EFFECTIVENESS OF USING THE OPENBCI BOARD FOR CLASSIFYING MOTOR IMAGERY
DOI: https://doi.org/10.17721/1728.2748.2025.102.48-52
Keywords:
OpenBCI, motor imagery, neurofeedback, neurorehabilitation, brain-computer interfaceAbstract
This study explores the potential of brain-computer interface (BCI) systems based on motor imagery for application in modern neurorehabilitation. Motor imagery, as a non-invasive BCI modality, enables device control without physical movement, making it especially promising for restoring motor function in individuals recovering from stroke, injury, or neurodegenerative diseases.
Special attention is given to the OpenBCI platform — an open-source hardware and software solution for electroencephalographic (EEG) signal acquisition. The relevance of this research lies in the need for accessible, portable, and effective BCI systems suitable for use outside of laboratory settings. Despite limited accuracy compared to commercial EEG systems, OpenBCI demonstrates considerable potential due to its openness, modularity, and low cost.
The aim of this work is to analyze the effectiveness of an OpenBCI-based BCI system in motor imagery recognition, particularly for rehabilitation purposes. The object of the research is the brain-computer interface system with non-invasive signal acquisition. The subject of the research comprises algorithms and techniques aimed at improving the accuracy of motor imagery classification based on EEG signals acquired via OpenBCI.
The methodological foundation of the study includes the analysis of scientific publications utilizing spatial filtering methods, machine learning (particularly deep learning), visual neurofeedback, adaptive stimulation, and signal window optimization. The literature review is based on scientific articles from databases such as IEEE Xplore, MDPI, Springer Nature, Frontiers, IOPscience, among others.
This study seeks to systematize current approaches for enhancing the accuracy of motor imagery classification using OpenBCI and to outline prospects for their implementation in personalized rehabilitation systems. The advantages and challenges of employing open-source BCI solutions in clinical and non-clinical environments are also discussed.
References
Branco, M. P., Pels, E. G. M., Sars, R. H., Aarnoutse, E. J., Ramsey, N. F., Vansteensel, M. J., & Nijboer, F. (2021). Brain-Computer Interfaces for Communication: Preferences of Individuals With Locked-in Syndrome. Neurorehabilitation and neural repair, 35(3), 267–279. https://doi.org/10.1177/1545968321989331.
Agarwal, M., & Sivakumar, R. (2015). THINK: toward practical General-Purpose Brain-Computer communication. HotWireless ’15, 41–45. https://doi.org/10.1145/2799650.2799659.
Suryotrisongko, H., & Samopa, F. (2015). Evaluating OpenBCI Spiderclaw V1 Headwear’s electrodes placements for Brain-Computer Interface (BCI) Motor Imagery Application. Procedia Computer Science, 72, 398–405. https://doi.org/10.1016/j.procs.2015.12.155.
Cely, A. X. G., Blanco-Diaz, C. F., Mendez, C. D. G., Parra, A. C. V., & Bastos-Filho, T. F. (2024b). Classification of opening/closing hand motor imagery induced by left and right robotic gloves through EEG signals. Transactions on Energy Systems and Engineering Applications, 5(2), 1–9. https://doi.org/10.32397/tesea.vol5.n2.579.
Kabeer, A. M., Megalingam, R. K., & Sakthiprasad, K. M. (2024). Brain–Computer Interfaces for Mobility Assistance: A Comparative Analysis of EEG-Based Classification Models for Brain-Controlled Wheelchairs. In Smart innovation, systems and technologies (pp. 245–256). https://doi.org/10.1007/978-981-97-6810-3_20.
Yohanandan, S. A., Kiral-Kornek, I., Tang, J., Mshford, B. S., Asif, U., & Harrer, S. (2018). A robust Low-Cost EEG motor Imagery-Based Brain-Computer interface. IEEE, 5089–5092. https://doi.org/10.1109/embc.2018.8513429.
Aalborg Universitet, & Leerskov, K. (2024). Hybrid FES-Robotic Rehabilitation System for Lower Limb Neurorehabilitation: Design and evaluation (By L. N. S. Andreasen Struijk, E. G. Spaich, R. G. Larsen, S. Crea, & P. Kidmose) [Aalborg University Open Publishing]. https://vbn.aau.dk/ws/portalfiles/portal/768141147/PHD_KL_ONLINE.pdf.
Cely, A. X. G., Blanco-Diaz, C. F., Mendez, C. D. G., Parra, A. C. V., & Bastos-Filho, T. F. (2024). Classification of opening/closing hand motor imagery induced by left and right robotic gloves through EEG signals. Transactions on Energy Systems and Engineering Applications, 5(2), 1–9. https://doi.org/10.32397/tesea.vol5.n2.579.
Kabeer, A. M., Megalingam, R. K., & Sakthiprasad, K. M. (2024b). Brain–Computer Interfaces for Mobility Assistance: A Comparative Analysis of EEG-Based Classification Models for Brain-Controlled Wheelchairs. In Smart innovation, systems and technologies (pp. 245–256). https://www.researchgate.net/publication/385389496_Brain-Computer_Interfaces_for_Mobility_Assistance_A_Comparative_Analysis_of_EEG-Based_Classification_Models_for_Brain-Controlled_Wheelchairs.
