Statistical Analysis of Spectral Entropy Features for the Detection of Alcoholics Based on Elecroencephalogram (EEG) Signals

Statistical Analysis of Spectral Entropy Features for the Detection of Alcoholics Based on Elecroencephalogram (EEG) Signals

T.K. Padma Shri (SCSVMV University, Kanchi, Tamil Nadu, India & Department of ECE, Manipal Institute of Technology, Manipal, Karnataka, India) and N. Sriraam (Center for Medical Electronics and Computing, Department of Medical Electronics, M S Ramaiah Institute of Technology, Bangalore, Karnataka, India)
Copyright: © 2012 |Pages: 8
DOI: 10.4018/ijbce.2012070104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

EEG happens to be an important tool for brain study providing a non- invasive and cost effective method to detect the effects of alcohol on the human brain. This paper highlights the importance of statistical analysis to determine the usefulness of spectral entropy features for discriminating alcoholics from healthy subjects. The open source EEG database consisting of 10 alcoholic and 10 control subjects recordings under visual stimulus is considered for the study. The EEG signal is preprocessed to remove eye blink artefact using independent component analysis (ICA) and the gamma sub band is extracted by using an elliptic band pass filter to obtain the visually evoked pattern (VEP) signal. The spectral entropy (SEN) coefficients are computed on all the 61 VEP signals of each subject. To obtain a statistical measure of SEN coefficients suitability for classifying the alcoholic EEG, ANOVA tests are performed. Results show that the test exhibits interesting observations in the form of p-value <0.05 (accepted significance level) for most of the channels and p-value >0.05 for the remaining channels. This study may help in identifying those significant channels (p<0.05) which contribute to the classification of both the groups.
Article Preview

2. Method

2.1. EEG Dataset

The EEG dataset used in the proposed study is from an open EEG database of State University of New York Health Centre. This data arises from a large number of studies to examine EEG correlates of genetic predisposition to alcoholism. It contains measurements from 64electrodes placed on subject's scalps which were sampled at 256 Hz. For further details, refer to http://kdd.ics.uci.edu/databases.

2.2. Artifact Removal & Preprocessing

The eye blink artefact produces voltages >100μV in the EEG recordings (Palaniappan et al., 2006). These artefacts are removed by applying ICA(Independent Component Analysis).The gamma sub band signals between 30-50 Hz are extracted by passing the artifact free EEG signal through an elliptic band pass filter. The gamma band signal of 2 minutes EEG data for both alcoholic and control subjects are as shown in Figures 1 and 2.

Figure 1.

Sample plot of VEP (gamma band) signal of alcoholic subject

Figure 2.

Sample plot of VEP (gamma band) signal of control subjects

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 6: 2 Issues (2017)
Volume 5: 2 Issues (2016)
Volume 4: 2 Issues (2015)
Volume 3: 2 Issues (2014)
Volume 2: 2 Issues (2013)
Volume 1: 2 Issues (2012)
View Complete Journal Contents Listing