An improved multilayer perceptron based on wavelet approach for physical time series prediction

The real world datasets engage many challenges such as noisy data, periodic variations on several scales and long-term trends that do not vary periodically. Meanwhile, Neural Networks (NN) has been successfully applied in many problems in the domain of time series prediction. The standard NN a...

Full description

Saved in:

Bibliographic Details
Main Author:	Ali, Ashikin
Format:	Thesis
Language:	English English English
Published:	2014
Subjects:	QA76 Computer software
Online Access:	http://eprints.uthm.edu.my/1454/1/24p%20ASHIKIN%20ALI.pdf http://eprints.uthm.edu.my/1454/2/ASHIKIN%20ALI%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/1454/3/ASHIKIN%20ALI%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.1454
record_format	uketd_dc
spelling	my-uthm-ep.14542021-10-03T07:25:06Z An improved multilayer perceptron based on wavelet approach for physical time series prediction 2014-02 Ali, Ashikin QA76 Computer software The real world datasets engage many challenges such as noisy data, periodic variations on several scales and long-term trends that do not vary periodically. Meanwhile, Neural Networks (NN) has been successfully applied in many problems in the domain of time series prediction. The standard NN adopts computationally intensive training algorithms and can easily get trapped into local minima. To overcome such drawbacks in ordinary NN, this study focuses on using a wavelet technique as a filter at the pre-processing part of the ordinary NN. However, this study exposed towards an idea to develop a model called An Improved Multilayer Perceptron based on Wavelet Approach for Physical Time Series Prediction (W�MLP) to overcome such drawbacks of ordinary NN. W-MLP, a network model with a wavelet technique added in the network, is trained using the standard backpropagation gradient descent algorithm and tested with historical temperature, evaporation, humidity and wind direction data of Batu Pahat for 5-years-period (2005-2009) and earthquake data of North California for 4-years-period (1995-1998). Based on the obtained results, the proposed method W-MLP yields better performance compared to the existing filtering techniques. Therefore, it can be concluded that the proposed W-MLP can be an alternative mechanism to ordinary NN for a one-step-ahead prediction of those five events. 2014-02 Thesis http://eprints.uthm.edu.my/1454/ http://eprints.uthm.edu.my/1454/1/24p%20ASHIKIN%20ALI.pdf text en public http://eprints.uthm.edu.my/1454/2/ASHIKIN%20ALI%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/1454/3/ASHIKIN%20ALI%20WATERMARK.pdf text en validuser mphil masters Universiti Tun Hussein Onn Malaysia Fakulti Sains Komputer dan Teknologi Maklumat
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	QA76 Computer software
spellingShingle	QA76 Computer software Ali, Ashikin An improved multilayer perceptron based on wavelet approach for physical time series prediction
description	The real world datasets engage many challenges such as noisy data, periodic variations on several scales and long-term trends that do not vary periodically. Meanwhile, Neural Networks (NN) has been successfully applied in many problems in the domain of time series prediction. The standard NN adopts computationally intensive training algorithms and can easily get trapped into local minima. To overcome such drawbacks in ordinary NN, this study focuses on using a wavelet technique as a filter at the pre-processing part of the ordinary NN. However, this study exposed towards an idea to develop a model called An Improved Multilayer Perceptron based on Wavelet Approach for Physical Time Series Prediction (W�MLP) to overcome such drawbacks of ordinary NN. W-MLP, a network model with a wavelet technique added in the network, is trained using the standard backpropagation gradient descent algorithm and tested with historical temperature, evaporation, humidity and wind direction data of Batu Pahat for 5-years-period (2005-2009) and earthquake data of North California for 4-years-period (1995-1998). Based on the obtained results, the proposed method W-MLP yields better performance compared to the existing filtering techniques. Therefore, it can be concluded that the proposed W-MLP can be an alternative mechanism to ordinary NN for a one-step-ahead prediction of those five events.
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Ali, Ashikin
author_facet	Ali, Ashikin
author_sort	Ali, Ashikin
title	An improved multilayer perceptron based on wavelet approach for physical time series prediction
title_short	An improved multilayer perceptron based on wavelet approach for physical time series prediction
title_full	An improved multilayer perceptron based on wavelet approach for physical time series prediction
title_fullStr	An improved multilayer perceptron based on wavelet approach for physical time series prediction
title_full_unstemmed	An improved multilayer perceptron based on wavelet approach for physical time series prediction
title_sort	improved multilayer perceptron based on wavelet approach for physical time series prediction
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Fakulti Sains Komputer dan Teknologi Maklumat
publishDate	2014
url	http://eprints.uthm.edu.my/1454/1/24p%20ASHIKIN%20ALI.pdf http://eprints.uthm.edu.my/1454/2/ASHIKIN%20ALI%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/1454/3/ASHIKIN%20ALI%20WATERMARK.pdf
_version_	1747830793491709952

An improved multilayer perceptron based on wavelet approach for physical time series prediction

Similar Items