Presentation | 2021-07-08 Research for using image analysis of program fault by deep learning for code review. Kazuhiko Ogawa, Takako Nakatani, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In order to predict the location of faults in a program, we imaged the source code of the defective program and verified whether we could find the defective part of the program by learning with deep learning. We found that the descriptions of the programs that caused the defects had something in common in the appearance of the source code, and we thought that we could find the defects by applying CNN (Convolutional Neural Network), which is one of the deep learning methods. In this paper, we compare the results of a code review of a program that uses the results of inference from a model learned by deep learning and a code review of a program that does not use the results of inference. We will experiment to see whether the code review using the results of inference by deep learning can reduce the review time and detect more defects than the code review without the results of inference. We will also verify whether it is possible to detect unknown faults. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | bug inference / convolutional nural network / image of source code / deep learning / code review |
Paper # | SS2021-6,KBSE2021-18 |
Date of Issue | 2021-07-01 (SS, KBSE) |
Conference Information | |
Committee | KBSE / IPSJ-SE / SS |
---|---|
Conference Date | 2021/7/8(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Virtual (Zoom) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hiroyuki Nakagawa(Osaka Univ.) / 鷲崎 弘宜(早稲田大学) / Takashi Kobayashi(Tokyo Inst. of Tech.) |
Vice Chair | Takuya Saruwatari(NTT Data) / / Kozo Okano(Shinshu Univ.) |
Secretary | Takuya Saruwatari(Shinshu Univ) / (Doshisha Univ,) / Kozo Okano |
Assistant | Hideharu Kojima(Osaka Univ.) / Yutaro Kashiwa(Kyushu Univ,) / 伊原 彰紀(和歌山大学) / 小川 秀人(日立製作所) / 竹内 広宜(武蔵大学) / 徳本 晋(富士通) / 伏田 享平(NTT株式会社) / 福田 浩章(芝浦工業大学) / 横川 智教(岡山県立大学) / Shinpei Ogata(Shinshu Univ.) |
Paper Information | |
Registration To | Technical Committee on Knowledge-Based Software Engineering / Special Interest Group on Software Engineering / Technical Committee on Software Science |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Research for using image analysis of program fault by deep learning for code review. |
Sub Title (in English) | |
Keyword(1) | bug inference |
Keyword(2) | convolutional nural network |
Keyword(3) | image of source code |
Keyword(4) | deep learning |
Keyword(5) | code review |
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 | 2021-07-08 |
Paper # | SS2021-6,KBSE2021-18 |
Volume (vol) | vol.121 |
Number (no) | SS-94,KBSE-95 |
Page | pp.pp.31-36(SS), pp.31-36(KBSE), |
#Pages | 6 |
Date of Issue | 2021-07-01 (SS, KBSE) |