Abstract

Info

Title:: Steady-state visual evoked potential classification algorithm based on MVMDMS-CCA

Author(s):: NIE Zihao; WANG Raofen; School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

Keywords:: multivariate variational mode decomposition; steady-state visual evoked potential; mode selection; canonicalcorrelation analysis

Abstract:: Abstract: Considering the classification problems of electroencephalogram (EEG) signals and their nonlinear, non-stationarycharacteristics, multivariate variational mode decomposition (MVMD) is introduced to process steady-state visual evokedpotential (SSVEP) signals. Herein a novel classification algorithm for SSVEP called MVMDMS-CCA which combines anew approach for mode selection with canonical correlation analysis (CCA) algorithm is presented. MVMDMS-CCA methoduses the signal-to-noise ratio to determine the key parameter K in MVMD, and then performs MVMD decomposition. Modeselection is carried out by setting a threshold using the maximal information coefficient (MIC) method, and the modes notmeeting the threshold are adaptively denoised using wavelet denoising. A new combination of modes is constructed and inputinto the CCA algorithm to achieve SSVEP signal classification. The proposed method is validated on a self-collected EEGdataset, and it achieves an average classification accuracy of 93.23% under a 3 s window, showing 5.78% higher thanstandard CCA and 1.51% higher than the improved filter bank CCA. MVMDMS-CCA can effectively extract SSVEPcomponents from EEG signals while suppressing noises, providing a new perspective for the research of SSVEP decodingalgorithms.