A motor imagery decoding study integrating differential attention with a multi-scale adaptive temporal convolutional network_Journal of Biomedical Engineering

Authors：

DONG Zheng ^1,2 ,  BAO Xueliang ^1,2 , YANG Yabing ^1,2 , WU Jiao ³

1. Department of Biomedical Engineering, School of Information Engineering, Ningxia University, Yinchuan 750021, P. R. China;
2. Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West of Ningxia, Yinchuan 750021, P. R. China;
3. People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan 750004, P. R. China;

Corresponding?author：

BAO Xueliang, Email: xlbao@nxu.edu.cn

Keywords：

Motor imagery decoding; Brain-computer interface; Differential attention mechanism; Feature fusion; Temporal convolutional network

DOI：

10.7507/1001-5515.202507012

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Motor imagery electroencephalogram (MI-EEG) decoding algorithms face multiple challenges. These include incomplete feature extraction, susceptibility of attention mechanisms to distraction under low signal-to-noise ratios, and limited capture of long-range temporal dependencies. To address these issues, this paper proposes a multi-branch differential attention temporal network (MDAT-Net). First, the method constructed a multi-branch feature fusion module to extract and fuse diverse spatio-temporal features from different scales. Next, to suppress noise and stabilize attention, a novel multi-head differential attention mechanism was introduced to enhance key signal dynamics by calculating the difference between attention maps. Finally, an adaptive residual separable temporal convolutional network was designed to efficiently capture long-range dependencies within the feature sequence for precise classification. Experimental results showed that the proposed method achieved average classification accuracies of 85.73%, 90.04%, and 96.30% on the public datasets BCI-IV-2a, BCI-IV-2b, and HGD, respectively, significantly outperforming several baseline models. This research provides an effective new solution for developing high-precision motor imagery brain-computer interface systems.

