The effect of pre-processing techniques and optimal parameters on BPNN for data classification

The architecture of artificial neural network (ANN) laid the foundation as a powerful technique in handling problems such as pattern recognition and data analysis. It’s data-driven, self-adaptive, and non-linear capabilities channel it for use in processing at high speed and ability to learn the sol...

Full description

Saved in:

Bibliographic Details
Main Author:	HUSSEIN, AMEER SALEH
Format:	Thesis
Language:	English English English
Published:	2015
Subjects:	QA76 Computer software
Online Access:	http://eprints.uthm.edu.my/1294/2/AMEER%20SALEH%20HUSSEIN%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/1294/1/24p%20AMEER%20SALEH%20HUSSEIN.pdf http://eprints.uthm.edu.my/1294/3/AMEER%20SALEH%20HUSSEIN%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.1294
record_format	uketd_dc
spelling	my-uthm-ep.12942021-10-03T06:13:29Z The effect of pre-processing techniques and optimal parameters on BPNN for data classification 2015-02 HUSSEIN, AMEER SALEH QA76 Computer software The architecture of artificial neural network (ANN) laid the foundation as a powerful technique in handling problems such as pattern recognition and data analysis. It’s data-driven, self-adaptive, and non-linear capabilities channel it for use in processing at high speed and ability to learn the solution to a problem from a set of examples. It has been adequately applied in areas such as medical, financial, economy, and engineering. Neural network training has been a dynamic area of research, with the Multi-Layer Perceptron (MLP) trained with back propagation (BP) mostly worked on by various researchers. However, this algorithm is prone to have difficulties such as local minimum which are caused by neuron saturation in the hidden layer. Most existing approaches modify the learning model in order to add a random factor to the model which can help to overcome the tendency to sink into local minima. However, the random perturbations of the search direction and various kinds of stochastic adjustment to the current set of weights are not effective in enabling a network to escape from local minimum within a reasonable number of iterations. In this research, a performance analysis based on different activation functions; gradient descent and gradient descent with momentum, for training the BP algorithm with pre-processing techniques was executed. The Min-Max, Z-Score, and Decimal Scaling Normalization pre-processing techniques were analyzed. Results generated from the simulations reveal that the pre-processing techniques greatly increased the ANN convergence with Z-Score producing the best performance on all datasets by reaching up to 97.99%, 95.41% and 96.36% accuracy. 2015-02 Thesis http://eprints.uthm.edu.my/1294/ http://eprints.uthm.edu.my/1294/2/AMEER%20SALEH%20HUSSEIN%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/1294/1/24p%20AMEER%20SALEH%20HUSSEIN.pdf text en public http://eprints.uthm.edu.my/1294/3/AMEER%20SALEH%20HUSSEIN%20WATERMARK.pdf text en validuser mphil masters Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	QA76 Computer software
spellingShingle	QA76 Computer software HUSSEIN, AMEER SALEH The effect of pre-processing techniques and optimal parameters on BPNN for data classification
description	The architecture of artificial neural network (ANN) laid the foundation as a powerful technique in handling problems such as pattern recognition and data analysis. It’s data-driven, self-adaptive, and non-linear capabilities channel it for use in processing at high speed and ability to learn the solution to a problem from a set of examples. It has been adequately applied in areas such as medical, financial, economy, and engineering. Neural network training has been a dynamic area of research, with the Multi-Layer Perceptron (MLP) trained with back propagation (BP) mostly worked on by various researchers. However, this algorithm is prone to have difficulties such as local minimum which are caused by neuron saturation in the hidden layer. Most existing approaches modify the learning model in order to add a random factor to the model which can help to overcome the tendency to sink into local minima. However, the random perturbations of the search direction and various kinds of stochastic adjustment to the current set of weights are not effective in enabling a network to escape from local minimum within a reasonable number of iterations. In this research, a performance analysis based on different activation functions; gradient descent and gradient descent with momentum, for training the BP algorithm with pre-processing techniques was executed. The Min-Max, Z-Score, and Decimal Scaling Normalization pre-processing techniques were analyzed. Results generated from the simulations reveal that the pre-processing techniques greatly increased the ANN convergence with Z-Score producing the best performance on all datasets by reaching up to 97.99%, 95.41% and 96.36% accuracy.
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	HUSSEIN, AMEER SALEH
author_facet	HUSSEIN, AMEER SALEH
author_sort	HUSSEIN, AMEER SALEH
title	The effect of pre-processing techniques and optimal parameters on BPNN for data classification
title_short	The effect of pre-processing techniques and optimal parameters on BPNN for data classification
title_full	The effect of pre-processing techniques and optimal parameters on BPNN for data classification
title_fullStr	The effect of pre-processing techniques and optimal parameters on BPNN for data classification
title_full_unstemmed	The effect of pre-processing techniques and optimal parameters on BPNN for data classification
title_sort	effect of pre-processing techniques and optimal parameters on bpnn for data classification
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Faculty of Computer Science and Information Technology
publishDate	2015
url	http://eprints.uthm.edu.my/1294/2/AMEER%20SALEH%20HUSSEIN%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/1294/1/24p%20AMEER%20SALEH%20HUSSEIN.pdf http://eprints.uthm.edu.my/1294/3/AMEER%20SALEH%20HUSSEIN%20WATERMARK.pdf
_version_	1747830764830982144

The effect of pre-processing techniques and optimal parameters on BPNN for data classification

Similar Items