Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data

Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, in order to improve the predictive capability of WNNs, the types of activation functions used in the hidden layer of the WNN were varied. The modified WNNs were then appl...

Full description

Bibliographic Details
Main Authors: Zainuddin, Zarita, Pauline, Ong
Format: Article
Language:English
Published: Elsevier 2011
Subjects:
Online Access:http://eprints.uthm.edu.my/4220/
http://eprints.uthm.edu.my/4220/1/AJ%202017%20%28582%29.pdf
_version_ 1848888228210278400
author Zainuddin, Zarita
Pauline, Ong
author_facet Zainuddin, Zarita
Pauline, Ong
author_sort Zainuddin, Zarita
building UTHM Institutional Repository
collection Online Access
description Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, in order to improve the predictive capability of WNNs, the types of activation functions used in the hidden layer of the WNN were varied. The modified WNNs were then applied in approximating a benchmark piecewise function. Subsequently, performance comparisons with other developed methods in studying the same benchmark function were made. An assessment analysis showed that this proposed approach outperformed the rest. The efficiency of the modified WNNs was explored through a real-world application problem-specifically, the prediction of time-series pollution data at Texas of United States. The comparative experimental results showed that integrating different wavelet families into the hidden layer of WNNs leads to superior performance
first_indexed 2025-11-15T20:06:57Z
format Article
id uthm-4220
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:06:57Z
publishDate 2011
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling uthm-42202021-12-01T06:12:19Z http://eprints.uthm.edu.my/4220/ Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data Zainuddin, Zarita Pauline, Ong TK7800-8360 Electronics Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, in order to improve the predictive capability of WNNs, the types of activation functions used in the hidden layer of the WNN were varied. The modified WNNs were then applied in approximating a benchmark piecewise function. Subsequently, performance comparisons with other developed methods in studying the same benchmark function were made. An assessment analysis showed that this proposed approach outperformed the rest. The efficiency of the modified WNNs was explored through a real-world application problem-specifically, the prediction of time-series pollution data at Texas of United States. The comparative experimental results showed that integrating different wavelet families into the hidden layer of WNNs leads to superior performance Elsevier 2011 Article PeerReviewed text en http://eprints.uthm.edu.my/4220/1/AJ%202017%20%28582%29.pdf Zainuddin, Zarita and Pauline, Ong (2011) Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data. Applied Soft Computing, 11 (8). pp. 4866-4874. ISSN 1568-4946 https://dx.doi.org/10.1016/j.asoc.2011.06.013
spellingShingle TK7800-8360 Electronics
Zainuddin, Zarita
Pauline, Ong
Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title_full Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title_fullStr Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title_full_unstemmed Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title_short Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
title_sort modified wavelet neural network in function approximation and its application in prediction of time-series pollution data
topic TK7800-8360 Electronics
url http://eprints.uthm.edu.my/4220/
http://eprints.uthm.edu.my/4220/
http://eprints.uthm.edu.my/4220/1/AJ%202017%20%28582%29.pdf