Improved approach for software defect prediction using artificial neural networks

Abstract

Software defect prediction (SDP) is a most dynamic research area in software engineering. SDP is a process used to predict the deformities in the software. To identifying the defects before the arrival of item or aimed the software improvement, to make software dependable, defect prediction model is utilized. It is always desirable to predict the defects at early stages of life cycle. Hence to predict the defects before testing the SDP is done at end of each phase of SDLC. It helps to reduce the cost as well as time. To produce high quality software, the artificial neural network approach is applied to predict the defect. Nine metrics are applied to the multiple phases of SDLC and twenty genuine software projects are used. The software project data were collected from a team of organization and their responses were recorded in linguistic terms. For assessment of model the mean magnitude of relative error (MMRE) and balanced mean magnitude of relative error (BMMRE) measures are used. In this research work, the implementation of neural network based software defect prediction is compared with the results of fuzzy logic basic approach. In the proposed approach, it is found that the neural network based training model is providing better and effective results on multiple parameters.