Feature fusion improves brain-interface paradigm based on steady state visual evoked potential blocking response

• DOI: 10.1016/j.jrras.2024.100940
• Publication Date: 2024-05-09T13:04:44Z
• Authors: Xiangtian Lin; Li Zhang; Xiaoyang Yuan; Changsheng Li; Le He
• Keywords: Canonical correlation; Sliding window protocol; Benchmark (surveying); Feature (linguistics); Interface (matter)

The steady-state visual evoked potential blocking response (SSVEP-BR) is produced on an electroencephalogram (EEG) when the SSVEP interrupted or abolished and allows augmentation of brain-computer interface (BCI) paradigms. Integration SSVEP-BR with enables increase in number commands without addition further stimuli but refinement would improve performance. current study evaluated a novel method to combine multiple features enhance performance frequency recognition identification proposed. Correlation were extracted by filter bank canonical correlation analysis (FBCCA) synchronization multivariate index (MSI) before being integrated. task-related component (TRCA) also evaluated. integrated was compared FBCCA, MSI TRCA for identification. achieved higher classification accuracy than FBCCA benchmark datasets sliding window used EEG data. However, not stable used. improvement over dataset. found be effective A proposed which gives more data shows superior BCI paradigm based SSVEP-BR.