Adaptive Brain-Computer Interface Based on CNN-RNN for Medical Rehabilitation and Smart Device Control
Keywords:
Brain Computer Interface, Electroencephalography, Deep Learning, Convolutional Neural Networks, Recurrent Neural NetworkAbstract
Brain-Computer Interfaces (BCIs) based on motor imagery (MI) offer a direct communication pathway for assistive technologies and neurorehabilitation. A significant challenge lies in the inherent non-stationarity and inter-subject variability of Electroencephalography (EEG) signals, which limits the performance and adaptability of conventional systems. This paper proposes a novel adaptive BCI framework that leverages a hybrid Convolutional and Recurrent Neural Network (CNN-RNN) to dynamically learn spatio-temporal features from raw, multi-channel EEG data. This study aims to develop a lightweight and stable model for accurate MI classification. The model was designed for efficiency, utilizing a streamlined architecture with merely 41,860 parameters, and was rigorously evaluated on the public BCI Competition IV 2a dataset for four-class MI classification across nine subjects. The results demonstrate a robust validation accuracy of 62.17%, significantly surpassing the chance-level baseline of 25%. Crucially, the model exhibited exceptional stability, converging rapidly and maintaining consistent performance without overfitting, while also showcasing efficient computational properties. This study confirms the viability of lightweight, adaptive deep learning models in creating more reliable and practical BCIs, establishing a foundational step towards their application in clinical rehabilitation and smart device control.
References
V. Khorev et al., “Review on the Use of Brain Computer Interface Rehabilitation Methods for Treating Mental and Neurological Conditions,” J. Integr. Neurosci., vol. 23, no. 7, pp. 1–18, Jul. 2024, [Online].
Available: https://www.imrpress.com/journal/JIN/23/7/10.31083/j.jin2307125
W. Liao, J. Li, X. Zhang, and C. Li, “Motor imagery brain–computer interface rehabilitation system enhances upper limb performance and improves brain activity in stroke patients: A clinical study,” Front. Hum. Neurosci., vol. 17, no. March, pp. 1–9, 2023, doi: 10.3389/fnhum.2023.1117670.
M. Orban, M. Elsamanty, K. Guo, S. Zhang, and H. Yang, “A Review of Brain Activity and EEG-Based Brain–Computer Interfaces for Rehabilitation Application,” Bioengineering, vol. 9, no. 12, 2022, doi: 10.3390/bioengineering9120768.
Z. Z. Ma et al., “Motor imagery-based brain–computer interface rehabilitation programs enhance upper extremity performance and cortical activation in stroke patients,” J. Neuroeng. Rehabil., vol. 21, no. 1,
pp. 1–14, 2024, doi: 10.1186/s12984-024-01387-w.
W. Zhang, X. Tang, X. Dang, and M. Wang, “A Capsule Decision Neural Network Based on Transfer Learning for EEG Signal Classification,” Biomimetics, vol. 10, no. 4, pp. 1–18, 2025, doi: 10.3390/biomimetics10040225.
W. H. Elashmawi et al., “A Comprehensive Review on Brain–Computer Interface (BCI)-Based Machine and Deep Learning Algorithms for Stroke Rehabilitation,” Appl. Sci., vol. 14, no. 14, pp. 1–19, 2024, doi: 10.3390/app14146347.
N. A. Alzahab et al., “Hybrid deep learning (Hdl)-based brain-computer interface (bci) systems: A systematic review,” Brain Sci., vol. 11, no. 11, pp. 1–37, 2021, doi: 10.3390/brainsci11010075.
A. Bonci, S. Fiori, H. Higashi, T. Tanaka, and F. Verdini, “An introductory tutorial on brain–computer interfaces and their applications,” Electron., vol. 10, no. 5, pp. 1–43, 2021, doi: 10.3390/electronics10050560.
M. Saeidi, P. A. Hancock, and A. Al-juaid, “brain sciences Neural Decoding of EEG Signals with Machine Learning : A Systematic Review,” Brain Sci., vol. 11, no. 1, pp. 1–44, 2021, [Online].
Available: https://www.mdpi.com/2076-3425/11/11/1525
T. Najafi, R. Jaafar, R. Remli, and W. A. Wan Zaidi, “A Classification Model of EEG Signals Based on RNN-LSTM for Diagnosing Focal and Generalized Epilepsy,” Sensors, vol. 22, no. 19, pp. 1–13, 2022, doi: 10.3390/s22197269.
