Improving Multi-Class Motor Imagery Classification Using EEG Signals and a Hybrid Deep Learning Model in Brain–Computer Interface Systems for Patients with Motor Disabilities
DOI:
https://doi.org/10.31185/wjes.Vol14.Iss3.944Keywords:
EEG signals, brain–computer interface, motor imagery, multi-class classification, deep learning, motor disabilitiesAbstract
EEG (Electroencephalography)-based BCI (brain-computer interface) systems are widely used to help patients with motor disabilities. Motor imagery (MI) is a major BCI paradigm since it allows the user to imagine the movement of limbs without its muscular execution. Nonetheless, the multi-class MI-EEG classification remains challenging because EEG signals are nonlinear and non-stationary in nature. This research proposes a model for four-class MI-EEG classification using a compact hybrid CNN-BiLSTM-attention in compact form. The framework integrates spatial CNN filtering, bidirectional temporal sequence modeling, and attention-based temporal weighting within a single end-to-end model. The BCI Competition IV Dataset 2a was used to evaluate the proposed model and compared it with CSP-LDA, SVM, CNN and CNN-LSTM baselines. Based on the experimental results, the proposed model achieved the best overall performance with a mean accuracy of 83.89% ±4.20% and Cohen’s kappa of 0.7077 ±0.0635. The results of the study show that bidirectional temporal modeling and attention weighting can enhance the robustness and discriminative ability of EEG-based MI classification for assistive BCI applications.
References
[1] X. Wang, V. Liesaputra, Z. Liu, Y. Wang, and Z. Huang, “An in-depth survey on Deep Learning-based Motor Imagery Electroencephalogram (EEG) classification,” Artificial Intelligence in Medicine, vol. 147, art. no. 102738, 2024. https://doi.org/10.1016/j.artmed.2023.102738 DOI: https://doi.org/10.1016/j.artmed.2023.102738
[2] I. Hameed, D. M. Khan, S. M. Ahmed, S. S. Aftab, and H. Fazal, “Enhancing motor imagery EEG signal decoding through machine learning: A systematic review of recent progress,” Computers in Biology and Medicine, vol. 185, art. no. 109534, 2025. https://doi.org/10.1016/j.compbiomed.2024.109534 DOI: https://doi.org/10.1016/j.compbiomed.2024.109534
[3] B. Yang, F. Rong, Y. Xie, D. Li, J. Zhang, F. Li, G. Shi, et al., “A multi-day and high-quality EEG dataset for motor imagery brain-computer interface,” Scientific Data, vol. 12, art. no. 488, 2025. https://doi.org/10.1038/s41597-025-04826-y DOI: https://doi.org/10.1038/s41597-025-04826-y
[4] X. Wang, Y. Wang, W. Qi, D. Kong, and W. Wang, “BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery,” Neural Networks, vol. 170, pp. 312–324, 2024. https://doi.org/10.1016/j.neunet.2023.11.037 DOI: https://doi.org/10.1016/j.neunet.2023.11.037
[5] S. Lian and Z. Li, “An end-to-end multi-task motor imagery EEG classification neural network based on dynamic fusion of spectral-temporal features,” Computers in Biology and Medicine, vol. 178, art. no. 108727, 2024. https://doi.org/10.1016/j.compbiomed.2024.108727
[6] H. Gu, T. Chen, X. Ma, M. Zhang, Y. Sun, and J. Zhao, “CLTNet: A hybrid deep learning model for motor imagery classification,” Brain Sciences, vol. 15, no. 2, art. no. 124, 2025. https://doi.org/10.3390/brainsci15020124 DOI: https://doi.org/10.3390/brainsci15020124
[7] Y. Ding, C. Udompanyawit, Y. Zhang, et al., “EEG-based brain-computer interface enables real-time robotic hand control at individual finger level,” Nature Communications, vol. 16, art. no. 5401, 2025. https://doi.org/10.1038/s41467-025-61064-x DOI: https://doi.org/10.1038/s41467-025-61064-x
[8] Z. Ming, W. Yu, J. Fan, et al., “Efficacy of kinesthetic motor imagery based brain computer interface combined with tDCS on upper limb function in subacute stroke,” Scientific Reports, vol. 15, art. no. 11829, 2025. DOI: https://doi.org/10.1038/s41598-025-96039-x DOI: https://doi.org/10.1038/s41598-025-96039-x
[9] X. Deng, H. Huo, L. Ai, D. Xu, and C. Li, “A novel 3D approach with a CNN and Swin Transformer for decoding EEG-based motor imagery classification,” Sensors, vol. 25, no. 9, art. no. 2922, 2025. https://doi.org/10.3390/s25092922 DOI: https://doi.org/10.3390/s25092922
