Decoding of responses to mixed frequency and phase coded visual stimuli using multiset canonical correlation analysis.

Abstract

Brain-computer interfacing (BCI) based on steady-state visual evoked potentials (SSVEPs) is one of the most practical BCIs because of its high recognition accuracies and little training of a user. Mixed frequency and phase coding which can implement a number of commands and achieve a high information transfer rate (ITR) has recently been gaining much attention. In order to implement mixed-coded SSVEP-BCI as a reliable interface, it is important to detect commands fast and accurately. This paper presents a novel method to recognize mixed-coded SSVEPs which achieves high performance. The method employs multiset canonical correlation analysis to obtain spatial filters which enhance SSVEP components. An experiment with a mixed-coded SSVEP-BCI was conducted to evaluate performance of the proposed method compared with the previous work. The experimental results showed that the proposed method achieved significantly higher command recognition accuracy and ITR than the state-of-the-art.