Enhancing detection of SSVEP-based BCIs via a novel temporally local canonical correlation analysis

• Published in: Journal of neuroscience methods Vol. 414; p. 110325
• Main Authors: Xia, Guoxian, Wang, Li, Xiong, Shiming, Deng, Jiaxian
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.02.2025
• Subjects: Adult; Algorithms; Brain - physiology; Brain-computer interface (BCI); Brain-Computer Interfaces; Canonical correlation analysis (CCA); Electroencephalography - methods; Evoked Potentials, Visual - physiology; Female; Humans; Male; Signal Processing, Computer-Assisted; Steady-state visual evoked potential (SSVEP); Temporally information; Training data-driven; Young Adult; Temporally information; Brain-computer interface (BCI); Steady-state visual evoked potential (SSVEP); Training data-driven; Canonical correlation analysis (CCA)
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2024.110325

In recent years, spatial filter-based frequency recognition methods have become popular in steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. However, these methods are ineffective in suppressing local noise, and they rely on the length of the data. In practical applications, enhancing recognition performance with short data windows is a significant challenge for the BCI systems. With extracting temporal information and eliminating local noise, a temporally local canonical correlation analysis based on training data-driven (TI-tdCCA) method is proposed to enhance the recognition performance of SSVEPs. Based on a novel framework, the filters are derived by incorporating the Laplacian matrix through the use of TI-CCA between the concatenated training data and individual templates. The target frequency is subsequently determined by applying the appropriate spatial filters and Laplacian matrix. The experimental results on two datasets, consisting of 40 classes and recording from 35 and 70 subjects respectively, demonstrate that the proposed method consistently outperforms the eight competing methods in the majority of cases. The proposed method is simultaneously evaluated by an extended version that incorporates artificial reference signals. The extended method demonstrates a significant improvement over the proposed method. Specifically, with a time window of 0.7 s, the average recognition accuracy of the subjects increases by 10.71 % on the Benchmark dataset and by 6.98 % on the BETA dataset, respectively. Our extended method outperforms the state-of-the-art methods by at least 3 %, and it effectively suppresses local noise and maintains excellent scalability. The proposed method can effectively combine spatial and temporal filters to improve the recognition performance of SSVEPs. •A novel approach is proposed for SSVEP with the integration of spatial filters and the suppression of local noise.•The novel approach is extended by combining the sine and cosine reference signals with individual modules.•The proposed method is superior to other state-of-the-art models.•The proposed method can effectively improve the recognition performance of SSVEP.