• Apr 24, 2017 News! Vol.6, No.4 has been indexed by EI (Inspec).   [Click]
  • Apr 24, 2017 News! Vol.6, No.3 has been indexed by EI (Inspec).   [Click]
  • Jun 26, 2017 News!Vol 7, No 4 has been published with online version 12 original aritcles from 6 countries are published in this issue   [Click]
General Information
    • ISSN: 2010-3697
    • Frequency: Bimonthly
    • DOI: 10.7763/IJMO
    • Editor-in-Chief: Prof. Adrian Olaru
    • Executive Editor: Ms.Yoyo Y. Zhou
    • Abstracting/ Indexing: Engineering & Technology Digital Library, ProQuest, Crossref, Electronic Journals Library, Google Scholar, EI (INSPEC, IET).
    • E-mail ijmo@iacsitp.com
Editor-in-chief
Prof. Adrian Olaru
University Politehnica of Bucharest, Romania
I'm happy to take on the position of editor in chief of IJMO. It's a journal that shows promise of becoming a recognized journal in the area of modelling and optimization. I'll work together with the editors to help it progress.
IJMO 2015 Vol.5(2): 90-97 ISSN: 2010-3697
DOI: 10.7763/IJMO.2015.V5.442

An Enhanced Wavelet Neural Network Model with Metaheuristic Harmony Search Algorithm for Epileptic Seizure Prediction

Zarita Zainuddin, Kee Huong Lai, and Pauline Ong
Abstract—The task of epileptic seizure prediction aims at differentiating between two classes of electroencephalography (EEG) signals, namely interictal and pre-ictal signals. The development of an automated classifier that is capable of performing such task with high sensitivity and low false positive rate is of paramount importance, as such classifier will improve the quality of life of patients diagnosed with epilepsy. In this paper, an enhanced wavelet neural network (WNN) model is proposed by incorporating the metaheuristic harmony search (HS) algorithm. The enhancement is accomplished via two modifications to the standard WNN model. First, a binary version of the HS algorithm is employed in the stage of feature selection, which aims at selecting the most optimal subset of input features for the WNN model during the preprocessing stage. Second, the HS algorithm is used to determine the best translation vectors for the hidden nodes of the WNN model. The simulation performed on the benchmark Freiburg dataset reported an average sensitivity of 85.55% and an average false positive rate of 0.22 per hour. It was found that the WNN model that gave the best performance is the one that employs the HS algorithm, in both feature selection and clustering stages. The satisfactory values of sensitivity and false positive rate obtained demonstrate the effectiveness of the proposed model for predicting the occurrence of impending seizures.

Index Terms—Epileptic seizure prediction, harmony search, feature selection, clustering, wavelet neural networks.

Zarita Zainuddin and Kee Huong Lai are with the School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang, Malaysia (e-mail: zarita@cs.usm.my, laikeehuong1986@yahoo.com).
Pauline Ong is with Faculty of Mechanical and Manufacturing Engineering, Universiti Tun Hussein Onn Malaysia, 86400 Parit Raja, Batu Pahat, Johor, Malaysia (e-mail: ongp@uthm.edu.my).

[PDF]

Cite: Zarita Zainuddin, Kee Huong Lai, and Pauline Ong, "An Enhanced Wavelet Neural Network Model with Metaheuristic Harmony Search Algorithm for Epileptic Seizure Prediction," International Journal of Modeling and Optimization vol. 5, no. 2, pp. 90-97, 2015.

Copyright © 2008-2015.International Journal of Modeling and Optimization. All rights reserved.
E-mail: ijmo@iacsitp.com