Identification of various neurological disorders using EEG signals

Abstract

Activity of human body is controlled by human brain. Identification of different neurological disorders from EEG signals is still a challenging task. In this paper EEG dataset of forty eight subjects (twelve - epileptic, twelve -normal, twelve - schizophrenic and twelve – alzheimer) have been investigated and it is evident from the findings that remarkable difference exists for extracted features. Six statistical features have been extracted from the dataset of aforementioned neurological disorders. Extensive variation in extracted features exists for different neurological disorders. Principal features are selected by calculating Euclidean Distance between different feature vectors. Mean, median and mode are proven to be the best features. The findings are statistically validated using one way analysis of variance (ANOVA).