Fault Prediction Using the Similarity Weights Method

被引：0

作者：

Jindarak, Kidsana ^{[1
]}

Sammapun, Usa ^{[1
]}

机构：

[1] Kasetsart Univ, Dept Comp Sci, Fac Sci, Bangkok, Thailand

来源：

MODELING, SIMULATION AND CONTROL | 2011年 / 10卷

关键词：

fault prediction; bug prediction; source code similarity;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Software maintenance is one of difficult activities in the development process and could force developers to put in significant time and effort to find and debug software defects. In this paper, we propose a new and simple method for automatically predicting fault in unlabelled code. Our technique predicts faults that occur in the software by using local alignment to find significant weight and applying SVM algorithm to classify code to pinpoint which pieces of code is buggy. As an experiment, we applied our technique to an open source software project, and preliminary results show that our technique is possible and leads to software quality and fault prediction.

引用

页码：173 / 178

页数：6

共 50 条

[1] A Fault Prediction Method Based on IAALO-SVM and Similarity Measure
Hu, Weiwei
Fan, Hui
Liu, Jiamin
Sun, Yufeng
Zhao, Guangyan
2019 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE (PHM-QINGDAO), 2019,
[2] A new study of using temporality and weights to improve similarity measures for link prediction of social networks
Aghabozorgi, Farshad
Khayyambashi, Mohammad Reza
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 34 (04) : 2667 - 2678
[3] Fault prediction of wind turbine by using the SVM method
Shin, Jun-Hyun
Lee, Yun-Seong
Kim, Jin-O
2014 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE, ELECTRONICS AND ELECTRICAL ENGINEERING (ISEEE), VOLS 1-3, 2014, : 1923 - 1926
[4] Fault prediction of wind turbine by using the SVM method
20144900293291
(1) Department of Electrical Engineering, Hanyang University, Seoul, Korea, Republic of, Future University Hakodate; IEEE Sapporo Section; Xiamen University (Institute of Electrical and Electronics Engineers Inc., United States):
[5] Improving the MLP Learning by Using a Method to Calculate the Initial Weights of the Network Based on the Quality of Similarity Measure
Filiberto Cabrera, Yaima
Bello Perez, Rafael
Caballero Mota, Yaile
Ramos Jimenez, Gonzalo
ADVANCES IN SOFT COMPUTING, PT II, 2011, 7095 : 351 - +
[6] A two-stage method for bearing fault detection using graph similarity evaluation
Sun, Weifang
Zhou, Yuqing
Cao, Xincheng
Chen, Binqiang
Feng, Wei
Chen, Leiqing
MEASUREMENT, 2020, 165
[7] Looking below the ground: Prediction of Tuber indicum habitat using the Weights of Evidence method
Yang, Xue-Qing
Kodikara, Gayantha R. L.
Luedeling, Eike
Yang, Xue-Fei
He, Jun
Liu, Pei-gui
Xu, Jian-Chu
ECOLOGICAL MODELLING, 2012, 247 : 27 - 39
[8] Learning feature weights for similarity measures using genetic algorithms
Ishii, N
Wang, Y
IEEE INTERNATIONAL JOINT SYMPOSIA ON INTELLIGENCE AND SYSTEMS - PROCEEDINGS, 1998, : 27 - 33
[9] Prediction of Weights during Growth Stages of Onion Using Agricultural Data Analysis Method
Cho, Wanhyun
Na, Myung Hwan
Park, Yuha
Kim, Deok Hyeon
Cho, Yongbeen
APPLIED SCIENCES-BASEL, 2020, 10 (06):
[10] Personalized Disease Prediction Using a CNN-Based Similarity Learning Method
Suo, Qiuling
Ma, Fenglong
Yuan, Ye
Huai, Mengdi
Zhong, Weida
Zhang, Aidong
Gao, Jing
2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2017, : 811 - 816

← 1 2 3 4 5 →