A Study on the Significance of Software Metrics in Defect Prediction

被引：8

作者：

Xia, Ye ^{[1
]}

Yan, Guoying ^{[1
]}

Si, Qianran ^{[1
]}

机构：

[1] Beijing Inst Tracking & Telecommun Technol, Beijing, Peoples R China

来源：

2013 SIXTH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN (ISCID), VOL 2 | 2013年

关键词：

defect prediction; software metric; feature selection; classifier;

D O I：

10.1109/ISCID.2013.199

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the case of metrics-based software defect prediction, an intelligent selection of metrics plays an important role in improving the model performance. In this paper, we use different ways for feature selection and dimensionality reduction to determine the most important software metrics. Three different classifiers are utilized, namely Naive Bayes, support vector machine and decision tree. On the publicly NASA data, a comparative experiment results show that instead of 22 or more metrics, less than 10 metrics can get better performance.

引用

页码：343 / 346

页数：4

共 50 条

[11] An Empirical Study of Software Metrics Diversity for Cross-Project Defect Prediction
Zhong Y.
Song K.
Lv S.
He P.
Mathematical Problems in Engineering, 2021, 2021
[12] An Effective Rank Approach to Software Defect Prediction Using Software Metrics
Lakshmi, P.
Maheswari, Latha T.
PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND CONTROL (ISCO'16), 2016,
[13] A study on software metrics based software defect prediction using data mining and machine learning techniques
Prasad, Manjula C.M.
Florence, Lilly
Arya, Arti
International Journal of Database Theory and Application, 2015, 8 (03): : 179 - 190
[14] Weighted software metrics aggregation and its application to defect prediction
Ulan, Maria
Lowe, Welf
Ericsson, Morgan
Wingkvist, Anna
EMPIRICAL SOFTWARE ENGINEERING, 2021, 26 (05)
[15] New Conceptual Cohesion Metrics: Assessment for Software Defect Prediction
Miholca, Diana-Lucia
2021 23RD INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2021), 2021, : 163 - 170
[16] Weighted software metrics aggregation and its application to defect prediction
Maria Ulan
Welf Löwe
Morgan Ericsson
Anna Wingkvist
Empirical Software Engineering, 2021, 26
[17] Revisiting the Impact of Dependency Network Metrics on Software Defect Prediction
Gong, Lina
Rajbahadur, Gopi Krishnan
Hassan, Ahmed E.
Jiang, Shujuan
IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2022, 48 (12) : 5030 - 5049
[18] Software Defect Prediction Using Static Code Metrics Underestimates Defect-Proneness
Gray, David
Bowes, David
Davey, Neil
Sun, Yi
Christianson, Bruce
2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[19] Modeling Structural Model for Defect Categories Based On Software Metrics for Categorical Defect Prediction
Gupta, Niketa
Panwar, Deepali
Sharma, Ashish
6TH INTERNATIONAL CONFERENCE ON COMPUTER & COMMUNICATION TECHNOLOGY (ICCCT-2015), 2015, : 46 - 50
[20] Cross-project software defect prediction based on the reduction and hybridization of software metrics
Abdu, Ahmed
Zhai, Zhengjun
Abdo, Hakim A.
Lee, Sungon
Al-masni, Mohammed A.
Gu, Yeong Hyeon
Algabri, Redhwan
ALEXANDRIA ENGINEERING JOURNAL, 2025, 112 : 161 - 176

← 1 2 3 4 5 →