Optimization based machine learning algorithms for software reliability growth models

Software reliability is a critical factor for system performance and safety, especially in defense industries, where operational failures can have severe consequences. To evaluate and improve software reliability, Software Reliability Growth Models (SRGMs) are widely used. However, many previous st...

Full description

Saved in:
Bibliographic Details
Main Authors: Myeongguen Shin, Juwon Jung, Jihyun Lee, Insoo Ryu, Sanggun Park
Format: Article
Language:English
Published: Institute of Defense Acquisition Program 2025-05-01
Series:선진국방연구
Subjects:
Online Access:https://journal.idap.re.kr/index.php/JAMS/article/view/275
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850112800829997056
author Myeongguen Shin
Juwon Jung
Jihyun Lee
Insoo Ryu
Sanggun Park
author_facet Myeongguen Shin
Juwon Jung
Jihyun Lee
Insoo Ryu
Sanggun Park
author_sort Myeongguen Shin
collection DOAJ
description Software reliability is a critical factor for system performance and safety, especially in defense industries, where operational failures can have severe consequences. To evaluate and improve software reliability, Software Reliability Growth Models (SRGMs) are widely used. However, many previous studies have relied on single optimization methods or deep learning approaches, which are prone to local optima and extrapolation issues, reducing prediction accuracy. To fill this gap, current study employs a broader range of optimization algorithms based on the Least Squares Method (LSM) and Maximum Likelihood Estimation (MLE) to approximate global optima. NASA’s Jet Propulsion Laboratory (JPL) software defect datasets were used, and several widely recognized SRGM models, including Goel-Okumoto, Delayed S-Shape, Inflection S-Shape, Weibull, and Log-Logistic, were evaluated. Experimental results show that the choice of optimization method significantly affects prediction performance, as measured by Mean Squared Error (MSE). For example, in the J2 dataset, the Weibull model exhibited MSE values ranging from 70.778 to 15,767.68—a 222-fold difference—demonstrating the critical role of optimization in prediction accuracy. The findings confirm the risks of relying solely on single-method approaches and highlight the value of diverse optimization strategies for achieving near-global optima. The study presents a practical framework for improving software reliability assessments, contributing to the development of highly reliable software for the defense industry.
format Article
id doaj-art-e9242eadcf264f25b5af7f53237fdc43
institution OA Journals
issn 2635-5531
2636-1329
language English
publishDate 2025-05-01
publisher Institute of Defense Acquisition Program
record_format Article
series 선진국방연구
spelling doaj-art-e9242eadcf264f25b5af7f53237fdc432025-08-20T02:37:17ZengInstitute of Defense Acquisition Program선진국방연구2635-55312636-13292025-05-0181Optimization based machine learning algorithms for software reliability growth modelsMyeongguen Shin0Juwon Jung1Jihyun Lee2Insoo Ryu3Sanggun Park4MOASOFT Co., Ltd., KoreaMOASOFT Co., Ltd., KoreaMOASOFT Co., Ltd., KoreaMOASOFT Co., Ltd., KoreaMOASOFT Co., Ltd., Korea Software reliability is a critical factor for system performance and safety, especially in defense industries, where operational failures can have severe consequences. To evaluate and improve software reliability, Software Reliability Growth Models (SRGMs) are widely used. However, many previous studies have relied on single optimization methods or deep learning approaches, which are prone to local optima and extrapolation issues, reducing prediction accuracy. To fill this gap, current study employs a broader range of optimization algorithms based on the Least Squares Method (LSM) and Maximum Likelihood Estimation (MLE) to approximate global optima. NASA’s Jet Propulsion Laboratory (JPL) software defect datasets were used, and several widely recognized SRGM models, including Goel-Okumoto, Delayed S-Shape, Inflection S-Shape, Weibull, and Log-Logistic, were evaluated. Experimental results show that the choice of optimization method significantly affects prediction performance, as measured by Mean Squared Error (MSE). For example, in the J2 dataset, the Weibull model exhibited MSE values ranging from 70.778 to 15,767.68—a 222-fold difference—demonstrating the critical role of optimization in prediction accuracy. The findings confirm the risks of relying solely on single-method approaches and highlight the value of diverse optimization strategies for achieving near-global optima. The study presents a practical framework for improving software reliability assessments, contributing to the development of highly reliable software for the defense industry. https://journal.idap.re.kr/index.php/JAMS/article/view/275software reliabilitysoftware reliability growth modelartificial intelligence optimizationmachine learning
spellingShingle Myeongguen Shin
Juwon Jung
Jihyun Lee
Insoo Ryu
Sanggun Park
Optimization based machine learning algorithms for software reliability growth models
선진국방연구
software reliability
software reliability growth model
artificial intelligence optimization
machine learning
title Optimization based machine learning algorithms for software reliability growth models
title_full Optimization based machine learning algorithms for software reliability growth models
title_fullStr Optimization based machine learning algorithms for software reliability growth models
title_full_unstemmed Optimization based machine learning algorithms for software reliability growth models
title_short Optimization based machine learning algorithms for software reliability growth models
title_sort optimization based machine learning algorithms for software reliability growth models
topic software reliability
software reliability growth model
artificial intelligence optimization
machine learning
url https://journal.idap.re.kr/index.php/JAMS/article/view/275
work_keys_str_mv AT myeongguenshin optimizationbasedmachinelearningalgorithmsforsoftwarereliabilitygrowthmodels
AT juwonjung optimizationbasedmachinelearningalgorithmsforsoftwarereliabilitygrowthmodels
AT jihyunlee optimizationbasedmachinelearningalgorithmsforsoftwarereliabilitygrowthmodels
AT insooryu optimizationbasedmachinelearningalgorithmsforsoftwarereliabilitygrowthmodels
AT sanggunpark optimizationbasedmachinelearningalgorithmsforsoftwarereliabilitygrowthmodels