Toward exoskeleton control based on steady state visual evoked potentials

Abstract

Brain-machine interfaces (BMIs) are systems that establish a direct connection between the human brain and a machine. These systems are applicable to neuro-rehabilitation. In this study, we propose a method of finding optimal threshold of canonical correlation analysis (CCA) based steady state visual evoked potentials (SSVEPs) classification for detecting resting state and reducing misclassification. As a result, we successfully found optimal threshold for the best performance. This result shows the possibility of SSVEP based exoskeleton online control with a proposed method.