Influence of Stimuli Color and Comparison of SVM and ANN Classifier Models for Steady- State Visual Evoked Potentials

In recent years, Brain Computer Interface (BCI) systems based on Steady-State Visual Evoked Potential (SSVEP) have received much attentions. In this study four different flickering frequencies in low frequency region were used to elicit the SSVEPs and were displayed on a Liquid Crystal Display (LCD) monitor using LabVIEW. Two stimuli colors, green and violet were used in this study to investigate the color influence in SSVEPs. The Electroencephalogram (EEG) signals recorded from the occipital region were segmented into 1 second window and features were extracted by using Fast Fourier Transform (FFT). This study tries to develop a classifier, which can provide higher classification accuracy for multiclass SSVEP data. Support Vector Machines (SVM) is a powerful approach for classification and hence widely used in BCI applications. One-Against-All (OAA), a popular strategy for multiclass SVM is compared with Artificial Neural Network (ANN) models on the basis of SSVEP classifier accuracies. Based on this study, it is found that OAA based SVM classifier can provide a better results than ANN. In color comparison SSVEP with violet color showed higher accuracy than that with green stimuli.