15(5): 056013.
[26] Schirrmeister R, Gemein L, Eggensperger K, et al. Deep learning with convolutional neural networks for EEG decoding and visualization [J]. Human Brain Mapping, 2017, 38(11): 5391-5420.
[27] Miao Tianhua, Sha Liansen, Huang Kun, et al. TFCA-TransNet: convolutional time-frequency-spatial feature fusion with channel attention transformer network for EEG-MI signal [J]. Biomedical Signal Processing and Control, 2026, 112: 108692.
[28] Yu Hongli, Ba Sidi, Guo Yuxue, et al. Effects of motor imagery tasks on brain functional networks based on EEG Mu/Beta rhythm [J]. Brain Sciences, 2022, 12(2): 194.
[29] Jeon Y, Nam CS, Kim YJ, et al. Event-related (De)synchronization (ERD/ERS) during motor imagery tasks: Implications for brain-computer interfaces [J]. International Journal of Industrial Ergonomics, 2011,41(5): 428-436.
[30] Wang Yangchuang, Yu Hongli, Zhao Xiuzhi, et al. A dual-branch neural network and attention mechanism for decoding EEG-based motor imagery[J]. Cogn Neurodyn, 2025,19(1):177.
[31] Chen Junfu, Pi Dechang, Gao Feng, et al. MI-DGHCL: motor imagery EEG domain generalization via hyperbolic contrastive learning [J]. Expert Systems with Applications, 2026, 312: 131477.
[32] Sedi Nzakuna P, D'Auria E, Paciello V, et al. Real-world evaluation of deep learning decoders for motor imagery EEG-based BCIs [J]. Front Syst Neurosci, 2025, 19: 1718390.
[33] Zhang Minghan, Cross-subject generalisation in diverse electroencephalogram classification tasks: a deep learning and large language model perspective [D]. Coventry: University of Warwick, 2024.