1.	Ma Y, Karako K, Song P, et al. Integrative neurorehabilitation using brain-computer interface: From motor function to mental health after stroke. Biosci Trends, 2025, 19(3): 243-251.
2.	Zhang X, Xie L, Liu W, et al. Exoskeleton-guided passive movement elicits standardized EEG patterns for generalizable BCIs in stroke rehabilitation. J NeuroEngineering Rehabil, 2025, 22(1): 97.
3.	Zhang Y, Gao Y, Zhou J, et al. Advances in brain-computer interface controlled functional electrical stimulation for upper limb recovery after stroke. Brain Res Bull, 2025, 226: 111354.
4.	Cruz M V, Jamal S, Sethuraman S C. A comprehensive survey of brain–computer interface technology in health care: Research perspectives. J Med Signals Sens, 2025, 15(6): 16.
5.	Chen S, Chen M, Wang X, et al. Brain–computer interfaces in 2023–2024. Brain‐X, 2025, 3(1): e70024.
6.	Shirodkar V, Reddy Edla D, Kumari A, et al. Event-related desynchronization detection and electroencephalography motor imagery classification using vision transformer. Intell Data Anal, 2025, 29(6): 1598-1614.
7.	Liu J, Li Y, Zhao D, et al. Efficacy and safety of brain–computer interface for stroke rehabilitation: an overview of systematic review. Front Hum Neurosci, 2025, 19: 1525293.
8.	Gómez-Morales ó W, Collazos-Huertas D F, álvarez-Meza A M, et al. EEG signal prediction for motor imagery classification in brain–computer interfaces. Sensors, 2025, 25(7): 2259.
9.	Blankertz B, Tomioka R, Lemm S, et al. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag, 2007, 25(1): 41-56.
10.	Chen X, Li C, Liu A, et al. Toward open-world electroencephalogram decoding via deep learning: A comprehensive survey. IEEE Signal Process Mag, 2022, 39(2): 117-134.
11.	Schirrmeister R T, Springenberg J T, Fiederer L D J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp, 2017, 38(11): 5391-5420.
12.	Lawhern V J, Solon A J, Waytowich N R, et al. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J Neural Eng, 2018, 15(5): 056013.
13.	Mane R, Chew E, Chua K, et al. FBCNet: A multi-view convolutional neural network for brain-computer interface. arXiv preprint arXiv, 2021: 2104.01233.
14.	Ang K K, Chin Z Y, Zhang H, et al. Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface// 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). Hong Kong: IEEE, 2008: 2390-2397.
15.	Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. J Neural Eng, 2019, 16(5): 051001.
16.	Song Y, Zheng Q, Liu B, et al. EEG conformer: Convolutional transformer for EEG decoding and visualization. IEEE Trans Neural Syst Rehabil Eng, 2022, 31: 710-719.
17.	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need// NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: NIPS, 2017: 6000-6010.
18.	Bai S, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv, 2018: 1803.01271.
19.	Ingolfsson T M, Hersche M, Wang X, et al. EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery brain–machine interfaces// 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Toronto: IEEE, 2020: 2958-2965.
20.	Musallam Y K, AlFassam N I, Muhammad G, et al. Electroencephalography-based motor imagery classification using temporal convolutional network fusion. Biomed Signal Process Control, 2021, 69: 102826.
21.	Altaheri H, Muhammad G, Alsulaiman M. Physics-informed attention temporal convolutional network for EEG-based motor imagery classification. IEEE Trans Ind Inform, 2022, 19(2): 2249-2258.
22.	Ye T, Dong L, Xia Y, et al. Differential transformer. arXiv preprint arXiv, 2024: 2410.05258.
23.	Brunner C, Leeb R, Müller-Putz G, et al. BCI Competition 2008–Graz data set A. Graz: Graz University of Technology, 2008.
24.	Leeb R, Brunner C, Müller-Putz G, et al. BCI Competition 2008–Graz data set B. Graz: Graz University of Technology, 2008.
25.	Mane R, Robinson N, Vinod A P, et al. A multi-view CNN with novel variance layer for motor imagery brain computer interface//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal: IEEE, 2020: 2950-2953.
26.	Tao W, Wang Z, Wong C M, et al. ADFCNN: attention-based dual-scale fusion convolutional neural network for motor imagery brain–computer interface. IEEE Trans Neural Syst Rehabil Eng, 2023, 32: 154-165.
27.	Zhao Q, Zhu W. TMSA-Net: A novel attention mechanism for improved motor imagery EEG signal processing. Biomed Signal Process Control, 2025, 102: 107189.
28.	Gu H, Chen T, Ma X, et al. CLTNet: A hybrid deep learning model for motor imagery classification. Brain Sci, 2025, 15(2): 124.
29.	Ai Q, Liu Y, Liu Q, et al. Holographic convolutional attention neural network for motor imagery decoding based on EEG temporal–spatial frequency features. Biomed Signal Process Control, 2025, 104: 107526.
30.	Wang D, Wei Q. SMANet: A model combining SincNet, multi-branch spatial-temporal CNN and attention mechanism for motor imagery BCI. IEEE Trans Neural Syst Rehabil Eng, 2025, 33: 1497-1508.
31.	Lotte F, Bougrain L, Cichocki A, et al. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng, 2018, 15(3): 031005.

