[1]史作婷,吴 迪,荆晓远,等.类不平衡稀疏重构度量学习软件缺陷预测[J].计算机技术与发展,2018,28(06):125-128.[doi:10.3969/ j. issn.1673-629X.2018.06.028]
　SHI Zuo-ting,WU Di,JING Xiao-yuan,et al.Prediction of Defect of Class-imbalance Sparse Reconstruction Metric Learning Software[J].,2018,28(06):125-128.[doi:10.3969/ j. issn.1673-629X.2018.06.028]
点击复制

类不平衡稀疏重构度量学习软件缺陷预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年06期
页码:
125-128
栏目:
安全与防范
出版日期:
2018-06-10

文章信息/Info

Title:
Prediction of Defect of Class-imbalance Sparse Reconstruction Metric Learning Software
文章编号:
1673-629X(2018)06-0125-04
作者:
史作婷 1 ; 吴 迪 2 ; 荆晓远 2; 3 ; 吴 飞 3
1. 南京邮电大学 计算机学院,江苏 南京 210003;
2. 武汉大学 计算机学院 软件工程国家重点实验室,湖北 武汉 430072;
3. 南京邮电大学 自动化学院,江苏 南京 210003)
Author(s):
SHI Zuo-ting 1 ; WU Di 2 ; JING Xiao-yuan 2; 3 ; WU Fei 3
1. School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;
2. State Key Laboratory of Software Engineering,School of Computer,Wuhan University,Wuhan 430072,China;
3. School of Automation,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
软件缺陷预测; 类不平衡; 改进加权 KNN; 度量学习
Keywords:
software defect prediction; class-imbalance; IWKNN; metric learning
分类号:
TP31
DOI:
10.3969/ j. issn.1673-629X.2018.06.028
文献标志码:
A
摘要:
软件缺陷预测是提升软件质量的重要手段。 为了改善缺陷预测性能,目前许多机器学习领域的最新成果已经引入到软件缺陷预测中。 但是,软件缺陷预测数据通常存在类别分布不平衡的问题,这会影响预测效果。 针对这个问题,提出了类不平衡稀疏重构距离度量学习软件缺陷预测方法。该方法首先在度量学习中加入代价敏感因素,学习距离度量特征矩阵并解决软件缺陷预测中分类错误代价不同的问题。 其次,通过在目标函数中加入权重来进一步提高小类样本距离度量学习的准确性。最后,为了解决预测阶段数据集的类别不平衡问题,采用了改进加权 KNN 算法预测测试样本标签。在 NASA 软件缺陷预测标准数据集上的实验结果证明了该方法能提高召回率与 F -measure 值,改善分类性能。
Abstract:
Software defect prediction (SDP) is an important method to improve the quality of software. Currently many latest results from machine learning has been applied to improve the performance of defect prediction. However,imbalance of class distribution usually exists in SDP dataset,which might affect the prediction performance. For this,we propose a novel software defect prediction method termed class-imbalance sparse reconstruction metric learning (CSRML). In CSRML,by introducing cost-sensitive factor into metric learning,a feature matrix of distance metric can be learned and the problem of different cost of misclassification can also be solved. And weight parameter is added in objective function to further improve the accuracy of the small class samples distance metric learning. Finally,improved weighted KNN (IWKNN) method is employed to predict the label of test sample for tackling class imbalance in prediction phase.
Experiment on the NASA SDP dataset demonstrates that the proposed method can improve the recall rate, F -measure value and classification performance.

相似文献/References:

[1]黄明晓,荆晓远,李敏,等.基于主动学习的平衡类鉴别分析[J].计算机技术与发展,2014,24(06):95.
　HUANG Ming-xiao,JING Xiao-yuan,LI Min,et al.Class-balanced Discriminant Analysis Based on Active Learning[J].,2014,24(06):95.
[2]成希[][],荆晓远[],姚永芳[],等. 核化正交平衡类鉴别分析[J].计算机技术与发展,2015,25(01):133.
　CHENG Xi[][],JING Xiao-yuan[],YAO Yong-fang[],et al. Kernel Orthogonal Class-balanced Discriminant Analysis[J].,2015,25(06):133.
[3]陆海洋[],荆晓远[],董西伟[],等. 基于代价敏感学习的软件缺陷预测方法[J].计算机技术与发展,2015,25(11):58.
　LU Hai-yang[],JING Xiao-yuan[],DONG Xi-wei[],et al. Software Defect Prediction Based on Cost-sensitive Learning[J].,2015,25(06):58.
[4]王晴[],荆晓远[][],朱阳平[],等. 基于局部稀疏重构度量学习的软件缺陷预测[J].计算机技术与发展,2016,26(11):54.
　WANG Qing[],JING Xiao-yuan[][],ZHU Yang-ping[],et al. Software Defect Prediction of Metric Learning Based on Local Sparse Reconstruction[J].,2016,26(06):54.
[5]张志武[],荆晓远[][],吴飞[]. 基于非负稀疏图的协同训练软件缺陷预测[J].计算机技术与发展,2017,27(07):38.
　ZHANG Zhi-wu[],JING Xiao-yuan[] [],WU Fei[]. Defect Prediction of Co-training Software with Non-negative Sparse Graph[J].,2017,27(06):38.
[6]史雪静,吴 飞,荆晓远.基于改进 MDS 的软件缺陷预测[J].计算机技术与发展,2017,27(12):20.[doi:10.3969/ j. issn.1673-629X.2017.12.005]
　SHI Xue-jing,WU Fei,JING Xiao-yuan.Software Defect Prediction Based on Improved MDS[J].,2017,27(06):20.[doi:10.3969/ j. issn.1673-629X.2017.12.005]
[7]娄丰鹏,吴迪,荆晓远,等.增加度量元的迁移学习跨项目软件缺陷预测[J].计算机技术与发展,2018,28(07):103.[doi:10.3969/ j. issn.1673-629X.2018.07.022]
　LOU Feng-peng,WU Di,JING Xiao-yuan,et al.Cross-project Software Defect Prediction Based on Transfer Learning with Metrics[J].,2018,28(06):103.[doi:10.3969/ j. issn.1673-629X.2018.07.022]
[8]张洋洋,荆晓远,吴飞.基于迁移学习的跨项目软件缺陷预测[J].计算机技术与发展,2018,28(12):82.[doi:10．3969/j． issn．1673－629X．2018．12．018]
　ZHANG Yangyang,JING Xiaoyuan,WU Fei.Cross－project Software Defect Prediction Based on Transfer Learning[J].,2018,28(06):82.[doi:10．3969/j． issn．1673－629X．2018．12．018]
[9]李 昭,彭小红,谢仕义*,等.海洋资源大数据系统中缺陷多步预测方法[J].计算机技术与发展,2021,31(06):81.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 015]
　LI Zhao,PENG Xiao-hong,XIE Shi-yi*,et al.Multiple Steps for Predicting Number of Defects in MarineResources Big Data System[J].,2021,31(06):81.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 015]
[10]陆子豪,荆晓远.基于改进 SMOTE 的半监督极限学习机缺陷预测[J].计算机技术与发展,2021,31(12):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 004]
　LU Zi-hao,JING Xiao-yuan.Semi-supervised Extreme Learning Machine Based on Improved SMOTE for Software Defect Prediction[J].,2021,31(06):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 004]

更新日期/Last Update: 2018-08-21