Optimized Feature Selection for Enhanced Epileptic Seizure Detection

ISSN: 1875-6603 (Online)
ISSN: 1573-4056 (Print)


Volume 10, 4 Issues, 2014


Download PDF Flyer




Current Medical Imaging Reviews

Aims & ScopeAbstracted/Indexed in

Ranking and Category:
  • 114th of 120 in Radiology, Nuclear Medicine & Medical Imaging

Submit Abstracts Online Submit Manuscripts Online

Editor-in-Chief:
E. Edmund Kim
Professor of Diagnostic Radiology University of California
Irvine, CA
USA


View Full Editorial Board

Subscribe Purchase Articles Order Reprints

Current: 0.429
5 - Year: 0.665

Optimized Feature Selection for Enhanced Epileptic Seizure Detection

Author(s): Krishnakumar Sivasankari, Keppana Gowder Thanushkodi and Nambiraj Suguna

Affiliation: Anna University of Technology, Coimbatore, India.

Abstract

Genetic algorithm (GA) based feature selection method is an evolving search heuristic, used to provide solutions to optimization problems. Feature selection is an important aspect that improves classification accuracy. The main objective of this work is to utilize GA for feature selection by integrating it with a bank of multi-class Support Vector Machine (SVM) for identification of the effective feature set. The proposed GA based approach finds its application in epileptic seizure detection. EEG dataset containing artefacts and noise were removed by employing constrained Independent Component Analysis (cICA) and Stationary Wavelet Transform (SWT). The features of the input data are constructed in the form of feature vector by FastICA technique. The fitness calculation for the selection of individuals in the GA is calculated by a Linear Discriminant Analysis (LDA) classifier. The multi-class Support Vector Machine (SVM) (one-against-all) classifier is used for the validation of the selected features. The samples are taken from 948 patients and the classes are divided as normal, seizure, and seizure-free using artificial neural networks. Experimental results shows that the GA - multi-SVM feature selection technique can achieve higher accuracies as compared to the case without feature selection.

Keywords: EEG (Electroencephalogram), Electrocardiogram (EKG), Electromyogram (EMG), EOG (Electro-oculogram), Genetic Algorithm (GA), Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM).

Download Free Rights and Permissions

Article Details

Volume: 10
Issue Number: 1
First Page: 35
Last Page: 47
Page Count: 13
DOI: 10.2174/157340561001140424143814
Advertisement

Related Journals




Webmaster Contact: urooj@benthamscience.org Copyright © 2014 Bentham Science