P300 Oddball Task and Classification Based on Support Vector Machine for BCI System

Abstract

The P300 oddball task is the most popular paradigm in the existing BCI systems. Recently using auditory stimuli in P300 oddball task arises since it gives much freedom to the BCI user. In this paper, we present a novel BCI paradigm using P300 and P100 responses. Since P300 and P100 responses occur in the frontal lobe and the temporal lobe respectively, so that we can use these responses stimulated by an audio in a single task. The main advantage of our designed paradigm is that we can obtain two different kinds of responses in a single trial EEG task. In the EEG data analysis, we first employ the multivariate empirical mode decomposition (MEMD) algorithm to extract P300 and P100 components. And then, we employ a support vector machine (SVM) technique for the feature classification.