A GMM and SVM Combined Approach for Automatically Software Fault Localization

To improve the efficiency and accuracy of automatic fault localization. We propose an approach to direct fault localization by applying Gaussian Mixture Model (GMM) and Support Vector Machine (SVM), which are two mathematical models with excellent classification and prediction abilities. We first preprocess the training data using GMM-based clustering algorithm. Then the constant penalty factor of SVM is replaced with two adjustable ones. After that, we find out the mapping relationships between the coverage information and the execution result of each test case by virtue of the robust learning ability of modified SVM. An efficiency comparison between our technique and others on Siemens Suite is carried out afterwards. The experiment result indicates that our localization approach achieves a better accuracy in single and multiple faults localization without increasing testing cost.