基于迁移学习的软件缺陷预测

doi:10.3969/j.issn.0372-2112.2016.01.017

电子学报 ›› 2016, Vol. 44 ›› Issue (1): 115-122.DOI: 10.3969/j.issn.0372-2112.2016.01.017

基于迁移学习的软件缺陷预测

程铭^1,2, 毋国庆^1,2, 袁梦霆^1,2

1. 武汉大学计算机学院, 湖北武汉 430072;
2. 武汉大学软件工程国家重点实验室, 湖北武汉 430072

收稿日期:2014-06-06 修回日期:2015-05-14 出版日期:2016-01-25
- 作者简介:
- 程铭 男,1985年生于河南郑州,武汉大学计算机学院博士研究生,研究方向:软件工程、缺陷预测、机器学习. E-mail:chengming@whu.edu.cn 毋国庆 男,1954年生,教授,博士生导师,研究方向:软件工程、软件演化. E-mail:wgq@whu.edu.cn
- 基金资助:
- 国家自然科学基金 (No.91118003,No.61003071); 深圳战略性新兴产业发展专项资金 (No.JCYJ20120616135936123)

Transfer Learning for Software Defect Prediction

CHENG Ming^1,2, WU Guo-qing^1,2, YUAN Meng-ting^1,2

1. School of Computer, Wuhan University, Wuhan, Hubei 430072, China;
2. State Key Lab of Software Engineering, Wuhan University, Wuhan, Hubei 430072, China

Received:2014-06-06 Revised:2015-05-14 Online:2016-01-25 Published:2016-01-25
- Supported by:
- National Natural Science Foundation of China (No.91118003, No.61003071); Special Fund for the Development of Strategic Emerging Industries in Shenzhen, Guangdong Province (No.JCYJ20120616135936123)

摘要/Abstract

摘要：

传统软件缺陷预测方法在解决跨项目缺陷预测过程中适应能力不足,主要是因为源项目和目标项目之间存在不同的特征分布.为了解决这个问题,提出一种新的加权贝叶斯迁移学习算法,算法首先收集训练数据和测试数据的特征信息,然后计算特征差异,将不同项目数据之间差异转化为训练数据权重,最后基于这些权重数据建立预测模型.在8个开源项目数据集上进行实验比较,实验结果表明与其他方法相比本文方法显著提高跨项目缺陷预测性能.

关键词: 软件缺陷预测, 迁移学习, 机器学习, 朴素贝叶斯

Abstract:

The traditional software defect prediction methods have weak adaptive ability for cross-project defect prediction, largely because of feature distribution differences between the source and target projects.In order to resolve this problem, we propose a novel weighted naive Bayes transfer learning algorithm.Firstly, the feature information of the test data and training data are collected;next, our solution computes feature differences, and transfers cross-project data differences into the weights of the training data;finally, on these weighted data, the defect prediction model is built.Our experiments are conducted on eight open-source projects, and experimental results demonstrate that our method significantly improves cross-project defect prediction performance, compared to other methods.

Key words: software defect prediction, transfer learning, machine learning, naive Bayes

中图分类号:

TP311

程铭, 毋国庆, 袁梦霆. 基于迁移学习的软件缺陷预测[J]. 电子学报, 2016, 44(1): 115-122.

CHENG Ming, WU Guo-qing, YUAN Meng-ting . Transfer Learning for Software Defect Prediction[J]. Acta Electronica Sinica, 2016, 44(1): 115-122.

