EEG Signals of Motor Imagery Classification Using Adaptive Neuro-Fuzzy Inference System

Brain Computer Interface (BCI) techniques are used to help disabled people to translate brain signals to control commands imitating specific human thinking based on Electroencephalography (EEG) signal processing. This paper tries to accurately classify motor imagery imagination tasks: e.g. left and right hand movement using three different methods which are: (1) Adaptive Neuro Fuzzy Inference System (ANFIS), (2) Linear Discriminant Analysis (LDA) and (3) k-nearest neighbor (KNN) classifiers. With ANFIS, different clustering methods are utilized which are Subtractive, Fuzzy C-Mean (FCM) and K-means. These clustering methods are examined and compared in terms of their accuracy. Three features are studied in this paper including AR coefficients, Band Power Frequency, and Common Spatial pattern (CSP). The classification accuracies with two optimal channels C3 and C4 are investigated.