Improved filter bank common spatial pattern algorithm based on the sparrow search algorithm
Among them, SSA-FBCSP-LDA achieved the best performance, outperforming the conventional uniform sub-band approach by 21.76% and reaching an average accuracy of 89.92%. The adaptively selected sub-bands closely matched the ERD/ERS distribution, confirming the method's effectiveness in frequency-band optimization. Compared with recent deep-learning-based MI-EEG models, the proposed technique offers a balance of accuracy, interpretability, and computational efficiency, providing a promising direction for personalized brain-computer interface systems.
Authors
- Zhenxi Zhao (ORCID: https://orcid.org/0000-0001-8056-484X)
- Jihui Ding (ORCID: https://orcid.org/0000-0002-9624-6376)
- Yingyu Cao (ORCID: https://orcid.org/0000-0002-0103-8997)
- Minyue Fu (ORCID: https://orcid.org/0000-0002-4659-601X)
- Xuecheng Liu (ORCID: https://orcid.org/0000-0002-4457-2620)
- Yongzheng He
- Xiangpeng Lyv
Institutions
- Beijing Institute of Petrochemical Technology (CN)
- Tiangong University (CN)
- Henan Medical University (CN)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2025-12-18
- DOI
- https://doi.org/10.3389/fnhum.2025.1679329
- Citations
- 1
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 1.43
Funders
- Beijing Municipal Science and Technology Commission
- National Key Research and Development Program of China