Cross-project software defect prediction through multiple learning

Cross-project defect prediction is a method that predicts defects in one software project by using the historical record of another software project. Due to distribution differences and the weak classifier used to build the prediction model, this method has poor prediction performance. Cross-project...

Full description

Bibliographic Details
Main Authors: Zakariyau Bala, Yahaya, Abdul Samat, Pathiah, Yatim Sharif, Khaironi, Manshor, Noridayu
Format: Article
Language:English
Published: Institute of Advanced Engineering and Science 2024
Online Access:http://psasir.upm.edu.my/id/eprint/111549/
http://psasir.upm.edu.my/id/eprint/111549/1/5258-20631-1-PB_beei-new.pdf
_version_ 1848865717227618304
author Zakariyau Bala, Yahaya
Abdul Samat, Pathiah
Yatim Sharif, Khaironi
Manshor, Noridayu
author_facet Zakariyau Bala, Yahaya
Abdul Samat, Pathiah
Yatim Sharif, Khaironi
Manshor, Noridayu
author_sort Zakariyau Bala, Yahaya
building UPM Institutional Repository
collection Online Access
description Cross-project defect prediction is a method that predicts defects in one software project by using the historical record of another software project. Due to distribution differences and the weak classifier used to build the prediction model, this method has poor prediction performance. Cross-project defect prediction may perform better if distribution differences are reduced, and an appropriate individual classifier is chosen. However, the prediction performance of individual classifiers may be affected in some way by their weaknesses. As a result, in order to boost the accuracy of cross-project defect prediction predictions, this study proposed a strategy that makes use of multiple classifiers and selects attributes that are similar to one another. The proposed method's efficacy was tested using the Relink and AEEEM datasets in an experiment. The findings of the experiments demonstrated that the proposed method produces superior outcomes. To further validate the method, we employed the Wilcoxon sum rank test at 95% significance level. The approach was found to perform significantly better than the baseline methods.
first_indexed 2025-11-15T14:09:08Z
format Article
id upm-111549
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:09:08Z
publishDate 2024
publisher Institute of Advanced Engineering and Science
recordtype eprints
repository_type Digital Repository
spelling upm-1115492024-08-09T02:17:15Z http://psasir.upm.edu.my/id/eprint/111549/ Cross-project software defect prediction through multiple learning Zakariyau Bala, Yahaya Abdul Samat, Pathiah Yatim Sharif, Khaironi Manshor, Noridayu Cross-project defect prediction is a method that predicts defects in one software project by using the historical record of another software project. Due to distribution differences and the weak classifier used to build the prediction model, this method has poor prediction performance. Cross-project defect prediction may perform better if distribution differences are reduced, and an appropriate individual classifier is chosen. However, the prediction performance of individual classifiers may be affected in some way by their weaknesses. As a result, in order to boost the accuracy of cross-project defect prediction predictions, this study proposed a strategy that makes use of multiple classifiers and selects attributes that are similar to one another. The proposed method's efficacy was tested using the Relink and AEEEM datasets in an experiment. The findings of the experiments demonstrated that the proposed method produces superior outcomes. To further validate the method, we employed the Wilcoxon sum rank test at 95% significance level. The approach was found to perform significantly better than the baseline methods. Institute of Advanced Engineering and Science 2024 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/111549/1/5258-20631-1-PB_beei-new.pdf Zakariyau Bala, Yahaya and Abdul Samat, Pathiah and Yatim Sharif, Khaironi and Manshor, Noridayu (2024) Cross-project software defect prediction through multiple learning. Bulletin of Electrical Engineering and Informatics, 13 (3). pp. 2027-2035. ISSN 2089-3191; EISSN: 2302-9285 https://beei.org/index.php/EEI/article/view/5258 10.11591/eei.v13i3.5258
spellingShingle Zakariyau Bala, Yahaya
Abdul Samat, Pathiah
Yatim Sharif, Khaironi
Manshor, Noridayu
Cross-project software defect prediction through multiple learning
title Cross-project software defect prediction through multiple learning
title_full Cross-project software defect prediction through multiple learning
title_fullStr Cross-project software defect prediction through multiple learning
title_full_unstemmed Cross-project software defect prediction through multiple learning
title_short Cross-project software defect prediction through multiple learning
title_sort cross-project software defect prediction through multiple learning
url http://psasir.upm.edu.my/id/eprint/111549/
http://psasir.upm.edu.my/id/eprint/111549/
http://psasir.upm.edu.my/id/eprint/111549/
http://psasir.upm.edu.my/id/eprint/111549/1/5258-20631-1-PB_beei-new.pdf