[10] Z. Li, M. Li, and Y. Yang, “Motor imagery decoding network with multisubject dynamic transfer,” Brain Informatics, vol. 12, art. no. 20, 2025. https://doi.org/10.1186/s40708-025-00267-w DOI: https://doi.org/10.1186/s40708-025-00267-w
[11] J. Ma, J. Zhang, Y. Yang, B. Yang, and C. Shan, “Motor imagery classification based on temporal-spatial domain adaptation for stroke patients,” Cognitive Computation, vol. 17, art. no. 119, 2025. https://doi.org/10.1007/s12559-025-10477-3 DOI: https://doi.org/10.1007/s12559-025-10477-3
[12] M. Tangermann, K.-R. Müller, A. Aertsen, N. Birbaumer, C. Braun, C. Brunner, R. Leeb, C. Mehring, K. J. Miller, G. Mueller-Putz, G. Nolte, G. Pfurtscheller, H. Preissl, G. Schalk, A. Schlögl, C. Vidaurre, S. Waldert, and B. Blankertz, “Review of the BCI Competition IV,” Frontiers in Neuroscience, vol. 6, art. no. 55, 2012. https://doi.org/10.3389/fnins.2012.00055 DOI: https://doi.org/10.3389/fnins.2012.00055
[13] B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, and K.-R. Müller, “Optimizing spatial filters for robust EEG single-trial analysis,” IEEE Signal Processing Magazine, vol. 25, no. 1, pp. 41–56, 2008. https://doi.org/10.1109/MSP.2008.4408441 DOI: https://doi.org/10.1109/MSP.2008.4408441
[14] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, art. no. 6, 2020. https://doi.org/10.1186/s12864-019-6413-7 DOI: https://doi.org/10.1186/s12864-019-6413-7
[15] V. J. Lawhern, A. J. Solon, N. R. Waytowich, S. M. Gordon, C. P. Hung, and B. J. Lance, “EEGNet: A compact convolutional neural network for EEG-based brain-computer interfaces,” Journal of Neural Engineering, vol. 15, no. 5, art. no. 056013, 2018. https://doi.org/10.1088/1741-2552/aace8c DOI: https://doi.org/10.1088/1741-2552/aace8c
[16] R. T. Schirrmeister, J. T. Springenberg, L. D. J. Fiederer, M. Glasstetter, K. Eggensperger, M. Tangermann, F. Hutter, W. Burgard, and T. Ball, “Deep learning with convolutional neural networks for EEG decoding and visualization,” Human Brain Mapping, vol. 38, no. 11, pp. 5391–5420, 2017. https://doi.org/10.1002/hbm.23730 DOI: https://doi.org/10.1002/hbm.23730
[17] S. Sakhavi, C. Guan, and S. Yan, “Learning temporal information for brain-computer interface using convolutional neural networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 11, pp. 5619–5629, 2018. https://doi.org/10.1109/TNNLS.2018.2789927 DOI: https://doi.org/10.1109/TNNLS.2018.2789927
[18] T. M. Ingolfsson, M. Hersche, X. Wang, N. Kobayashi, L. Cavigelli, and L. Benini, “EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery brain-machine interfaces,” in Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada, 2020, pp. 2958–2965. https://doi.org/10.1109/SMC42975.2020.9283028 DOI: https://doi.org/10.1109/SMC42975.2020.9283028
[19] C. Zhang, Y.-K. Kim, and A. Eskandarian, “EEG-inception: An accurate and robust end-to-end neural network for EEG-based motor imagery classification,” Journal of Neural Engineering, vol. 18, no. 4, art. no. 046014, 2021. https://doi.org/10.1088/1741-2552/abed81 DOI: https://doi.org/10.1088/1741-2552/abed81
[20] S. Lian and Z. Li, “An end-to-end multi-task motor imagery EEG classification neural network based on dynamic fusion of spectral-temporal features,” Computers in Biology and Medicine, vol. 178, art. no. 108727, 2024. https://doi.org/10.1016/j.compbiomed.2024.108727 DOI: https://doi.org/10.1016/j.compbiomed.2024.108727
[21] W. Zhao, X. Jiang, B. Zhang, S. Xiao, and S. Weng, “CTNet: A convolutional transformer network for EEG-based motor imagery classification,” Scientific Reports, vol. 14, art. no. 20237, 2024. https://doi.org/10.1038/s41598-024-71118-7 DOI: https://doi.org/10.1038/s41598-024-71118-7
[22] V. Jayaram and A. Barachant, “MOABB: Trustworthy algorithm benchmarking for BCIs,” Journal of Neural Engineering, vol. 15, no. 6, art. no. 066011, 2018. https://doi.org/10.1088/1741-2552/aadea0 DOI: https://doi.org/10.1088/1741-2552/aadea0
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahmed Aljabery
This work is licensed under a Creative Commons Attribution 4.0 International License.
