Untitled

Abstract

Finding faults in software modules is an emerging issue in software reliability systems and the assessment of the fault is performed by software fault prediction systems (SFPS). An identification process of faultprone of software modules is the most prioritized before initiating the testing process of the same modules. The SFPS helps to improve the quality of software within the specified time and cost values. Early fault prediction in SFPS for the different software components showed significant results concerning the cost and time parameters. According to the state-of-the-art of SFPS, ensemble-based classifiers were performed as the best and most cost-effective when compared to other classifier methods. An ensemble random forest with adaptive synthetic sampling (E-RF-ADASYN) is developed recently is tested on a sample of PROMISE datasets and shows the cost-effective classifier results. Our proposed work is focused on the development of another sampling method, say, Multi-Distinguished-Features Sampling (MDFS) for obtaining the best sample illustration for representing the entire dataset. The experiments are conducted on bench-marked PROMISE datasets for demonstrating the efficiency of the proposed MDFS-E-RF compared to other traditional methods.