Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function

Software cost estimation is a complex and critical issue in software industry but it is an inevitable activity in the software development process. It is one of important factors for projects failure due to the ambiguity and uncertainty of software attributes at the early stages of software devel...

Full description

Saved in:

Bibliographic Details
Main Author:	Abdulaziz Al-Shalif, Sarah Abdulkarem
Format:	Thesis
Language:	English English English
Published:	2017
Subjects:	TK7800-8360 Electronics
Online Access:	http://eprints.uthm.edu.my/859/1/24p%20SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF.pdf http://eprints.uthm.edu.my/859/2/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/859/3/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.859
record_format	uketd_dc
spelling	my-uthm-ep.8592021-09-06T05:41:46Z Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function 2017 Abdulaziz Al-Shalif, Sarah Abdulkarem TK7800-8360 Electronics Software cost estimation is a complex and critical issue in software industry but it is an inevitable activity in the software development process. It is one of important factors for projects failure due to the ambiguity and uncertainty of software attributes at the early stages of software development. The estimation of effort in COCOMO II depends on several software attributes namely software size (SS), scale factors (SFs) and effort multipliers (EMs). Several researchers integrate COCOMO II with Artificial Neural Network (ANN) to overcome the ambiguous and uncertain of these attributes. However, ANN contributes to slow convergence caused by sigmoid function. Thus, this research proposes Hyperbolic Tangent activation function (Tanh) to be used in the hidden layer of the ANN architecture to produce faster convergence. Back-propagation learning algorithm is applied to the multilayer neural network for training and testing. The proposed activation function has been trained and tested using two different architectures of NN which are basic COCOMO II-NN and modified COCOMO II-NN that uses COCOMO II NASA93 dataset. The result has been compared to different activation functions namely Uni-polar sigmoid, Bi-polar sigmoid, Gaussian and Softsign. The experiment results indicate that Tanh with modified COCOMO II-NN architecture achieved 23.2780 % Mean Magnitude Relative Error (MMRE) for 19 testing projects and 9.8948 % MMRE for 9 testing projects which is the lowest MMRE among other activation functions. In conclusion, Tanh with modified architecture of COCOMO II-NN provides much better estimation results than other methods and can lead to improvement of software estimates. 2017 Thesis http://eprints.uthm.edu.my/859/ http://eprints.uthm.edu.my/859/1/24p%20SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF.pdf text en public http://eprints.uthm.edu.my/859/2/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/859/3/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%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	TK7800-8360 Electronics
spellingShingle	TK7800-8360 Electronics Abdulaziz Al-Shalif, Sarah Abdulkarem Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
description	Software cost estimation is a complex and critical issue in software industry but it is an inevitable activity in the software development process. It is one of important factors for projects failure due to the ambiguity and uncertainty of software attributes at the early stages of software development. The estimation of effort in COCOMO II depends on several software attributes namely software size (SS), scale factors (SFs) and effort multipliers (EMs). Several researchers integrate COCOMO II with Artificial Neural Network (ANN) to overcome the ambiguous and uncertain of these attributes. However, ANN contributes to slow convergence caused by sigmoid function. Thus, this research proposes Hyperbolic Tangent activation function (Tanh) to be used in the hidden layer of the ANN architecture to produce faster convergence. Back-propagation learning algorithm is applied to the multilayer neural network for training and testing. The proposed activation function has been trained and tested using two different architectures of NN which are basic COCOMO II-NN and modified COCOMO II-NN that uses COCOMO II NASA93 dataset. The result has been compared to different activation functions namely Uni-polar sigmoid, Bi-polar sigmoid, Gaussian and Softsign. The experiment results indicate that Tanh with modified COCOMO II-NN architecture achieved 23.2780 % Mean Magnitude Relative Error (MMRE) for 19 testing projects and 9.8948 % MMRE for 9 testing projects which is the lowest MMRE among other activation functions. In conclusion, Tanh with modified architecture of COCOMO II-NN provides much better estimation results than other methods and can lead to improvement of software estimates.
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Abdulaziz Al-Shalif, Sarah Abdulkarem
author_facet	Abdulaziz Al-Shalif, Sarah Abdulkarem
author_sort	Abdulaziz Al-Shalif, Sarah Abdulkarem
title	Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
title_short	Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
title_full	Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
title_fullStr	Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
title_full_unstemmed	Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
title_sort	improving modified cocomo ii artificial neural network using hyperbolic tangent activation function
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Fakulti Sains Komputer dan Teknologi Maklumat
publishDate	2017
url	http://eprints.uthm.edu.my/859/1/24p%20SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF.pdf http://eprints.uthm.edu.my/859/2/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/859/3/SARAH%20ABDULKAREM%20ABDULAZIZ%20AL-SHALIF%20WATERMARK.pdf
_version_	1747830695656423424

Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function

Similar Items