Efficient Spatial Filters Enhance SSVEP Target Recognition Based on Task-Related Component Analysis

Abstract

Task-related component analysis (TRCA) has been applied successfully in the recently popular steady-state visual evoked potential (SSVEP) target recognition methods. However, a spatial filter is trained for each class in TRCA, and the training of each filter uses only the training data of the corresponding class. Therefore, the information between classes is ignored in the training process, which leads to classification inefficiency. Aiming at solving this defect in TRCA, we proposed a 2-D locality preserving projections (2DLPP) method and a 2-D linear discriminant analysis (2DLDA) method based on the 2-Norm form of Pearson’s correlation coefficient. The 2DLPP and 2DLDA methods can simultaneously use the samples of all categories to train the spatial filters so that these two methods can make use of the information between classes to some extent. We also showed that the 2DLPP method and the 2DLDA method performed significantly better than the multiset canonical correlation analysis (MsetCCA), extended CCA (eCCA), and TRCA methods with two public data sets. Therefore, the proposed methods based on 2DLPP or 2DLDA can make more efficient use of sample information and have a great potential for SSVEP target recognition.