Experimental Evaluation of Hybrid Algorithm in Spectrum based Fault Localization

摘要

During debugging process in software development cycle, fault localization is inevitable work. Diverse approaches have been proposed, such as program slicing, machine learning, and data mining for fault localization. In this paper we propose an effective hybrid fault localization algorithm based on a spectrum that enables fault detection in every statement. This algorithm distinguishes the location of a bug that causes a false positive score through the relationship between a test case and statement hit information. We also provide a fault localization tool named SKKU Fault localizer which enables source code instrumentation, test automation, test result comparison, extraction of distinct data, and fault ratio display. We applied it to the bug detection in Siemens test suite. Empirical results show that the hybrid algorithm not only decreases the amount of code to be reviewed by the programmer but also increases the effectiveness.