A harmony search-based learning algorithm for epileptic seizure prediction

The learning phase of wavelet neural network entails the task of finding the optimal set of parameter, which includes wavelet activation function, translation centers, dilation parameter, synaptic weight values, and bias terms. Apart from the traditional gradient descent-based approach, metaheuristi...

Full description

Bibliographic Details
Main Authors: Kee, Huong Lai, Zainuddin, Zarita, Ong, Pauline
Format: Article
Language:English
Published: Institute of Research and Journals 2016
Subjects:
Online Access:http://eprints.uthm.edu.my/5275/
http://eprints.uthm.edu.my/5275/1/AJ%202017%20%28747%29.pdf
_version_ 1848888510721818624
author Kee, Huong Lai
Zainuddin, Zarita
Ong, Pauline
author_facet Kee, Huong Lai
Zainuddin, Zarita
Ong, Pauline
author_sort Kee, Huong Lai
building UTHM Institutional Repository
collection Online Access
description The learning phase of wavelet neural network entails the task of finding the optimal set of parameter, which includes wavelet activation function, translation centers, dilation parameter, synaptic weight values, and bias terms. Apart from the traditional gradient descent-based approach, metaheuristic algorithms can also be used to determine these parameters. In this work, the harmony search algorithm is employed to find the optimal solution for both synaptic weight values and bias terms in the learning of wavelet neural network. The standard harmony search algorithm is modified accordingly in the aspect of initialization of harmony memory, as well as during the improvisation stage. The proposed harmony search-based learning algorithm is used in the task of epileptic seizure prediction. Simulation results show that the proposed algorithm outperforms other metaheuristic algorithms in terms of sensitivity.
first_indexed 2025-11-15T20:11:26Z
format Article
id uthm-5275
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:11:26Z
publishDate 2016
publisher Institute of Research and Journals
recordtype eprints
repository_type Digital Repository
spelling uthm-52752022-01-06T08:29:47Z http://eprints.uthm.edu.my/5275/ A harmony search-based learning algorithm for epileptic seizure prediction Kee, Huong Lai Zainuddin, Zarita Ong, Pauline TS Manufactures TK7800-8360 Electronics The learning phase of wavelet neural network entails the task of finding the optimal set of parameter, which includes wavelet activation function, translation centers, dilation parameter, synaptic weight values, and bias terms. Apart from the traditional gradient descent-based approach, metaheuristic algorithms can also be used to determine these parameters. In this work, the harmony search algorithm is employed to find the optimal solution for both synaptic weight values and bias terms in the learning of wavelet neural network. The standard harmony search algorithm is modified accordingly in the aspect of initialization of harmony memory, as well as during the improvisation stage. The proposed harmony search-based learning algorithm is used in the task of epileptic seizure prediction. Simulation results show that the proposed algorithm outperforms other metaheuristic algorithms in terms of sensitivity. Institute of Research and Journals 2016 Article PeerReviewed text en http://eprints.uthm.edu.my/5275/1/AJ%202017%20%28747%29.pdf Kee, Huong Lai and Zainuddin, Zarita and Ong, Pauline (2016) A harmony search-based learning algorithm for epileptic seizure prediction. International Journal of Management and Applied Science, 2 (12). pp. 164-169. ISSN 2394-7926
spellingShingle TS Manufactures
TK7800-8360 Electronics
Kee, Huong Lai
Zainuddin, Zarita
Ong, Pauline
A harmony search-based learning algorithm for epileptic seizure prediction
title A harmony search-based learning algorithm for epileptic seizure prediction
title_full A harmony search-based learning algorithm for epileptic seizure prediction
title_fullStr A harmony search-based learning algorithm for epileptic seizure prediction
title_full_unstemmed A harmony search-based learning algorithm for epileptic seizure prediction
title_short A harmony search-based learning algorithm for epileptic seizure prediction
title_sort harmony search-based learning algorithm for epileptic seizure prediction
topic TS Manufactures
TK7800-8360 Electronics
url http://eprints.uthm.edu.my/5275/
http://eprints.uthm.edu.my/5275/1/AJ%202017%20%28747%29.pdf