Software Defects Prediction At Method Level Using Ensemble Learning Techniques
Ibrahim, A., Abdelsalam, H., Taj-Eddin, I. (2023). Software Defects Prediction At Method Level Using Ensemble Learning Techniques. EKB Journal Management System, 23(2), 28-49. doi: 10.21608/ijicis.2023.189934.1251
Asmaa M Ibrahim; Hicham Abdelsalam; Islam A.T.F Taj-Eddin. "Software Defects Prediction At Method Level Using Ensemble Learning Techniques". EKB Journal Management System, 23, 2, 2023, 28-49. doi: 10.21608/ijicis.2023.189934.1251
Ibrahim, A., Abdelsalam, H., Taj-Eddin, I. (2023). 'Software Defects Prediction At Method Level Using Ensemble Learning Techniques', EKB Journal Management System, 23(2), pp. 28-49. doi: 10.21608/ijicis.2023.189934.1251
Ibrahim, A., Abdelsalam, H., Taj-Eddin, I. Software Defects Prediction At Method Level Using Ensemble Learning Techniques. EKB Journal Management System, 2023; 23(2): 28-49. doi: 10.21608/ijicis.2023.189934.1251

Software Defects Prediction At Method Level Using Ensemble Learning Techniques

International Journal of Intelligent Computing and Information Sciences
Volume 23, Issue 2, June 2023, Page 28-49  XML PDF (1.12 MB)
Document Type: Original Article
DOI: 10.21608/ijicis.2023.189934.1251
View on SCiNiTO View on SCiNiTO
Authors
Asmaa M Ibrahim email 1; Hicham Abdelsalam2; Islam A.T.F Taj-Eddin3
1Software Engineering Faculty of Computers and Information Technology, Egyptian E-learning University, Assuit,
2Faculty of Computers and Information Technology Cairo-Egypt, Egyptian E-learning University
3Faculty of Computers and Information , Assuit University
Abstract
Abstract: Creating error-free software artifacts is essential to increase software quality and potential re-usability. However, testing software artifacts to find defects and fix them is time-consuming and costly, so predicting the most error-prone software components can optimise the testing process by focusing testing resources on those components to save time and money. Much software defect prediction research has focused on higher granularities, e.g., file and package levels, and fewer have focused on the method level due to the lack of method-level  bug-related datasets . In this paper, software defect prediction will be performed on highly imbalanced  method-level datasets extracted from 23 open source Java projects . Eight ensemble learning algorithms will be applied to the datasets: Bagging, Ada-Boost, Random Forest, Random Under sampling Boost, Easy Ensemble, Balanced Bagging and Balanced Random Forest. The results showed that the Balanced Random Forest classifier achieved the best results regarding Recall and Roc_Auc values  .
Keywords
Method Level Software Defects Prediction; Ensemble Learning; Balanced Ensemble Learning; Imbalanced dataset; ELFF datasets
Statistics
Article View: 187
PDF Download: 185