Cross-project software defect prediction based on multi-source data sets

doi:10.19682/j.cnki.1005-8885.2021.2007

中国邮电高校学报(英文) ›› 2021, Vol. 28 ›› Issue (4): 75-87.doi: 10.19682/j.cnki.1005-8885.2021.2007

Cross-project software defect prediction based on multi-source data sets

Huang Junfu, Wang Yawen, Gong Yunzhan, Jin Dahai

School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China

收稿日期:2019-10-18 修回日期:2021-06-11 接受日期:2021-07-29 出版日期:2021-08-31 发布日期:2021-10-11
通讯作者: Corresponding author: Wang Yawen, E-mail: wangyawen@bupt.edu.cn E-mail:wangyawen@bupt.edu.cn

Cross-project software defect prediction based on multi-source data sets

Huang Junfu, Wang Yawen, Gong Yunzhan, Jin Dahai

School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2019-10-18 Revised:2021-06-11 Accepted:2021-07-29 Online:2021-08-31 Published:2021-10-11
Contact: Corresponding author: Wang Yawen, E-mail: wangyawen@bupt.edu.cn E-mail:wangyawen@bupt.edu.cn

摘要/Abstract

摘要： Cross-project defect prediction (CPDP) uses one or more source projects to build a defect prediction model and applies the model to the target project. There is usually a big difference between the data distribution of the source project and the target project, which makes it difficult to construct an effective defect prediction model. In order to alleviate the problem of negative migration between the source project and the target project in CPDP, this paper proposes an integrated transfer adaptive boosting (TrAdaBoost) algorithm based on multi-source data sets (MSITrA). The algorithm uses an existing two-stage data filtering algorithm to obtain source project data related to the target project from multiple source items, and then uses the integrated TrAdaBoost algorithm proposed in the paper to build a CPDP model. The experimental results of Promise's 15 public data sets show that: 1) The cross-project software defect prediction model proposed in this paper has better performance in all tested CPDP methods; 2) In the within-project software defect prediction (WPDP) experiment, the proposed CPDP method has achieved the better experimental results than the tested WPDP method.

关键词: cross-project defect prediction, multi-source transfer adaptive boosting, ensemble learning

Abstract: Cross-project defect prediction (CPDP) uses one or more source projects to build a defect prediction model and applies the model to the target project. There is usually a big difference between the data distribution of the source project and the target project, which makes it difficult to construct an effective defect prediction model. In order to alleviate the problem of negative migration between the source project and the target project in CPDP, this paper proposes an integrated transfer adaptive boosting (TrAdaBoost) algorithm based on multi-source data sets (MSITrA). The algorithm uses an existing two-stage data filtering algorithm to obtain source project data related to the target project from multiple source items, and then uses the integrated TrAdaBoost algorithm proposed in the paper to build a CPDP model. The experimental results of Promise's 15 public data sets show that: 1) The cross-project software defect prediction model proposed in this paper has better performance in all tested CPDP methods; 2) In the within-project software defect prediction (WPDP) experiment, the proposed CPDP method has achieved the better experimental results than the tested WPDP method.

Key words: cross-project defect prediction, multi-source transfer adaptive boosting, ensemble learning

中图分类号:

TP311.5

Huang Junfu, Wang Yawen, Gong Yunzhan, Jin Dahai. Cross-project software defect prediction based on multi-source data sets[J]. The Journal of China Universities of Posts and Telecommunications, 2021, 28(4): 75-87.

