A new hybrid algorithm for software fault localization
Jeongho Kim, Jong-Hee Park, Eunseok Lee · 2015
We previously presented a spectrum-based fault localization (SFL) technique, which we named Hybrid, that localizes a bug by using the program hit spectra and test results. We also proposed a distinct mechanism for test data that enables the SFL algorithms to localize fault in a more precise manner than what would be possible with the original test data. However, there was a limitation of the Hybrid algorithm. In that the technique only showed better performance when using distinct test data. Therefore, in the current work, we improve over Hybrid by analyzing more than 30 types of existing algorithms. After choosing the appropriate algorithms, we adopted their specific strengths through experimentation. Finally, we developed the novel Combination Algorithms (CAL). In our experimental study, we used the Siemens test program to confirm that our technique was more precise than the state-of-the-art SFL algorithm D Star and Heuristic III for both original and distinct test data. In particular, our technique localizes a fault under 2 percent on average as well as decreases the coverage of the reading code by a third of the source code.