| Presentation | 2020-03-07 Research for improving the accuracy of program fault detection by CNN-BI system Kazuhiko Ogawa, Takako Nakatani, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Many researchers have done much research to improve software quality.One way to improve the quality of a program is to infer defects in the source code. The inferred bug is used to improve the quality of debug and review.There are methods for inferring defects using the results obtained from metrics, and methods for inferring defects using source code.In addition to statistical methods, techniques such as machine learning and deep learning are used to improve program accuracy.In this paper, we tried to improve the inference accuracy, which was a problem in inferring defects.We used to learn all programs as one learning model.We learned by classifying project members with similar years of experience and skills.We thought that learning could improve accuracy by performing inference using multiple models. We conducted experiments to see if the accuracy improved. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | bug inference / convolutional nural network / image of source code / deep learning |
| Paper # | KBSE2019-58 |
| Date of Issue | 2020-02-28 (KBSE) |
| Conference Information | |
| Committee | KBSE |
|---|---|
| Conference Date | 2020/3/6(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tenbusu-Naha |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General, Student |
| Chair | Fumihiro Kumeno(Nippon Inst. of Tech.) |
| Vice Chair | Hiroyuki Nakagawa(Osaka Univ.) |
| Secretary | Hiroyuki Nakagawa(Ibaraki Univ.) |
| Assistant | Nahomi Kikuchi(OKi) / Tomoko Kaneko(NII) |
| Paper Information | |
| Registration To | Technical Committee on Knowledge-Based Software Engineering |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Research for improving the accuracy of program fault detection by CNN-BI system |
| Sub Title (in English) | |
| Keyword(1) | bug inference |
| Keyword(2) | convolutional nural network |
| Keyword(3) | image of source code |
| Keyword(4) | deep learning |
| 1st Author's Name | Kazuhiko Ogawa |
| 1st Author's Affiliation | The Open University of Japan(OUJ) |
| 2nd Author's Name | Takako Nakatani |
| 2nd Author's Affiliation | The Open University of Japan(OUJ) |
| Date | 2020-03-07 |
| Paper # | KBSE2019-58 |
| Volume (vol) | vol.119 |
| Number (no) | KBSE-467 |
| Page | pp.pp.73-78(KBSE), |
| #Pages | 6 |
| Date of Issue | 2020-02-28 (KBSE) |