An autoregressive neural network for recognition of eye commands in an EEG-controlled wheelchair

This paper represents an autoregressive (AR) neural network for recognizing eye movement commands for control of an electrical wheelchair using EEG technology. The eye movements such as opening eyes, blinking eyes, glancing left and glancing right related to a few areas of human brain were investigated. A Hamming low-pass filter was applied to remove noise and artifacts of the eye movement signals and to extract the frequency range of the measured signals. An autoregressive model was employed to produce coefficients containing features of the EEG eye signals. The coefficients obtained were inserted the input layer of a neural network (NN) model to classify the eye activities. From the identified output of the network, the wheelchair was controlled to follow the desired direction of user. Experimental results of controlling the wheelchair in the indoor environment showed to illustrate the effectiveness of the proposed approach.