参考文献

[1] Pizzi N J.A fuzzy classifier approach to estimating software quality[J].Information Sciences, 2013, 241:1-11.
[2] Jing X Y, Ying S, et al.Dictionary learning based software defect prediction[A].Proceedings of the 36th International Conference on Software Engineering[C].Hyderabad:ACM, 2014.414-423.
[3] Wang J, Shen B J, Chen Y T.Compressed C4.5 models for software defect prediction[A].Proceedings of the 12th International Conference on Quality Software[C].Xi'an:IEEE, 2012.13-16.
[4] 姜慧研, 宗茂, 刘相莹.基于ACO-SVM的软件缺陷预测模型的研究[J].计算机学报, 2011, 34(6):1148-1154. Jiang Hui-yan, Zong Mao, Liu Xiang-ying.Research of software defect prediction model based on ACO-SVM[J].Chinese Journal of Computers, 2011, 34(6):1148-1154.(in Chinese)
[5] Zimmermann T, Nagappan N, et al.Cross-project defect prediction[A].Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on Foundations of Software Engineering[C].Amsterdam:ACM, 2009.91-100.
[6] Pan S J, Yang Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[7] Turhan B, Menzies T, et al.On the relative value of cross-company and within-company data for defect prediction[J].Empirical Software Engineering, 2009, 14(5):540-578.
[8] Canfora G, Lucia A D, et al.Multi-objective cross-project defect prediction[A].Proceedings of the 6th IEEE International Conference on Software Testing, Verification and Validation[C].Luxembourg:IEEE, 2013.252-261.
[9] Nam J, Pan S J, et al.Transfer defect learning[A].Proceedings of the 35th International Conference on Software Engineering[C].San Francisco:ACM/IEEE, 2013.382-391.
[10] Ma Y, Luo G C, et al.Transfer learning for crosscompany software defect prediction[J].Information and Software Technology, 2012, 54(3):248-256.
[11] Peng L Z, Yang B, et al.Data gravitation based classification[J].Information Sciences, 2009, 179(6):809-819.
[12] Wang C, Chen Y Q.Improving nearest neighbor classification with simulated gravitational collapse[A].Proceedings of the First International Conference on Natural Computation[C].Changsha:Springer-Verlag, 2005.845-854.
[13] Frank E, Hall M, et al.Locally weighted naive Bayes[A].Proceedings of the 9th International Conference on Uncertainty in Artificial Intelligence[C].San Francisco:Morgan Kaufmann, 2003.249-256.
[14] D'Ambros M, Lanza M, et al.An extensive comparison of bug prediction approaches[A].Proceedings of the 7th IEEE Working Conference on Mining Software Repositories[C].Cape Town:IEEE, 2010.31-41.
[15] Wu R X, Zhang H Y, et al.Relink:recovering links between bugs and changes[A].Proceedings of the 19th ACM SIGSOFT Symposium and the Thirteenth European Conference on Foundations of Software Engineering[C].Szeged:ACM, 2011.15-25.
[16] Bird C, Bachmann A, et al.Fair and balanced?:bias in bug-fix datasets[A].Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on Foundations of Software Engineering[C].Amsterdam:ACM, 2009.121-130.

基于迁移学习的软件缺陷预测

Transfer Learning for Software Defect Prediction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴军君, 王涛, 王英楷, 王星辉. 基于迁移学习的LiPON制备工艺模拟优化[J]. 电子学报, 2023, 51(3): 687-693.
[2]	杨威, 李玮杰, 刘永祥, 黎湘. 基于测地线流式核的雷达目标高分辨距离像鲁棒识别方法[J]. 电子学报, 2023, 51(3): 527-536.
[3]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[4]	邵志文, 周勇, 谭鑫, 马利庄, 刘兵, 姚睿. 基于深度学习的表情动作单元识别综述[J]. 电子学报, 2022, 50(8): 2003-2017.
[5]	黄璐, 蔚保国, 李宏生, 李隽, 贾浩男, 程建强, 李雅宁. GNSS拒止环境下的伪卫星指纹定位方法[J]. 电子学报, 2022, 50(4): 811-822.
[6]	崔亚奇, 何友, 唐田田, 熊伟. 一种深度学习航迹关联方法[J]. 电子学报, 2022, 50(3): 759-763.
[7]	李维刚, 甘平, 谢璐, 李松涛. 基于样本对元学习的小样本图像分类方法[J]. 电子学报, 2022, 50(2): 295-304.
[8]	蒋华伟, 郭陶, 杨震. 车辆路径问题研究进展[J]. 电子学报, 2022, 50(2): 480-492.
[9]	张笑宇, 沈超, 蔺琛皓, 李前, 王骞, 李琦, 管晓宏. 面向机器学习模型安全的测试与修复[J]. 电子学报, 2022, 50(12): 2884-2918.
[10]	郑锐, 汪秋云, 林卓庞, 靖蓉琦, 姜政伟, 傅建明, 汪姝玮. 一种基于威胁情报层次特征集成的挖矿恶意软件检测方法[J]. 电子学报, 2022, 50(11): 2707-2715.
[11]	陈文俊, 杨春玲. 图像压缩感知的特征域优化及自注意力增强神经网络重构算法[J]. 电子学报, 2022, 50(11): 2629-2637.
[12]	张小恒, 张馨月, 李勇明, 王品, 刘玉川. 面向帕金森病语音诊断的非监督两步式卷积稀疏迁移学习算法[J]. 电子学报, 2022, 50(1): 177-184.
[13]	李勇斌, 王彬, 邵高平, 邵帅. 一种基于RCGAN的水声通信信号降噪方法[J]. 电子学报, 2022, 50(1): 54-62.
[14]	张梦, 郑建宏, 刘香燕, 何云. 基于集成学习的全双工中继系统安全中继选择方案研究[J]. 电子学报, 2021, 49(9): 1852-1856.
[15]	郑海颖, 王峰, 姜维, 王志强, 姚西文. 神经网络训练策略对高分辨率遥感图像场景分类性能影响的评估[J]. 电子学报, 2021, 49(8): 1599-1614.