Channel optimization and nonlinear feature extraction for Electroencephalogram signals classification

In present work, a methodology for automatic vigilance level detection of human brain using nonlinear features of Electroencephalogram (EEG) signals is presented. Vigilance level detection methodology consists of three steps, EEG channels selection, feature extraction and classification. EEG signals obtained from 64 channels are sub-divided into four frequency sub-bands i.e. alpha, beta, delta and theta. Channel selection criteria Maximum Energy to Shannon Entropy ratio is applied on each frequency band to select appropriate EEG channels. EEG signals obtained from selected channels are further divided into frequency sub-bands i.e. alpha, beta and alpha–beta bands. Three nonlinear features such as Higuchi fractal dimension, Petrosian fractal dimension and Detrended Fluctuation Analysis are calculated to prepare three feature vectors respective to each frequency sub-bands. Three machine learning techniques are used for vigilance level detection such as Support Vector Machine, Least Square-Support Vector Machine and Artificial Neural Network.