Information fusion with dempster-shafer evidence theory for software defect prediction

Abstract

Finding defects in software is a challenging and time and budget consuming task. Minimizing these adverse effects using software defect prediction models via guiding testers with defective parts of software system is an attractive research area. Previous research emphasized the value of these tools with a mean probability of detection of 71 percent and mean false alarm rates of 25 percent. This paper examines software defect prediction and aims to improve prediction results using information fusion technique. Results indicate that the prediction results can be improved using Dempster-Shafer Evidence Theory for information fusion. (C) 2010 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Guest Editor.