V. Asanza, E. Peláez, F. Loayza, L. L. Lorente-Leyva, and D. H. Peluffo-Ordóñez, “Identification of Lower-Limb Motor Tasks via Brain–Computer Interfaces: A Topical Overview,” Sensors, vol. 22, no. 5,
pp. 1–24, 2022, doi: 10.3390/s22052028.
E. H. Houssein, A. Hammad, and A. A. Ali, Human emotion recognition from EEG-based brain– computer interface using machine learning: a comprehensive review, vol. 34, no. 15. Springer London, 2022. doi: 10.1007/s00521-022-07292-4.
R. Shelishiyah, D. B. Thiyam, M. J. Margaret, and N. M. M. Banu, “A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system,” Sci. Rep., vol. 15, no. 1, pp. 1–10, 2025, doi: 10.1038/s41598-024-84883-2.
C. T. Lin, F. C. Lin, S. A. Chen, S. W. Lu, T. C. Chen, and L. W. Ko, “EEG-based brain-computer interface for smart living environmental auto-adjustment,” J. Med. Biol. Eng., vol. 30, no. 4, pp. 237– 245, 2010, doi: 10.5405/jmbe.30.4.07.
Q. Xiao et al., “Secure wireless communication of brain–computer interface and mind control of smart devices enabled by space-time-coding metasurface,” Nat. Commun. , vol. 16, no. 1, pp. 1–11, 2025, doi: 10.1038/s41467-025-63326-0.
H. Liu et al., “An EEG motor imagery dataset for brain computer interface in acute stroke patients,” Sci. Data, vol. 11, no. 1, pp. 1–10, 2024, doi: 10.1038/s41597-023-02787-8.
M. A. Fodor, H. Herschel, A. Cantürk, G. Heisenberg, and I. Volosyak, “Evaluation of Different Visual Feedback Methods for Brain—Computer Interfaces (BCI) Based on Code-Modulated Visual Evoked Potentials (cVEP),” Brain Sci., vol. 14, no. 8, pp. 1–16, 2024, doi: 10.3390/brainsci14080846.
S. Rasheed, “A Review of the Role of Machine Learning Techniques towards Brain–Computer Interface Applications,” Mach. Learn. Knowl. Extr., vol. 3, no. 4, pp. 835–862, 2021, doi: 10.3390/make3040042.
E. Antoniou et al., “EEG-Based Eye Movement Recognition Using Brain–Computer Interface and Random Forests,” Sensors, vol. 21, no. 7, p. 2339, Mar. 2021, doi: 10.3390/s21072339.
A. Singh, A. A. Hussain, S. Lal, and H. W. Guesgen, “A Comprehensive Review on Critical Issues and Possible Solutions of Motor Imagery Based Electroencephalography Brain-Computer Interface,” Sensors, vol. 21, no. 6, p. 2173, Mar. 2021, doi: 10.3390/s21062173.
A. Kawala-Sterniuk et al., “Summary of over fifty years with brain-computer interfaces—a review,”
Brain Sci., vol. 11, no. 1, pp. 1–41, 2021, doi: 10.3390/brainsci11010043.
A. Appriou, L. Pillette, D. Trocellier, D. Dutartre, A. Cichocki, and F. Lotte, “BioPyC, an open-source python toolbox for offline electroencephalographic and physiological signals classification,” Sensors, vol. 21, no. 17, pp. 1–25, 2021, doi: 10.3390/s21175740.
L. Alahaideb, A. Al-Nafjan, H. Aljumah, and M. Aldayel, “Brain–Computer Interface for EEG-Based Authentication: Advancements and Practical Implications,” Sensors, vol. 25, no. 16, pp. 1–29, 2025, doi: 10.3390/s25164946.
P. Gong, P. Wang, Y. Zhou, and D. Zhang, “A Spiking Neural Network With Adaptive Graph Convolution and LSTM for EEG-Based Brain-Computer Interfaces,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 1440–1450, 2023, doi: 10.1109/TNSRE.2023.3246989.
M. Á. Luján, M. V. Jimeno, J. M. Sotos, J. J. Ricarte, and A. L. Borja, “A survey on eeg signal processing techniques and machine learning: Applications to the neurofeedback of autobiographical memory deficits in schizophrenia,” Electron., vol. 10, no. 23, pp. 1–19, 2021, doi: 10.3390/electronics10233037.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Rakha Dwi Prayoga
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
