1. The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models
2. In September 2020, López-Martín, Villuendas-Rey, Azzeh, Bou Nassif, and Banitaan introduced a novel approach called “Transformed k-Nearest Neighborhood Output Distance Minimization” for the prediction of defect density in software projects;This research was presented in the Journal of Systems Software
3. Umer, and Guo delved into the realm of software defect prediction using deep learning techniques. Their work, titled “Deep Learning-Based Software Defect Prediction,”;Qiao;was published in the journal Neurocomputing,2020
4. In July 2020, Rathaur, Kamath, and Ghanekar presented a methodology for software defect density prediction based on multiple linear regression
5. In November 2021, Sarker provided a comprehensive overview of deep learning techniques, taxonomy, applications, and research directions in the field. This overview, titled “Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications, and Research Directions,”;was published in the journal Social Networking and Computational Sciences