P300 Detection with Brain–Computer Interface Application Using PCA and Ensemble of Weighted SVMs

Abstract

Brain–computer interface (BCI) P300 speller can be used as a powerful aid for severely disabled people in their everyday life. The character recognition using P300 speller involves two stages for classification. First stage is to detect the P300 signal and second one is to determine the right character from the detected P300. Features are important for classification, but large feature dimension is a problem for P300 classification as computational complexity increase due to more number of features. In this work, principal component analysis (PCA) based ensemble of weighted support vector machine (PCA-EWSVM) is used for character recognition. The proposed method includes PCA for feature extraction and an ensemble of weighted SVM (EWSVM) for classification. PCA is used to reduce the redundant features and ensemble of weighted classifier for minimizing the classifier variability. The proposed algorithm has been evaluated on data-set of the BCI Competition II and data-set II of the BCI Competition III.