| Presentation | 2021-07-17 Refined Ensemble Learning Algorithms for Software Bug Prediction Keisuke Fukuda, Tadashi Dohi, Hiroyuki Okamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose to apply three metaheuristic algorithms; latin hypercube sampling, ABC (artificial bee colony) algorithm, and parameter free GA (genetic algorithm), to search the optimal hyperparameters in the random forest, and investigate the prediction accuracy of bug-prone modules. In experiments with actual software development project data, we compare our refined ensemble learning algorithms with the existing machine learning approaches. It is shown that the random forests with metaheuristic refinement could provide the better predictive performances of the software bug prediction in average. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | software bug prediction / bug-prone module / random forest / ensemble method / machine learning / hyperparameter / metaheuristics / search-based software engineering |
| Paper # | R2021-19 |
| Date of Issue | 2021-07-10 (R) |
| Conference Information | |
| Committee | R |
|---|---|
| Conference Date | 2021/7/17(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Virtual |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Reliability Theory, Communication Network Reliability, Reliability General |
| Chair | Tadashi Dohi(Hiroshima Univ.) |
| Vice Chair | Yasushi Kadota(Ricoh) |
| Secretary | Yasushi Kadota(Hiroshima Univ.) |
| Assistant | Shinji Yokogawa(Univ. of Electro-Comm.) / Takahide Yoshikawa(Fujitsu Lab.) / Takenori Sakumura(Housei Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Reliability |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Refined Ensemble Learning Algorithms for Software Bug Prediction |
| Sub Title (in English) | Metaheuristic Approach |
| Keyword(1) | software bug prediction |
| Keyword(2) | bug-prone module |
| Keyword(3) | random forest |
| Keyword(4) | ensemble method |
| Keyword(5) | machine learning |
| Keyword(6) | hyperparameter |
| Keyword(7) | metaheuristics |
| Keyword(8) | search-based software engineering |
| 1st Author's Name | Keisuke Fukuda |
| 1st Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 2nd Author's Name | Tadashi Dohi |
| 2nd Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 3rd Author's Name | Hiroyuki Okamura |
| 3rd Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| Date | 2021-07-17 |
| Paper # | R2021-19 |
| Volume (vol) | vol.121 |
| Number (no) | R-115 |
| Page | pp.pp.18-23(R), |
| #Pages | 6 |
| Date of Issue | 2021-07-10 (R) |