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

Guoxian Xia; Li Wang; Shiming Xiong; Jiaxian Deng

doi:10.1016/j.jneumeth.2024.110325

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

J Neurosci Methods. 2024 Nov 20:414:110325. doi: 10.1016/j.jneumeth.2024.110325. Online ahead of print.

Authors

Guoxian Xia¹, Li Wang², Shiming Xiong¹, Jiaxian Deng¹

Affiliations

¹ School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China.
² School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China. Electronic address: wangli@gzhu.edu.cn.

PMID: 39577701
DOI: 10.1016/j.jneumeth.2024.110325

Abstract

Background: 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.

New method: 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.

Results: 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.

Comparison with existing methods: Our extended method outperforms the state-of-the-art methods by at least 3 %, and it effectively suppresses local noise and maintains excellent scalability.

Conclusions for research articles: The proposed method can effectively combine spatial and temporal filters to improve the recognition performance of SSVEPs.

Keywords: Brain-computer interface (BCI); Canonical correlation analysis (CCA); Steady-state visual evoked potential (SSVEP); Temporally information; Training data-driven.