3066-280XISSN (Online)
Volume 5 , Issue 2 , PP: 01-21, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Ahmed EL-Emam 1 , Hossam El-Din Moustafa 2 , W. Mustafa 3 , Islam Ismael 4 , EL-Sayed M.El-Kenawy 5 *
Doi: https://doi.org/10.54216/MOR.050201
Brain-computer interface (BCI) systems based on electroencephalography (EEG) are applications that allow human-to-machine communication with intuitive (near-transparent) control, whose neural commands are decoded based on intentional movement. Recent research on the topic of machine learning (ML) has been able to greatly enhance the classification of the EEG-signals associated with the movement of the hands, head movements, and mobility movements of the eyes. The developments allow various utilization across assistive technologies, prosthetic control, and non-verbal communication. EEG, however, is highly non-stationery and noise-sensitive, so advanced preprocessing and optimization methods have to be applied to optimize performance in classification. This paper outlines an in-depth review of some of the most popular ML algorithms, i.e. support vector machines (SVMs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), and optimization methods, i.e., genetic algorithms (GAs), particle swarm optimization (PSO), and transfer learning. We point out existing problems in the processing of EEG signals and suggest directions in the future that will improve the robustness, generalization, and real-time behavior of BCI.
BCI , Machine Learning , Deep Learning , EEG , Optimization technique
[1] D. Li et al., “Effects of brain–computer interface based training on post-stroke upper-limb rehabilitation: a meta-analysis,” BioMed Central Ltd., Dec. 2025, doi: 10.1186/s12984-025-01588-x.
[2] H. Su et al., “Efficient motor imagery electroencephalogram classification via cross tensor coupling decomposition based on augmented covariance networks,” Neurocomputing, vol. 634, Jun. 2025, doi: 10.1016/j.neucom.2025.129911.
[3] J. Xie et al., “A novel method for motor imagery electroencephalogram classification: cross tensor coupling decomposition based on diverse modality brain functional networks,” Biomed. Signal Process. Control, vol. 110, Dec. 2025, doi: 10.1016/j.bspc.2025.108295.
[4] B. Lu, F. Wang, J. Chen, G. Wen, and R. Fu, “Improving two-dimensional linear discriminant analysis with L1 norm for optimizing EEG signal,” Inf. Sci., vol. 690, Feb. 2025, doi: 10.1016/j.ins.2024.121585.
[5] T. Klein, P. Minakowski, and S. Sager, “Flexible Patched Brain Transformer model for EEG decoding,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-86294-3.
[6] M. Bouchane, W. Guo, and S. Yang, “Hybrid CNN-GRU models for improved EEG motor imagery classification,” Sensors, vol. 25, no. 5, Mar. 2025, doi: 10.3390/s25051399.
[7] W. Chen et al., “A novel deep learning model for motor imagery classification in brain–computer interfaces,” Information, vol. 16, no. 7, p. 582, Jul. 2025, doi: 10.3390/info16070582.
[8] S. Mallat, E. Hkiri, A. M. Albarrak, and B. Louhichi, “A synergy of convolutional neural networks for sensor-based EEG brain–computer interfaces to enhance motor imagery classification,” Sensors, vol. 25, no. 2, Jan. 2025, doi: 10.3390/s25020443.
[9] J. Lu, Y. Tian, Y. Zhang, Q. Z. Sheng, and X. Zheng, “LGL-BCI: A motor-imagery-based brain–computer interface with geometric learning,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 9, no. 1, Mar. 2025, doi: 10.1145/3699732.
[10] K. Mróz and K. Jonak, “Preliminary electroencephalography-based assessment of anxiety using machine learning: A pilot study,” Brain Sci., vol. 15, no. 6, p. 571, May 2025, doi: 10.3390/brainsci15060571.
[11] Cataldo et al., “Deep learning-enhanced motor training: A hybrid VR and exoskeleton system for cognitive-motor rehabilitation,” Bioengineering, 2025, doi: 10.3390/bioengineering.
