Deep Learning-Based Fault Localization with Contextual Information

Zhuo ZHANG; Yan LEI; Qingping TAN; Xiaoguang MAO; Ping ZENG; Xi CHANG

doi:10.1587/transinf.2017EDL8143

Deep Learning-Based Fault Localization with Contextual Information

Zhuo ZHANG, Yan LEI, Qingping TAN, Xiaoguang MAO, Ping ZENG, Xi CHANG

Full Text Views

0

Share
Cite this

Summary :

Fault localization is essential for solving the issue of software faults. Aiming at improving fault localization, this paper proposes a deep learning-based fault localization with contextual information. Specifically, our approach uses deep neural network to construct a suspiciousness evaluation model to evaluate the suspiciousness of a statement being faulty, and then leverages dynamic backward slicing to extract contextual information. The empirical results show that our approach significantly outperforms the state-of-the-art technique Dstar.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.12 pp.3027-3031

Publication Date: 2017/12/01

Publicized: 2017/09/08

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDL8143

Type of Manuscript: LETTER

Category: Software Engineering

Authors

Zhuo ZHANG
  National University of Defense Technology
Yan LEI
  Ministry of Education,Chongqing University,Logistical Engineering University
Qingping TAN
  National University of Defense Technology
Xiaoguang MAO
  National University of Defense Technology
Ping ZENG
  National University of Defense Technology
Xi CHANG
  National University of Defense Technology

Keyword

fault localization, dynamic slice, deep learning, contextual information

Cite this

Copy

Zhuo ZHANG, Yan LEI, Qingping TAN, Xiaoguang MAO, Ping ZENG, Xi CHANG, "Deep Learning-Based Fault Localization with Contextual Information" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 12, pp. 3027-3031, December 2017, doi: 10.1587/transinf.2017EDL8143.
Abstract: Fault localization is essential for solving the issue of software faults. Aiming at improving fault localization, this paper proposes a deep learning-based fault localization with contextual information. Specifically, our approach uses deep neural network to construct a suspiciousness evaluation model to evaluate the suspiciousness of a statement being faulty, and then leverages dynamic backward slicing to extract contextual information. The empirical results show that our approach significantly outperforms the state-of-the-art technique Dstar.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8143/_p

Copy

@ARTICLE{e100-d_12_3027,
author={Zhuo ZHANG, Yan LEI, Qingping TAN, Xiaoguang MAO, Ping ZENG, Xi CHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Deep Learning-Based Fault Localization with Contextual Information},
year={2017},
volume={E100-D},
number={12},
pages={3027-3031},
abstract={Fault localization is essential for solving the issue of software faults. Aiming at improving fault localization, this paper proposes a deep learning-based fault localization with contextual information. Specifically, our approach uses deep neural network to construct a suspiciousness evaluation model to evaluate the suspiciousness of a statement being faulty, and then leverages dynamic backward slicing to extract contextual information. The empirical results show that our approach significantly outperforms the state-of-the-art technique Dstar.},
keywords={},
doi={10.1587/transinf.2017EDL8143},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Deep Learning-Based Fault Localization with Contextual Information
T2 - IEICE TRANSACTIONS on Information
SP - 3027
EP - 3031
AU - Zhuo ZHANG
AU - Yan LEI
AU - Qingping TAN
AU - Xiaoguang MAO
AU - Ping ZENG
AU - Xi CHANG
PY - 2017
DO - 10.1587/transinf.2017EDL8143
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2017
AB - Fault localization is essential for solving the issue of software faults. Aiming at improving fault localization, this paper proposes a deep learning-based fault localization with contextual information. Specifically, our approach uses deep neural network to construct a suspiciousness evaluation model to evaluate the suspiciousness of a statement being faulty, and then leverages dynamic backward slicing to extract contextual information. The empirical results show that our approach significantly outperforms the state-of-the-art technique Dstar.
ER -