The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La localisation des défauts existante basée sur les réseaux neuronaux utilise les informations indiquant si une déclaration est réalisé or Non exécuté pour identifier les déclarations suspectes potentiellement responsables d’un échec. Cependant, les informations montrent uniquement les états d'exécution binaires d'une instruction et ne peuvent pas montrer l'importance d'une instruction dans les exécutions. Par conséquent, cela peut dégrader l’efficacité de la localisation des pannes. Pour résoudre ce problème, cet article propose TFIDF-FL en utilisant le terme fréquence inverse de fréquence de document pour identifier un degré élevé ou faible d'influence d'une déclaration dans une exécution. Nos résultats empiriques sur 8 programmes réels montrent que TFIDF-FL améliore considérablement l'efficacité de la localisation des défauts.
Zhuo ZHANG
National University of Defense Technology
Yan LEI
Chongqing University
Jianjun XU
National University of Defense Technology
Xiaoguang MAO
National University of Defense Technology
Xi CHANG
National University of Defense Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Zhuo ZHANG, Yan LEI, Jianjun XU, Xiaoguang MAO, Xi CHANG, "TFIDF-FL: Localizing Faults Using Term Frequency-Inverse Document Frequency and Deep Learning" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 9, pp. 1860-1864, September 2019, doi: 10.1587/transinf.2018EDL8237.
Abstract: Existing fault localization based on neural networks utilize the information of whether a statement is executed or not executed to identify suspicious statements potentially responsible for a failure. However, the information just shows the binary execution states of a statement, and cannot show how important a statement is in executions. Consequently, it may degrade fault localization effectiveness. To address this issue, this paper proposes TFIDF-FL by using term frequency-inverse document frequency to identify a high or low degree of the influence of a statement in an execution. Our empirical results on 8 real-world programs show that TFIDF-FL significantly improves fault localization effectiveness.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8237/_p
Copier
@ARTICLE{e102-d_9_1860,
author={Zhuo ZHANG, Yan LEI, Jianjun XU, Xiaoguang MAO, Xi CHANG, },
journal={IEICE TRANSACTIONS on Information},
title={TFIDF-FL: Localizing Faults Using Term Frequency-Inverse Document Frequency and Deep Learning},
year={2019},
volume={E102-D},
number={9},
pages={1860-1864},
abstract={Existing fault localization based on neural networks utilize the information of whether a statement is executed or not executed to identify suspicious statements potentially responsible for a failure. However, the information just shows the binary execution states of a statement, and cannot show how important a statement is in executions. Consequently, it may degrade fault localization effectiveness. To address this issue, this paper proposes TFIDF-FL by using term frequency-inverse document frequency to identify a high or low degree of the influence of a statement in an execution. Our empirical results on 8 real-world programs show that TFIDF-FL significantly improves fault localization effectiveness.},
keywords={},
doi={10.1587/transinf.2018EDL8237},
ISSN={1745-1361},
month={September},}
Copier
TY - JOUR
TI - TFIDF-FL: Localizing Faults Using Term Frequency-Inverse Document Frequency and Deep Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1860
EP - 1864
AU - Zhuo ZHANG
AU - Yan LEI
AU - Jianjun XU
AU - Xiaoguang MAO
AU - Xi CHANG
PY - 2019
DO - 10.1587/transinf.2018EDL8237
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2019
AB - Existing fault localization based on neural networks utilize the information of whether a statement is executed or not executed to identify suspicious statements potentially responsible for a failure. However, the information just shows the binary execution states of a statement, and cannot show how important a statement is in executions. Consequently, it may degrade fault localization effectiveness. To address this issue, this paper proposes TFIDF-FL by using term frequency-inverse document frequency to identify a high or low degree of the influence of a statement in an execution. Our empirical results on 8 real-world programs show that TFIDF-FL significantly improves fault localization effectiveness.
ER -