Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering

Software reliability is an essential characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development pha...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kyawt Kyawt San, Hironori Washizaki, Yoshiaki Fukazawa, Kiyoshi Honda, Masahiro Taga, Akira Matsuzaki
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/3b8cfe7004ee41788bbe8bc1602e1a4d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3b8cfe7004ee41788bbe8bc1602e1a4d
record_format dspace
spelling oai:doaj.org-article:3b8cfe7004ee41788bbe8bc1602e1a4d2021-11-25T18:17:23ZDeep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering10.3390/math92229452227-7390https://doaj.org/article/3b8cfe7004ee41788bbe8bc1602e1a4d2021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2945https://doaj.org/toc/2227-7390Software reliability is an essential characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development phases, applying traditional software reliability growth models (SRGMs) with limited past data does not always provide reliable prediction result for decision making. To overcome this, herein, we propose a new software reliability modeling method called a deep cross-project software reliability growth model (DC-SRGM). DC-SRGM is a cross-project prediction method that uses features of previous projects’ data through project similarity. Specifically, the proposed method applies cluster-based project selection for the training data source and modeling by a deep learning method. Experiments involving 15 real datasets from a company and 11 open source software datasets show that DC-SRGM can more precisely describe the reliability of ongoing development projects than existing traditional SRGMs and the LSTM model.Kyawt Kyawt SanHironori WashizakiYoshiaki FukazawaKiyoshi HondaMasahiro TagaAkira MatsuzakiMDPI AGarticlesoftware reliabilitydeep learninglong short-term memoryproject similarity and clusteringcross-project predictionMathematicsQA1-939ENMathematics, Vol 9, Iss 2945, p 2945 (2021)
institution DOAJ
collection DOAJ
language EN
topic software reliability
deep learning
long short-term memory
project similarity and clustering
cross-project prediction
Mathematics
QA1-939
spellingShingle software reliability
deep learning
long short-term memory
project similarity and clustering
cross-project prediction
Mathematics
QA1-939
Kyawt Kyawt San
Hironori Washizaki
Yoshiaki Fukazawa
Kiyoshi Honda
Masahiro Taga
Akira Matsuzaki
Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
description Software reliability is an essential characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development phases, applying traditional software reliability growth models (SRGMs) with limited past data does not always provide reliable prediction result for decision making. To overcome this, herein, we propose a new software reliability modeling method called a deep cross-project software reliability growth model (DC-SRGM). DC-SRGM is a cross-project prediction method that uses features of previous projects’ data through project similarity. Specifically, the proposed method applies cluster-based project selection for the training data source and modeling by a deep learning method. Experiments involving 15 real datasets from a company and 11 open source software datasets show that DC-SRGM can more precisely describe the reliability of ongoing development projects than existing traditional SRGMs and the LSTM model.
format article
author Kyawt Kyawt San
Hironori Washizaki
Yoshiaki Fukazawa
Kiyoshi Honda
Masahiro Taga
Akira Matsuzaki
author_facet Kyawt Kyawt San
Hironori Washizaki
Yoshiaki Fukazawa
Kiyoshi Honda
Masahiro Taga
Akira Matsuzaki
author_sort Kyawt Kyawt San
title Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
title_short Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
title_full Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
title_fullStr Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
title_full_unstemmed Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering
title_sort deep cross-project software reliability growth model using project similarity-based clustering
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/3b8cfe7004ee41788bbe8bc1602e1a4d
work_keys_str_mv AT kyawtkyawtsan deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
AT hironoriwashizaki deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
AT yoshiakifukazawa deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
AT kiyoshihonda deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
AT masahirotaga deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
AT akiramatsuzaki deepcrossprojectsoftwarereliabilitygrowthmodelusingprojectsimilaritybasedclustering
_version_ 1718411373223870464