Effect of Wavelet Packet Log Energy Entropy on Electroencephalogram (EEG) Signals

Effect of Wavelet Packet Log Energy Entropy on Electroencephalogram (EEG) Signals

S. Raghu (Center for Medical Electronics and Computing, M.S. Ramaiah Institute of Technology and Christ University, Bangalore, India), N. Sriraam (Center for Medical Electronics and Computing, M.S. Ramaiah Institute of Technology, Bangalore, India) and G. Pradeep Kumar (Department of ECE, Christ University, Bangalore, India)
Copyright: © 2015 |Pages: 12
DOI: 10.4018/IJBCE.2015010103
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The scaling behavior of human electroencephalogram (EEG) signals is well exploited by appropriate extraction of time – frequency domain and entropy based features. Such measurable inherently helps understanding the neurophysiological phenomenon of brain as well as its associated cortical activities. Being a non-linear time series, EEG's are assumed to be fragment of fluctuations. Several attempts have been made to study the EEG signals for clinical applications such as epileptic seizure detection, evoked response potential recognition, tumor detection, identification of alcoholics and so on. In all such applications appropriate selection of feature parameter plays an important role in discriminating normal EEG from abnormal. In the recent past one can find the importance of wavelet and wavelet packet towards EEG analysis. This proposed research work investigates the effect of wavelet packet log energy entropy on EEG signals. Entropy being the measure of relative information, the proposed study attempts to discriminate the normal EEGs from abnormal EEG's by employing the log energy entropy features. For better brevity, this study restricts to the analysis of epileptic seizure from normal EEGs. Different decomposition levels from 2 to 5 were considered for wavelet packets with application of Haar, rbio3.1, sym7, dmey wavelets. A one second windowing was introduced for the data segmentation and Shannon's log energy entropy was estimated. Then the statistical non-parametric Wilcoxon model was employed. The result shows that the application of wavelet packet log energy entropy found to be a potential indicator for discriminating epileptic seizure from normal.
Article Preview

Several works have been reported related to wavelet decomposition and entropy. Srinivasan et al. (2007) have used Approximate Entropy (ApEn), for detection of epilepsy using artificial neural networks. Data points of different frame sizes 173,256, 512, 1024 and 2048 were used to achieve an overall accuracy of 93.5% - 100% (Srinivasan et al. 2007). Yatindra Kumar et al. (2014) proposed a scheme for detecting epileptic seizures from EEG data recorded from normal subjects and epileptic patients. This method works based on discrete wavelet transforms (DWT) analysis and approximate entropy (ApEn) of EEG signals. EEG signals were decomposed by DWT to calculate approximation and detail coefficients, then ApEn values of the approximation and detail coefficients were calculated. Significant differences have been found between the ApEn values of the epileptic and the normal EEG to detect seizures with 100% classification accuracy using artificial neural network (Yatindra Kumar et al. 2014). Guo et al. (2010) decompose original EEG signal first into several sub bands through four-level multi wavelet transform and then calculated ApEn feature to classify the EEGs using three-layer MLPNN with Bayesian regularization back-propagation training algorithms (Guo et al., 2010).

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