期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：10
DOI：10.15680/IJIRCCE.2015.0310102
出版社：S&S Publications
摘要：In software development, early prediction of defective software modules can reduce overall time andbudget and increase customer satisfaction [1], by meeting customer requirements to the utmost. To deliver reliablesoftware, it is essential to execute a number of test cases, which is tedious and costly. Huge dimensions and noisy datamake the task of testing more cumbersome. In this paper, we discuss a new model towards reliability and qualityimprovement of software systems by predicting fault-prone modules before the testing phase. It focuses on outlierdetection and removal, followed by dimensional reduction, which aims at reducing the noise and dimensions of the datasets. Further, the system is trained to predict bugs efficiently at an earlier stage. The goal is to help testers toconcentrate their testing efforts to modules which have lesser bugs
