Brain machine interface based wheelchair control with minimal subject training

Abstract

Wheelchair control using a Brain Machine Interface based on motor imagery requires adequate subject training. In this paper we propose a new algorithm for a brain machine interface design which is implemented in real-time wheelchair navigation using minimum subject training. Classification of motor imagery for forward, stop, left and right hand movements are performed using Elman neural classifiers. Real-time wheelchair navigation is performed with trained and naive subjects to validate the proposed algorithm.