1. Ma Y, Karako K, Song P, et al. Integrative neurorehabilitation using brain-computer interface: From motor function to mental health after stroke. Biosci Trends, 2025, 19(3): 243-251.
2. Zhang X, Xie L, Liu W, et al. Exoskeleton-guided passive movement elicits standardized EEG patterns for generalizable BCIs in stroke rehabilitation. J NeuroEngineering Rehabil, 2025, 22(1): 97.
3. Zhang Y, Gao Y, Zhou J, et al. Advances in brain-computer interface controlled functional electrical stimulation for upper limb recovery after stroke. Brain Res Bull, 2025, 226: 111354.
4. Cruz M V, Jamal S, Sethuraman S C. A comprehensive survey of brain–computer interface technology in health care: Research perspectives. J Med Signals Sens, 2025, 15(6): 16.
5. Chen S, Chen M, Wang X, et al. Brain–computer interfaces in 2023–2024. Brain‐X, 2025, 3(1): e70024.
6. Shirodkar V, Reddy Edla D, Kumari A, et al. Event-related desynchronization detection and electroencephalography motor imagery classification using vision transformer. Intell Data Anal, 2025, 29(6): 1598-1614.
7. Liu J, Li Y, Zhao D, et al. Efficacy and safety of brain–computer interface for stroke rehabilitation: an overview of systematic review. Front Hum Neurosci, 2025, 19: 1525293.
8. Gómez-Morales ó W, Collazos-Huertas D F, álvarez-Meza A M, et al. EEG signal prediction for motor imagery classification in brain–computer interfaces. Sensors, 2025, 25(7): 2259.
9. Blankertz B, Tomioka R, Lemm S, et al. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag, 2007, 25(1): 41-56.
10. Chen X, Li C, Liu A, et al. Toward open-world electroencephalogram decoding via deep learning: A comprehensive survey. IEEE Signal Process Mag, 2022, 39(2): 117-134.
11. Schirrmeister R T, Springenberg J T, Fiederer L D J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp, 2017, 38(11): 5391-5420.
12. Lawhern V J, Solon A J, Waytowich N R, et al. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J Neural Eng, 2018, 15(5): 056013.
13. Mane R, Chew E, Chua K, et al. FBCNet: A multi-view convolutional neural network for brain-computer interface. arXiv preprint arXiv, 2021: 2104.01233.
14. Ang K K, Chin Z Y, Zhang H, et al. Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface// 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). Hong Kong: IEEE, 2008: 2390-2397.
15. Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. J Neural Eng, 2019, 16(5): 051001.
16. Song Y, Zheng Q, Liu B, et al. EEG conformer: Convolutional transformer for EEG decoding and visualization. IEEE Trans Neural Syst Rehabil Eng, 2022, 31: 710-719.
17. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need// NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: NIPS, 2017: 6000-6010.
18. Bai S, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv, 2018: 1803.01271.
19. Ingolfsson T M, Hersche M, Wang X, et al. EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery brain–machine interfaces// 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Toronto: IEEE, 2020: 2958-2965.
20. Musallam Y K, AlFassam N I, Muhammad G, et al. Electroencephalography-based motor imagery classification using temporal convolutional network fusion. Biomed Signal Process Control, 2021, 69: 102826.
21. Altaheri H, Muhammad G, Alsulaiman M. Physics-informed attention temporal convolutional network for EEG-based motor imagery classification. IEEE Trans Ind Inform, 2022, 19(2): 2249-2258.
22. Ye T, Dong L, Xia Y, et al. Differential transformer. arXiv preprint arXiv, 2024: 2410.05258.
23. Brunner C, Leeb R, Müller-Putz G, et al. BCI Competition 2008–Graz data set A. Graz: Graz University of Technology, 2008.
24. Leeb R, Brunner C, Müller-Putz G, et al. BCI Competition 2008–Graz data set B. Graz: Graz University of Technology, 2008.
25. Mane R, Robinson N, Vinod A P, et al. A multi-view CNN with novel variance layer for motor imagery brain computer interface//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal: IEEE, 2020: 2950-2953.
26. Tao W, Wang Z, Wong C M, et al. ADFCNN: attention-based dual-scale fusion convolutional neural network for motor imagery brain–computer interface. IEEE Trans Neural Syst Rehabil Eng, 2023, 32: 154-165.
27. Zhao Q, Zhu W. TMSA-Net: A novel attention mechanism for improved motor imagery EEG signal processing. Biomed Signal Process Control, 2025, 102: 107189.
28. Gu H, Chen T, Ma X, et al. CLTNet: A hybrid deep learning model for motor imagery classification. Brain Sci, 2025, 15(2): 124.
29. Ai Q, Liu Y, Liu Q, et al. Holographic convolutional attention neural network for motor imagery decoding based on EEG temporal–spatial frequency features. Biomed Signal Process Control, 2025, 104: 107526.
30. Wang D, Wei Q. SMANet: A model combining SincNet, multi-branch spatial-temporal CNN and attention mechanism for motor imagery BCI. IEEE Trans Neural Syst Rehabil Eng, 2025, 33: 1497-1508.
31. Lotte F, Bougrain L, Cichocki A, et al. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng, 2018, 15(3): 031005.

Journal of Biomedical Engineering

Latest ArticlesA motor imagery decoding study integrating differential attention with a multi-scale adaptive temporal convolutional network

Abstract Full text Figures/Tables Video References Cited by

Format

Content