Using modular neural network to SSVEP-based BCI

Abstract

A patient with amyotrophic lateral sclerosis is difficult to talk with other people and the cognitive function is generally spared for most people. Therefore, to develop a steady state visually evoked potential based brain computer interfaces can effectively help patients. To precisely represent the characteristics of frequency responses, three types of features estimated by fast Fourier transform, power cepstrum analysis, and canonical correlation analysis are adopted. To fuse these features, a modular neural network is applied find a decision. The experimental results demonstrated that the proposed approach outperform previous approaches.