Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier
Background: Software Defect Prediction (SDP) is a vital step in software development. SDP aims to identify the most likely defect-prone modules before starting the testing phase, and it helps assign resources and reduces the cost of testing. Aim: Although many machine learning algorithms have been...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wroclaw University of Science and Technology
2023-10-01
|
| Series: | e-Informatica Software Engineering Journal |
| Subjects: | |
| Online Access: | https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2024/issue-1/article-3/ |
| _version_ | 1797425181994516480 |
|---|---|
| author | Mohammad Azzeh Ali Bou Nassif Manar Abu Talib Hajra Iqbal |
| author_facet | Mohammad Azzeh Ali Bou Nassif Manar Abu Talib Hajra Iqbal |
| author_sort | Mohammad Azzeh |
| collection | DOAJ |
| description | Background: Software Defect Prediction (SDP) is a vital step in software development. SDP aims to identify the most likely defect-prone modules before starting the testing phase, and it helps assign resources and reduces the cost of testing.
Aim: Although many machine learning algorithms have been used to classify software modules based on static code metrics, the k-Nearest Neighbors (kNN) method does not greatly improve defect prediction because it requires careful set-up of multiple configuration parameters before it can be used. To address this issue, we used the Non-dominated Sorting Genetic Algorithm (NSGA-II) to optimize the parameters in the kNN classifier with favor to improve SDP accuracy. We used NSGA-II because the existing accuracy metrics often behave differently, making an opposite judgment in evaluating SDP models. This means that changing one parameter might improve one accuracy measure while it decreases the others.
Method: The proposed NSGAII-kNN model was evaluated against the classical kNN model and state-of-the-art machine learning algorithms such as Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF) classifiers.
Results: Results indicate that the GA-optimized kNN model yields a higher Matthews Coefficient Correlation and higher balanced accuracy based on ten datasets.
Conclusion: The paper concludes that integrating GA with kNN improved defect prediction when applied to large or small or large datasets. |
| first_indexed | 2024-03-09T08:12:21Z |
| format | Article |
| id | doaj.art-34030c3b45dc4d3badc0269693ce483c |
| institution | Directory Open Access Journal |
| issn | 1897-7979 2084-4840 |
| language | English |
| last_indexed | 2024-03-09T08:12:21Z |
| publishDate | 2023-10-01 |
| publisher | Wroclaw University of Science and Technology |
| record_format | Article |
| series | e-Informatica Software Engineering Journal |
| spelling | doaj.art-34030c3b45dc4d3badc0269693ce483c2023-12-02T23:10:17ZengWroclaw University of Science and Technologye-Informatica Software Engineering Journal1897-79792084-48402023-10-0118110.37190/e-Inf240103Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour ClassifierMohammad AzzehAli Bou NassifManar Abu TalibHajra Iqbal Background: Software Defect Prediction (SDP) is a vital step in software development. SDP aims to identify the most likely defect-prone modules before starting the testing phase, and it helps assign resources and reduces the cost of testing. Aim: Although many machine learning algorithms have been used to classify software modules based on static code metrics, the k-Nearest Neighbors (kNN) method does not greatly improve defect prediction because it requires careful set-up of multiple configuration parameters before it can be used. To address this issue, we used the Non-dominated Sorting Genetic Algorithm (NSGA-II) to optimize the parameters in the kNN classifier with favor to improve SDP accuracy. We used NSGA-II because the existing accuracy metrics often behave differently, making an opposite judgment in evaluating SDP models. This means that changing one parameter might improve one accuracy measure while it decreases the others. Method: The proposed NSGAII-kNN model was evaluated against the classical kNN model and state-of-the-art machine learning algorithms such as Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF) classifiers. Results: Results indicate that the GA-optimized kNN model yields a higher Matthews Coefficient Correlation and higher balanced accuracy based on ten datasets. Conclusion: The paper concludes that integrating GA with kNN improved defect prediction when applied to large or small or large datasets. https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2024/issue-1/article-3/software defect predictiongenetic algorithmmulti-objective optimizationk-nearest neighbor |
| spellingShingle | Mohammad Azzeh Ali Bou Nassif Manar Abu Talib Hajra Iqbal Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier e-Informatica Software Engineering Journal software defect prediction genetic algorithm multi-objective optimization k-nearest neighbor |
| title | Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier |
| title_full | Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier |
| title_fullStr | Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier |
| title_full_unstemmed | Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier |
| title_short | Software Defect Prediction Using Non-Dominated Sorting Genetic Algorithm and k-Nearest Neighbour Classifier |
| title_sort | software defect prediction using non dominated sorting genetic algorithm and k nearest neighbour classifier |
| topic | software defect prediction genetic algorithm multi-objective optimization k-nearest neighbor |
| url | https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2024/issue-1/article-3/ |
| work_keys_str_mv | AT mohammadazzeh softwaredefectpredictionusingnondominatedsortinggeneticalgorithmandknearestneighbourclassifier AT alibounassif softwaredefectpredictionusingnondominatedsortinggeneticalgorithmandknearestneighbourclassifier AT manarabutalib softwaredefectpredictionusingnondominatedsortinggeneticalgorithmandknearestneighbourclassifier AT hajraiqbal softwaredefectpredictionusingnondominatedsortinggeneticalgorithmandknearestneighbourclassifier |