期刊文献+

基于贡献者行为特征的开源软件缺陷预测研究

Research on open source software defect prediction based on characteristic behavior of contributors
下载PDF
导出
摘要 针对开源软件存在缺陷,改善软件质量等问题,文章提出了基于贡献者行为特征的开源软件缺陷预测研究。首先获取Apache软件基金会中的开源软件项目,运用Git和SVN版本控制系统对开发人员日志信息提取;然后采用K均值聚类算法模型挖掘开发人员团队(贡献者),采用词频统计和主成分分析算法模型得到贡献者行为特征;最后利用随机森林算法实现对贡献者特征行为的软件缺陷预测,该实验结果具有一定的参考意义。 Aiming at the problems of open source software defects and improving software quality,this paper puts forward a research on open source software defect prediction based on the behavior characteristics of contributors.First,obtain the open source software project in the Apache Software Foundation,and use GIT and SVN version control system to extract the developer’s log information;Then,the K-means clustering algorithm model is used to mine the developer team(contributors),and the word frequency statistics and principal component analysis algorithm model are used to obtain the behavior characteristics of contributors;Finally,the random forest algorithm is used to predict the software defects of contributors’characteristic behavior.The experimental results have certain reference significance.
作者 黄亚蒙 马璐璐 Huang Yameng;Ma Lulu(Huanghe Jiaotong University,Jiaozuo 454950,China;Zhengzhou Technical College,Zhengzhou 450100,China)
出处 《无线互联科技》 2023年第2期74-76,共3页 Wireless Internet Technology
基金 2021年度黄河交通学院校级课程教学资源库建设项目,项目名称:智能科学与技术导论,项目编号:HHJTXY-2021kczyk102 2021年黄河交通学院校级一流课程项目,项目编号:HHJTXY-2021ylkc04。
关键词 开源软件 行为特征 软件缺陷预测 open source software behavioral characteristics software defect prediction
  • 相关文献

参考文献4

二级参考文献70

  • 1费洪晓,康松林,朱小娟,谢文彪.基于词频统计的中文分词的研究[J].计算机工程与应用,2005,41(7):67-68. 被引量:68
  • 2胡海波,王林.幂律分布研究简史[J].物理,2005,34(12):889-896. 被引量:87
  • 3Wang Q, Wu S J, Li M S. Software defect prediction. J Softw, 2008, 19:1565-1580.
  • 4Hall T, Beecham S, Bowes D, et al. A systematic literature review on fault prediction performance in software engineering. IEEE Trans Softw Eng, 2012, 38:1276-1304.
  • 5Yu S S, Zhou S G, Guan J H. Software engineering data mining: a survey. J Front Comput Sci Tech, 2012, 6:1-31.
  • 6Chen X, Gu Q, Liu W S, et al. Survey of static software defect prediction. J Softw, 2016, 1:1-25.
  • 7Ghotra B, McIntosh S, Hassan A E. Revisiting the impact of classification techniques on the performance of defect prediction models. In: Proceedings of the International Conference on Software Engineering, Firenze, 2015. 789 -800.
  • 8Peters F, Menzies T, Layman L. LACE2: better privacy-preserving data sharing for cross project defect prediction. In: Proceedings of the International Conference on Software Engineering, Firenze, 2015. 801-811.
  • 9Tantithamthavorn C, McIntosh S, Hassan A E, et al. The impact of mislabelling on the performance and interpretation of defect prediction models. In: Proceedings of the International Conference on Software Engineering, Firenze, 2015. 812-823.
  • 10Jing X Y, Wu F, Dong X W, et M. Heterogeneous cross-company defect prediction by unified metric representation and CCA-based transfer learning. In: Proceedings of the International Symposium on Foundations of Software Engineering, Bergamo, 2015. 496-507.

共引文献161

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部