fulltext.study @t Gmail

Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals

Paper ID Volume ID Publish Year Pages File Format Full-Text
5130 341 2016 7 PDF Available
Title
Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals
Abstract

Epilepsy is a neurological disorder affecting more than 50 million individuals in the world. Analysis of the electroencephalogram (EEG) is a powerful tool to assist neurologists for diagnosis and treatment. In this paper a new feature extraction method based on empirical mode decomposition (EMD) is proposed. The EEG signal is decomposed into intrinsic mode functions (IMFs) by the EMD algorithm and four statistical parameters are calculated over these IMFs constituting the input feature vector to be fed to a multilayer perceptron neural network (MLPNN) classifier. Experimental results carried out on the publicly available Bonn dataset show that an accurate classification rate of 100% is achieved in the discrimination between normal and ictal EEG, and an accuracy of 97.7% is reached in the classification of interictal and ictal EEG signals. Our results are equivalent or outperform recent studies published in the literature.

Keywords
Electroencephalogram (EEG); Seizure detection; Epilepsy; Empirical mode decomposition (EMD); Statistics; Artificial neural network (ANN)
First Page Preview
Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals
Publisher
Database: Elsevier - ScienceDirect
Journal: Biocybernetics and Biomedical Engineering - Volume 36, Issue 1, 2016, Pages 285–291
Authors
, , ,
Subjects
Physical Sciences and Engineering Chemical Engineering Bioengineering