[12] S. M. Kaviri and R. Vinjamuri, “Decoding motor execution and motor imagery from EEG with deep learning and source localization,” Biomedical Engineering Advances, vol. 9, p. 100156, Jun. 2025, doi: 10.1016/j.bea.2025.100156.
[13] J. Gong, H. Liu, F. Duan, Y. Che, and Z. Yan, “Research on adaptive discriminating method of brain–computer interface for motor imagination,” Brain Sci., vol. 15, no. 4, Apr. 2025, doi: 10.3390/brainsci15040412.
[14] H. Gu et al., “CLTNet: A hybrid deep learning model for motor imagery classification,” Brain Sci., vol. 15, no. 2, Feb. 2025, doi: 10.3390/brainsci15020124.
[15] S. Ma et al., “FBATCNet: A temporal convolutional network with frequency band attention for decoding motor imagery EEG,” IEEE Access, vol. 13, pp. 11265–11279, 2025, doi: 10.1109/ACCESS.2025.3525528.
[16] H. R. Al Ghayab et al., “EEG-based over-complete rational dilation wavelet transform coupled with autoregressive for motor imagery classification,” Expert Syst. Appl., vol. 269, Apr. 2025, doi: 10.1016/j.eswa.2025.126433.
[17] R. Lv et al., “Enhanced classification of motor imagery EEG signals using spatio-temporal representations,” Inf. Sci., vol. 714, Oct. 2025, doi: 10.1016/j.ins.2025.122221.
[18] Falcon-Caro, J. Filipe Ferreira, and S. Sanei, “Cooperative identification of prolonged motor movement from EEG for BCI without feedback,” IEEE Access, vol. 13, pp. 11765–11777, 2025, doi: 10.1109/ACCESS.2025.3528539.
[19] Ó. W. Gómez-Morales et al., “EEG signal prediction for motor imagery classification in brain–computer interfaces,” Sensors, vol. 25, no. 7, Apr. 2025, doi: 10.3390/s25072259.
[20] F. Mohamed and V. Jusas, “Advancing fractal dimension techniques to enhance motor imagery tasks using EEG for brain–computer interface applications,” Appl. Sci., vol. 15, no. 11, Jun. 2025, doi: 10.3390/app15116021.
[21] Ekhlasi, H. Ahmadi, and M. S. Hoseinzadeh, “Investigating optimal EEG channels and features for brain–computer interfaces: An exploration using evolutionary algorithms and machine learning,” Front. Biomed. Technol., vol. 12, no. 2, pp. 278–291, Mar. 2025, doi: 10.18502/fbt.v12i2.18275.
[22] X. Deng et al., “A novel 3D approach with a CNN and Swin Transformer for decoding EEG-based motor imagery classification,” Sensors, vol. 25, no. 9, May 2025, doi: 10.3390/s25092922.
[23] Raza and M. Z. Yusoff, “Development of a CNN-LSTM deep learning model for motor imagery EEG classification for BCI applications,” Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22705–22711, Jun. 2025, doi: 10.48084/ETASR.9945.
[24] M. Heim et al., “Real-time EEG-based BCI for self-paced motor imagery and motor execution using functional neural networks,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3569932.
[25] M. K. Titkanlou, D. T. Pham, and R. Mouček, “Classification of EEG signal using deep learning architectures based motor-imagery for an upper-limb rehabilitation exoskeleton,” SN Comput. Sci., vol. 6, no. 3, Mar. 2025, doi: 10.1007/s42979-025-03743-6.
[26] S. Lv et al., “Classification of left and right-hand motor imagery in acute stroke patients using EEG microstate,” J. Neuroeng. Rehabil., vol. 22, no. 1, Dec. 2025, doi: 10.1186/s12984-025-01668-y.
[27] Y. Ding et al., “EEG-based brain–computer interface enables real-time robotic hand control at individual finger level,” Nat. Commun., vol. 16, no. 1, p. 5401, Jun. 2025, doi: 10.1038/s41467-025-61064-x.
[28] M. Degirmenci et al., “EEG-based finger movement classification with intrinsic time-scale decomposition,” Front. Hum. Neurosci., vol. 18, 2024, doi: 10.3389/fnhum.2024.1362135.