参考文献

1. Wang Q, Wu S J, Li M S. Software defect prediction. Journal of Software, 2008, 19(7): 1565 -1580 (in Chinese)
2. Hall T, Beecham S, Bowes D, et al. A systematic literature review on fault prediction performance in software engineering. IEEE Transactions on Software Engineering, 2012, 38(6): 1276 -1304
3. Liu W S, Chen X, Gu Q, et al. A noise tolerable feature selection framework for software defect prediction. Chinese Journal of Computers, 2018, 41(3): 506 -520 (in Chinese)
4. Liu W S, Liu S L, Gu Q, et al. Empirical studies of a two-stage data preprocessing approach for software fault prediction. IEEE Transactions on Reliability, 2016, 65(1): 38 -53
5. Chen X, Zhao Y Q, Wang Q P, et al. Multi: multi-objective effort-aware just-in-time software defect prediction. Information and Software Technology, 2018, 93: 1 -13
6. Chen X, Zhang D, Zhao Y Q, et al. Software defect number prediction: unsupervised vs supervised methods. Information and Software Technology, 2019, 106: 161 -181
7. Liu W S, Chen X, Gu Q, et al. A cluster analysis based feature selection method for software defect prediction. Scientia Sinica-Informationis, 2016, 46(9): 1298 -1320 (in Chinese)
8. He J Y. Search based semi-supervised ensemble learning research for cross-project defect prediction. Master Thesis. Tianjin, China: Tianjin University, 2017
9. Chen X, Wang L P, Gu Q, et al. A survey on cross-project software defect prediction methods. Chinese Journal of Computers, 2018, 41(1): 254 -274 (in Chinese)
10. Nam J, Pan S J, Kim S. Transfer defect learning. Proceedings of the 35th International Conference on Software Engineering (ICSE'13), 2013, May 18 -26, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2013: 382 -391
11. Zimmermann T, Nagappan N, Gall H, et al. Cross-project defect prediction: a large scale experiment on data vs domain vs process. Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering (ESEC/FSE'09), 2009, Aug 24 -28, Amsterdam, Netherlauds. New York, NY, USA: ACM, 2009: 91 -100
12. Fukushima T, Kamei Y, McIntosh S, et al. An empirical study of just-in-time defect prediction using cross-project models. Proceedings of the 11th Working Conference on Mining Software Repositories (MSR'14), 2014, May 31 - Jun 1, Hyderabad, India. New York, NY, USA: ACM, 2014: 172 -181
13. He J Y, Meng Z P, Chen X, et al. Semi-supervised ensemble learning approach for cross-project defect prediction. Journal of Software, 2017, 28(6): 1455 -1473 (in Chinese)
14. Turhan B, Menzies T, Bener A B, et al. On the relative value of cross-company and within-company data for defect prediction. Empirical Software Engineering, 2009, 14(5): 540 -578
15. He P, Li B, Zhang D G, et al. Simplification of training data for cross-project defect prediction. Computer Ence, 2014: 1 -17
16. Turhan B, Menzies T, Bener A B, et al. On the relative value of cross-company and within-company data for defect prediction. Empirical Software Engineering, 2009, 14(5): 540 -578
17. Ma Y, Luo G C, Zeng X, et al. Transfer learning for cross-company software defect prediction. Information and Software Technology, 2012, 54(3): 248 -256
18. Peng L Z, Yang B, Chen Y H, et al. Data gravitation based classification. Information Sciences, 2009, 179(6): 809 -819
19. Panichella A, Oliveto R, Lucia A D. Cross-project defect prediction models: l' union fait la force. Proceedings of the 2014 Software Evolution Week-IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE'14), 2014, Feb 3 -6, Autwerp, Belgium. Piscataway, NJ, USA: IEEE, 2014: 164 -173
20. Ryu D, Jang J I, Baik J. A transfer cost-sensitive boosting approach for cross-project defect prediction. Software Quality Journal, 2017, 25(1): 235 -272
21. Chen L, Fang B, Shang Z W, et al. Negative samples reduction in cross-company software defects prediction. Infomration and Software Technology, 2015, 62: 67 -77
22. Yu X, Wu M, Jian Y H, et al. Cross-company defect prediction via semi-supervised clustering-based data filtering and MSTrA-based transfer learning. Soft Computing, 2018, 22: 3461 -3472
23. Herbold S. Training data selection for cross-project defect prediction. Proceedings of the 9th International Conference on Predictive Models in Software Engineering (PROMISE'13), 2013, Oct 9, Baltimore MD, USA. New York, NY, USA: ACM, 2013: 1 -10
24. Lewis D D. Naive (Bayes) at forty: the independence assumption in information retrieval. Machine Learning: Proceedings of the 10th European Conference on Machine Zearuing (ECML'98), 1998, Apr 21 -23, Chemnitz, Germany. LNAI 1398. Berlin, Germany: Springer, 1998: 4 -15
25. Menzies T, Greenwald J, Frank A. Data mining static code attributes to learn defect predictors. IEEE Transactions on Software Engineering, 2007, 33(1): 2 -13

[1]	王红熳李晋忠邢颖周晓光. Multi-objective test case prioritization based on multi-population cooperative particle swarm optimization[J]. 中国邮电高校学报(英文版), 2020, 27(1): 38-50.
[2]	Han Xu, Wang Hongsu, Zhang Sanqian, Fu Qunchao, Liu Jun. Sentence segmentation for classical Chinese based on LSTM with radical embedding[J]. 中国邮电高校学报(英文版), 2019, 26(2): 1-8.

Cross-project software defect prediction based on multi-source data sets

Cross-project software defect prediction based on multi-source data sets

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价