基于多核集成学习的跨项目软件缺陷预测

详细信息    查看全文 | 推荐本文 |

英文篇名：Cross-project Software Defect Prediction Based on Multiple Kernel Ensemble Learning 作者：黄琳 ; 荆晓远 ; 董西伟 英文作者：HUANG Lin;JING Xiao-yuan;DONG Xi-wei;School of Automation,Nanjing University of Posts and Telecommunications; 关键词：跨项目缺陷预测 ; 多核学习 ; 集成学习 ; 代价敏感学习 ; 有监督学习 英文关键词：cross-project software defect prediction;;multiple kernel learning;;ensemble learning;;cost-sensitive learning;;supervised learning 中文刊名：WJFZ 英文刊名：Computer Technology and Development 机构：南京邮电大学自动化学院; 出版日期：2019-03-06 10:09 出版单位：计算机技术与发展 年：2019 期：v.29;No.266 基金：国家自然科学基金(61702280);国家自然科学基金重点项目通用技术基础研究联合基金(U1736211);; 江苏省自然科学基金(BK20170900);; 江苏省高等学校自然研究项目(17KJB520025);; 南京邮电大学引进人才科研启动基金(NY217009) 语种：中文; 页：WJFZ201906006 页数：5 CN：06 ISSN：61-1450/TP 分类号：33-37

摘要

软件缺陷预测的目的是通过历史缺陷数据预测新软件模块的缺陷倾向性,从而提高软件系统的质量。软件的缺陷模块存在结构复杂和类别分布不平衡的问题,并且历史数据是有限的。针对这些问题,提出了一种多核集成学习的跨项目软件缺陷预测方法。跨项目软件缺陷预测是解决项目初期缺陷预测缺乏数据集的有效途径。多核学习方法能够将不同特性的核函数进行组合,使数据在新的特征空间中得到更好的表达,提高预测精度。集成学习方法能够解决类别分布不平衡问题。考虑到在软件缺陷预测中将有缺陷模块预测为无缺陷模块的风险远远大于将无缺陷模块预测为有缺陷模块,在计算误差时引入了代价敏感矩阵。使用NASA和AEEEM这两个数据库来评估所有比较方法的性能,实验结果表明,提出的算法能够达到很好的效果。
        Software defect prediction aims to predict the defect proneness of new software modules with the historical defect data so as to improve the quality of software system. The defect modules of software have complex structure and unbalanced category distribution with limited historical data. In order to solve these problems,we propose a cross-project software defect prediction method based on multiple kernel ensemble learning. Cross-project software defect prediction is an effective way to solve the lack of datasets in the initial project defect prediction. Multiple kernel learning can combine kernel functions with different characteristics to make the data better expressed in the new feature space and improve the prediction accuracy. Ensemble learning can solve the problem of category distribution imbalance. Considering that the risk of predicting a defective module as a defect-free module in software defect prediction is far greater than predicting a defect-free module as a defective module,a cost-sensitive matrix is introduced in the calculation of the error. The NASA and AEEEM datasets as test data are used to evaluate the performance of all comparison methods. The experiment shows that the proposed algorithm is efficient.

引文

[1] 王青,伍书剑,李明树.软件缺陷预测技术[J].软件学报,2008,19(7):1565-1580.
    [2] 陈翔,顾庆,刘望舒,等.静态软件缺陷预测方法研究[J].软件学报,2016,27(1):1-25.
    [3] 李勇,黄志球,王勇,等.数据驱动的软件缺陷预测研究综述[J].电子学报,2017,45(4):982-988.
    [4] 李乔,郑啸.云计算研究现状综述[J].计算机科学,2011,38(4):32-37.
    [5] 王涛,李伟华,刘尊,等.基于支持向量机的软件缺陷预测模型[J].西北工业大学学报,2011,29(6):864-870.
    [6] LI Biwen,SHEN Beijun,WANG Jun,et al.A scenario-based approach to predicting software defects using compressed C4.5 model[C]//IEEE 38th annual computer software and applications conference.Vasteras,Sweden:IEEE,2014:406-415.
    [7] WANG Tao,LI Weihua.Naive bayes software defect prediction model[C]//International conference on computational intelligence and software engineering.Wuhan,China:IEEE,2010:1-4.
    [8] OKUTAN A,YILDIZ O T.Software defect prediction using Bayesian networks[J].Empirical Software Engineering,2014,19(1):154-181.
    [9] 缪林松.基于代价敏感神经网络算法的软件缺陷预测[J].电子科技,2012,25(6):75-78.
    [10] 熊婧,高岩,王雅瑜.基于Adaboost算法的软件缺陷预测模型[J].计算机科学,2016,43(7):186-190.
    [11] SUN Zhongbin,SONG Qinbao,ZHU Xiaoyan.Using coding-based ensemble learning to improve software defect prediction[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C (Applications and Reviews),2012,42(6):1806-1817.
    [12] JING Xiaoyuan,YING Shi,ZHANG Zhiwu,et al.Dictionary learning based software defect prediction[C]//Proceedings of the 36th international conference on software engineering.Hyderabad,India:ACM,2014:414-423.
    [13] ZHANG Zhiwu,JING Xiaoyuan,WANG Tiejian.Label propagation based semi-supervised learning for software defect prediction[J].Automated Software Engineering,2017,24(1):47-69.
    [14] JING Xiaoyuan,ZHANG Zhiwu,YING Shi,et al.Software defect prediction based on collaborative representation classification[C]//Companion proceedings of the 36th international conference on software engineering.Hyderabad,India:ACM,2014:632-633.
    [15] WANG Jun,SHEN Beijun,CHEN Yuting.Compressed C4.5 models for software defect prediction[C]//12th international conference on quality software.Xi’an,Shaanxi,China:IEEE,2012:13-16.
    [16] ZHENG Jun.Cost-sensitive boosting neural networks for software defect prediction[J].Expert Systems with Applications,2010,37(6):4537-4543.
    [17] XIA Hao,HOI S C H.MKBoost:a framework of multiple kernel boosting[J].IEEE Transactions on Knowledge and Data Engineering,2013,25(7):1574-1586.