[29] E. Mattei et al., “MOVING: A multi-modal dataset of EEG signals and virtual glove hand tracking,” Sensors, vol. 24, no. 16, 2024, doi: 10.3390/s24165207.
[30] L. Kok et al., “Transfer learning and deep neural networks for robust intersubject hand movement detection from EEG signals,” Appl. Sci., vol. 14, no. 17, Sep. 2024, doi: 10.3390/app14178091.
[31] Kumari et al., “EEG-based motor imagery channel selection and classification using hybrid optimization and two-tier deep learning,” J. Neurosci. Methods, vol. 409, 2024, doi: 10.1016/j.jneumeth.2024.110215.
[32] Altameem et al., “Performance analysis of machine learning algorithms for classifying hand motion-based EEG brain signals,” Comput. Syst. Sci. Eng., vol. 42, no. 3, pp. 1095–1107, 2022, doi: 10.32604/csse.2022.023256.
[33] S. M. Hosseini and V. Shalchyan, “Continuous decoding of hand movement from EEG signals using phase-based connectivity features,” Front. Hum. Neurosci., vol. 16, Jun. 2022, doi: 10.3389/fnhum.2022.901285.
[34] P. Kokate, S. Pancholi, and A. M. Joshi, “Classification of upper arm movements from EEG signals using machine learning with ICA analysis,” Jul. 2021. [Online]. Available: http://arxiv.org/abs/2107.08514
[35] W. Liang et al., “Variance characteristic preserving common spatial pattern for motor imagery BCI,” Front. Hum. Neurosci., vol. 17, 2023, doi: 10.3389/fnhum.2023.1243750.
[36] S. Mathiyazhagan and M. S. G. Devasena, “Motor imagery EEG signal classification using novel deep learning algorithm,” Sci. Rep., vol. 15, p. 24539, Jul. 2025, doi: 10.1038/s41598-025-00824-7.
[37] S. Agarwal, M. Jamal, and P. Kumar, “Deep learning based classification and combined transform based feature extraction approach for mental stress prediction of human beings using EEG,” Trans. Emerg. Telecommun. Technol., vol. 36, Jun. 2025, doi: 10.1002/ett.70155.
[38] H. Uyanik et al., “Automated detection of neurological and mental health disorders using EEG signals and artificial intelligence: A systematic review,” John Wiley and Sons Inc., Mar. 2025, doi: 10.1002/widm.70002.
[39] S. M. Atoar Rahman et al., “Advancement in graph neural networks for EEG signal analysis and application: A review,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3549120.
[40] Y. H. Gao, X. W. Huang, and Y. M. Meng, “A systematic evaluation of data preprocessing and model optimization for machine learning algorithms: Using sphalerite trace element data as an example,” J. Asian Earth Sci., vol. 292, Oct. 2025, doi: 10.1016/j.jseaes.2025.106728.
[41] M. A. Al-Betar, Z. A. A. Alyasseri, and S. N. Makhadmeh, “EEG channels selection for stroke patients rehabilitation using equilibrium optimizer,” J. Intell. Syst., vol. 34, no. 1, Aug. 2025, doi: 10.1515/jisys-2024-0252.
[42] H. A. Siddiqa et al., “EEG electrode setup optimization using feature extraction techniques for neonatal sleep state classification,” Front. Comput. Neurosci., vol. 19, 2025, doi: 10.3389/fncom.2025.1506869.
[43] Latreche, S. Slatnia, O. Kazar, and S. Harous, “An optimized deep hybrid learning for multi-channel EEG-based driver drowsiness detection,” Biomed. Signal Process. Control, vol. 99, Jan. 2025, doi: 10.1016/j.bspc.2024.106881.
[44] Ortega-Rodríguez, J. F. Gómez-González, and E. P. de Pablo, “Biometric identification based on EEG using fuzzy logic: A novel approach with metaheuristic optimization,” IEEE Trans. Dependable Secure Comput., vol. 22, no. 4, pp. 4116–4125, 2025, doi: 10.1109/TDSC.2025.3543598.
