Software defect prediction using Binary Particle Swarm Optimization with Binary Cross Entropy as the fitness function

Abstract

Software is a consequential asset because concrete software is needed in virtually every industry, in every business, and for every function. It becomes more paramount as time goes on – if something breaks within your application portfolio and expeditious, efficient, and efficacious fine-tune needs to transpire as anon as possible. Therefore, recognizing the faults in the early phase of the software development lifecycle is essential for both, diminishing the cost in terms of efforts and money Similarly, It is important to find out features which could be redundant or features which are highly correlated with each other, as it could largely affect the model’s learning process. This analysis refers to the use of crossover Artificial Neural Network (ANN) and Binary Particle Swarm Optimization (BPSO) with Binary Cross-Entropy (BCE) loss for the fitness function. The conclusion of proposed paper is to provide the significance and opportunity of using Binary Cross-Entropy (BCE) in Binary Particle Swarm Optimization (BPSO) for the feature reduction process in order to minimize the developer’s effort and costs for software development as well as for its maintenance.