Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation

A number of software effort estimations have attempted using statistical models, case based reasoning, and neural networks. The research results showed that the neural network models perform at least as well as the other approaches, so we selected the neural network model as the estimator. However,...

Full description

Saved in:
Bibliographic Details
Main Authors: JUN, Eung Sup, LEE, Jae Kyu
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2001
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/1154
http://dx.doi.org/10.1016/S0957-4174(01)00021-5
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-2153
record_format dspace
spelling sg-smu-ink.sis_research-21532010-12-22T08:24:06Z Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation JUN, Eung Sup LEE, Jae Kyu A number of software effort estimations have attempted using statistical models, case based reasoning, and neural networks. The research results showed that the neural network models perform at least as well as the other approaches, so we selected the neural network model as the estimator. However, since the computing environment changes so rapidly in terms of programming languages, development tools, and methodologies, it is very difficult to maintain the performance of estimation models for the new breed of projects. Therefore, we propose a search method that finds the right level of relevant cases for the neural network model. For the selected case set, the scale of the neural network model can be reduced by eliminating the qualitative input factors with the same values. Since there exist a multitude of combinations of case sets, we need to search for the optimal reduced neural network model and corresponding case set. To find the quasi-optimal model from the hierarchy of reduced neural network models, we adopted the beam search technique and devised the case-set selection algorithm. We have shown that the resulting model significantly outperforms the original full model for the software effort estimation. This approach can be also used for building any case-selective neural network. 2001-01-01T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/1154 info:doi/10.1016/S0957-4174(01)00021-5 http://dx.doi.org/10.1016/S0957-4174(01)00021-5 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Software effort estimation Reduced neural network model Case set hierarchy Beam search Sensitivity of beam width Case-set selection algorithm Computer Sciences Management Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Software effort estimation
Reduced neural network model
Case set hierarchy
Beam search
Sensitivity of beam width
Case-set selection algorithm
Computer Sciences
Management Information Systems
spellingShingle Software effort estimation
Reduced neural network model
Case set hierarchy
Beam search
Sensitivity of beam width
Case-set selection algorithm
Computer Sciences
Management Information Systems
JUN, Eung Sup
LEE, Jae Kyu
Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
description A number of software effort estimations have attempted using statistical models, case based reasoning, and neural networks. The research results showed that the neural network models perform at least as well as the other approaches, so we selected the neural network model as the estimator. However, since the computing environment changes so rapidly in terms of programming languages, development tools, and methodologies, it is very difficult to maintain the performance of estimation models for the new breed of projects. Therefore, we propose a search method that finds the right level of relevant cases for the neural network model. For the selected case set, the scale of the neural network model can be reduced by eliminating the qualitative input factors with the same values. Since there exist a multitude of combinations of case sets, we need to search for the optimal reduced neural network model and corresponding case set. To find the quasi-optimal model from the hierarchy of reduced neural network models, we adopted the beam search technique and devised the case-set selection algorithm. We have shown that the resulting model significantly outperforms the original full model for the software effort estimation. This approach can be also used for building any case-selective neural network.
format text
author JUN, Eung Sup
LEE, Jae Kyu
author_facet JUN, Eung Sup
LEE, Jae Kyu
author_sort JUN, Eung Sup
title Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
title_short Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
title_full Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
title_fullStr Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
title_full_unstemmed Quasi-Optimal Case-Selective Neural Network Model for Software Effort Estimation
title_sort quasi-optimal case-selective neural network model for software effort estimation
publisher Institutional Knowledge at Singapore Management University
publishDate 2001
url https://ink.library.smu.edu.sg/sis_research/1154
http://dx.doi.org/10.1016/S0957-4174(01)00021-5
_version_ 1770570880405995520