基于频谱注意力的运动想象解码

doi:10.3969/j.issn.0258-8021.2026.02.007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (5153 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming to solve the problem of insufficient ability of feature extraction by the traditional motor imagery decoding algorithm for long time series and low recognition rate of EEG signals, a novel CNN wavelet decomposition spectral encoder EEG decoding algorithm was proposed in this work, based on the fusion idea of convolutional neural network and transformer encoder and combining wavelet decomposition and spectral attention. First, the convolution module was constructed for local feature extraction, and the multi-level sub-features were obtained by one-level wavelet decomposition. Based on the transformer encoder, spectral attention was introduced to replace the traditional multi-head attention, and a new FFT-Former encoder was constructed followed by the input of multi-level sub-features into the spectrum attention for frequency domain modeling. Next, the time-domain features obtained by wavelet reconstruction technology were input into the feedforward network to enable the model to learn more complex feature dependencies. Finally, the feature information of convolution module and FFT-Former was fused to design a classifier to achieve low computational complexity and high accuracy EEG signal recognition. Verified by public datasets, the average accuracy of motor imagery decoding of CWFT network model on BCI Competition IV-2a and BCI Competition IV-2b reached 85.65% and 89.54% respectively, and the Kappa coefficient reached 80.86% and 79.07% respectively. By comparing with other comparison algorithms, we demonstrated that the proposed algorithm had excellent classification performance and provided a new idea for the construction of motor imagery brain-computer interface.

Key words： motor imagery brain-computer interface spectral attention wavelet decomposition

Received: 20 July 2025

PACS:

R318

Corresponding Authors: ^*E-mail: cxjnet@126.com

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chen Xuejun
	Chen Hongda
	Zhang Chenhua
	Chen Weijie

Cite this article:

Chen Xuejun,Chen Hongda,Zhang Chenhua, et al. Motor Imagery Decoding Based on Spectral Attention[J]. Chinese Journal of Biomedical Engineering, 2026, 45(2): 199-210.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2026.02.007 OR http://cjbme.csbme.org/EN/Y2026/V45/I2/199

[1] 何群, 邵丹丹, 王煜文, 等. 基于多特征卷积神经网路的运动想象脑电信号分析及意图识别[J]. 仪器仪表学报, 2020, 41(1): 138-146.
[2] Samejima S, Khorasani A, Ranganathan V, et al. brain-computer-spinal interface restores upper limb function after spinal cord injury[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 1233-1242.
[3] Ghosh A, Ghosh L, Saha S. Hybrid brain-computer interfacing paradigm for assistive robotics[J]. Robotics and Autonomous Systems, 2025, 185: 104893.
[4] Wen Dong, Liang Bingbing, Zhou Yanhong, et al. The current research of combining multi-modal brain-computer interfaces with virtual reality[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 25(9): 3278-3287.
[5] Lan Z, Zhao J, Liu P, et al. Driving fatigue detection based on fusion of EEG and vehicle motion information[J]. Biomedical Signal Processing and Control, 2024, 92: 106031.
[6] Mladenović J, Frey J, Pramij S, et al. Towards identifying optimal biased feedback for various user states and traits in motor imagery BCI[J]. IEEE Transactions on Biomedical Engineering, 2021, 69(3): 1101-1110.
[7] 柳长源, 李文强, 毕晓君. 基于脑电信号的情绪特征提取与分类[J]. 传感技术学报, 2019, 32(1): 82-88.
[8] 赵利民, 朱晓军, 高旭瑞. 基于改进的LMD运动想象信号识别[J]. 电子技术应用, 2016, 42(3): 116-119.
[9] Yang Jun, Ma Zhengmin, Shen Tao. Multi-time and multi-band CSP motor imagery EEG feature classification algorithm[J]. Applied Sciences, 2021, 11(21): 10294.
[10] Wang Han, Cao Lei, Huang Chenxi, et al. A novel algorithmic structure of EEG channel attention combined with swin transformer for motor patterns classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 3132-3141.
[11] 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.
[12] Saideepth P, Chowdhury A, Gaur P, et al. Sliding wINDOW aLONG with EEGNet-Based prediction of EEG motor imagery[J]. IEEE Sensors Journal, 2023, 23(15): 17703-17713.
[13] Zhang Chaozhu, Chu Hongxing, Ma Mingyuan. Decoding algorithm of motor imagery electroencephalogram signal based on CLRNet network model[J]. Sensors, 2023, 23(18): 7694.
[14] Wu Runze, Jin Jing, Daly L, et al. Classification of motor imagery based on multi-scale feature extraction and the channel-temporal attention module[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 3075-3085.
[15] Hou Pengfei, Li Xiaowei, Zhu Jing, et al. A lightweight convolutional transformer neural network for EEG-based depression recognition[J]. Biomedical Signal Processing and Control, 2025, 100: 107112.
[16] Li Chang, Huang Xiaoyang, Song Rencheng, et al. EEG-based seizure prediction via Transformer guided CNN[J]. Measurement, 2022, 203(15): 111948.
[17] Zhao Wei, Jiang Xiaolu, Zhang Baocan, et al. CTNet: a convolutional transformer network for EEG-based motor imagery classification[J]. Scientific Reports, 2025, 14(1): 20237.
[18] 俞小彤, 赵若辰, 宁晓琳. 多通道权重融合和小波分解的癫痫棘波检测方法[J]. 电子测量与仪器学报, 2024, 38(10): 24-34.
[19] Kaleem M, Guergachi A, Krishnan S. Patient-specific seizure detection in long-term EEG using wavelet decomposition[J]. Biomedical Signal Processing and Control, 2018, 46: 157-165.
[20] Xu Hongxiang, Pei Ziyi, Han Qi, et al. MASTF-net: An EEG emotion recognition network based on multi-source domain adaptive method based on spatio-temporal image and frequency domain information[J]. IEEE Access, 2024, 12: 8485-8501.
[21] Lv Ziyi, Zhang Jing, Epota Oma E. A novel method of emotion recognition from multi-band EEG topology maps based on erenet[J]. Applied Sciences, 2022, 12(20): 10273.
[22] Tangermann M, Müller KR, Aertsen A, et al. Review of the BCI competition IV[J]. Frontiers in neuroscience, 2012, 6: 55.
[23] Lotte F. Signal processing approaches to minimize or suppress calibration time in oscillatory activity-based brain-computer interfaces[J]. Proceedings of the IEEE, 2015, 103(6): 871-890.
[24] Fein-Ashley J. SPECTRE: an FFT-based efficient drop-in replacement to self-attention for long contexts[J/OL]. https://arxiv.org/abs/2502.18394,2025-05-18/2025-07-20.
[25] Schirrmeister RT, Springenberg JT, Fiederer LD J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization[J]. Human Brain Mapping, 2017, 38(11): 5391-5420.
[26] 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.