Improvement in bug localization based on kernel extreme learning machine

Marzie Rahmati, Mohammad Ali Zare Chahooki


Bug localization uses bug reports received from users, developers and testers to locate buggy files. Since finding a buggy file among thousands of files is time consuming and tedious for developers, various methods based on information retrieval is suggested to automate this process. In addition to information retrieval methods for error localization, machine learning methods are used too. Machine learning-based approach, improves methods of describing bug report and program code by representing them in feature vectors. Learning hypothesis on Extreme Learning Machine (ELM) has been recently effective in many areas. This paper shows effectiveness of none-linear kernel of ELM in bug localization. Furthermore the effectiveness of Different kernels in ELM compare to other kernel-based learning methods is analyzed. The experimental results for hypothesis evaluation on Mozilla Firefox dataset show effectiveness of Kernel ELM for bug localization in software projects.


machine learning; Extreme learning machine; information retrieval

Full Text:



D. Kim, Y. Tao, S. Kim, and A. Zeller, “Where should we fix this bug? A two-phase recommendation model,” IEEE transactions on software Engineering, vol. 39, no. 11, pp. 1597-1610, 2013.

M. Weiser, ”Program Slicing,” Proc. Of the 5th international conference on software engineering, no. 4, 1984, pp. 352-357

H. ledgard and M. Weiser, “Programmers Use Slices when Debugging,” Communications of ACM, vol. 25, no. 7, pp. 446-452, 1982.

Korel, Bogdan, and Janusz Laski. "STAD-A system for testing and debugging: User perspective." Proc. of the Second workshop on software testing, verification, and analysis, 1988, pp. 13 - 20.

C. Liu, et. al., "Statistical debugging: A hypothesis testing-based approach," IEEE Transactions on software engineering, vol. 32, no. pp. 831-848, 2006.

W. Lafayette, “Retrieval from Software Libraries for Bug Localization : A Comparative Study of Generic and Composite Text Models,” In proc. of the 8th working conference on mining Software repositories, 2011, pp. 43-52.

J. Zhou, H. Zhang, and D. Lo, “Where Should the Bugs Be Fixed ?

More Accurate Information Retrieval Based Bug Localization Based on Bug Reports,” 34th international conference of software engineering (ICSE), 2012, pp. 14-24.

G. Huang, S. Member, H. Zhou, X. Ding, and R. Zhang, “Extreme Learning Machine for Regression and Multiclass Classification,” vol. 42, no. 2, pp. 513–529, 2012.

G. H. Ã, Q. Zhu, and C. Siew, “Extreme learning machine : Theory and applications,” vol. 70, pp. 489–501, 2006.

N. Cristianini and J. Shawe-Taylor, “An Introduction to Support Vector Machines: And Other Kernel-based Learning Methods.” New York, NY, USA: Cambridge University Press, 2000.

N. Bettenburg, et. al., “Extracting Structural information from bug reports,” Proceeding of the 2008 international working conference on mining software repositories, ACM, 2008.