Investigating the Impact of Different Representations of Data on Neural Network and Regression

In this research the impact of different data representation on the performance of neural network and regression was investigated on different datasets that has binary or Boolean class target. In addition, the performance of particular predictive data mining model could be affected with the change o...

Full description

Saved in:

Bibliographic Details
Main Author:	Fallah, Ehab A. Omer El
Format:	Thesis
Language:	eng eng
Published:	2008
Subjects:	QA76 Computer software
Online Access:	https://etd.uum.edu.my/790/1/Ehab_A._Omer_El_Fallah.pdf https://etd.uum.edu.my/790/2/Ehab_A._Omer_El_Fallah.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uum-etd.790
record_format	uketd_dc
spelling	my-uum-etd.7902013-07-24T12:09:02Z Investigating the Impact of Different Representations of Data on Neural Network and Regression 2008-06 Fallah, Ehab A. Omer El College of Arts and Sciences (CAS) Graduate School QA76 Computer software In this research the impact of different data representation on the performance of neural network and regression was investigated on different datasets that has binary or Boolean class target. In addition, the performance of particular predictive data mining model could be affected with the change of data representation. The seven data representations that have been used in this research are As - Is, Min Max normalization, standard deviation normalization, sigmoidal normalization, thermometer representation, flag representation and simple binary representation. Moreover, all data representations have been applied on two datasets which are Wisconsin breast cancer and German credit dataset. As a result, the neural network performance is better than logistic regression on both datasets if we exclude the thermometer and flag representations. For datasets having a binary or Boolean target class, flag or thermometer binary representation is recommended to be used if logistic regression analysis is performed. Meanwhile, As-is representation, min max normalization, standard deviation normalization or sigmoidal normalization is recommended for neural network analysis on datasets having binary or Boolean target class. 2008-06 Thesis https://etd.uum.edu.my/790/ https://etd.uum.edu.my/790/1/Ehab_A._Omer_El_Fallah.pdf application/pdf eng validuser https://etd.uum.edu.my/790/2/Ehab_A._Omer_El_Fallah.pdf application/pdf eng public masters masters Universiti Utara Malaysia
institution	Universiti Utara Malaysia
collection	UUM ETD
language	eng eng
topic	QA76 Computer software
spellingShingle	QA76 Computer software Fallah, Ehab A. Omer El Investigating the Impact of Different Representations of Data on Neural Network and Regression
description	In this research the impact of different data representation on the performance of neural network and regression was investigated on different datasets that has binary or Boolean class target. In addition, the performance of particular predictive data mining model could be affected with the change of data representation. The seven data representations that have been used in this research are As - Is, Min Max normalization, standard deviation normalization, sigmoidal normalization, thermometer representation, flag representation and simple binary representation. Moreover, all data representations have been applied on two datasets which are Wisconsin breast cancer and German credit dataset. As a result, the neural network performance is better than logistic regression on both datasets if we exclude the thermometer and flag representations. For datasets having a binary or Boolean target class, flag or thermometer binary representation is recommended to be used if logistic regression analysis is performed. Meanwhile, As-is representation, min max normalization, standard deviation normalization or sigmoidal normalization is recommended for neural network analysis on datasets having binary or Boolean target class.
format	Thesis
qualification_name	masters
qualification_level	Master's degree
author	Fallah, Ehab A. Omer El
author_facet	Fallah, Ehab A. Omer El
author_sort	Fallah, Ehab A. Omer El
title	Investigating the Impact of Different Representations of Data on Neural Network and Regression
title_short	Investigating the Impact of Different Representations of Data on Neural Network and Regression
title_full	Investigating the Impact of Different Representations of Data on Neural Network and Regression
title_fullStr	Investigating the Impact of Different Representations of Data on Neural Network and Regression
title_full_unstemmed	Investigating the Impact of Different Representations of Data on Neural Network and Regression
title_sort	investigating the impact of different representations of data on neural network and regression
granting_institution	Universiti Utara Malaysia
granting_department	College of Arts and Sciences (CAS)
publishDate	2008
url	https://etd.uum.edu.my/790/1/Ehab_A._Omer_El_Fallah.pdf https://etd.uum.edu.my/790/2/Ehab_A._Omer_El_Fallah.pdf
_version_	1747826998612328448

Investigating the Impact of Different Representations of Data on Neural Network and Regression

Similar Items