基于半监督学习的多源软件缺陷预测模型
Multi-Source Software Defect Prediction Model Based on Semi-Supervised Learning
DOI: 10.12677/SEA.2020.92014, PDF,  被引量    科研立项经费支持
作者: 于龙海, 吴晓鸰*, 凌 捷, 许遵鸿：广东工业大学，广东 广州
关键词: Self-Training；软件缺陷预测；多源软件；Self-Training； Software Defect Prediction； Multi-Source Software
摘要: 本文研究在不同的软件项目之间，建立通用软件缺陷预测模型的方法。通过分析多源软件的项目信息，本文设计了25维软件特征用于机器学习。为了克服不同软件项目之间的代码区别，实现模型的通用性，使用基于半监督学习Self-training自训练算法生成分类器。最后利用本文设计的25维数据特征建立训练数据，通过Self-training算法生成通用的多源软件缺陷预测模型。
Abstract: This paper studies the method of establishing a general software defect prediction model between different software projects. By analyzing the project information of multi-source software, this paper designs 25-dimensional software features for machine learning. In order to overcome the differences between different software projects and achieve the generality of the model, a Self-training algorithm based on semi-supervised learning is used to generate a classifier. Finally, the 25-dimensional data features are used to build training data, and a general multi-source software defect prediction model is generated by the Self-training algorithm.
文章引用：于龙海, 吴晓鸰, 凌捷, 许遵鸿. 基于半监督学习的多源软件缺陷预测模型[J]. 软件工程与应用, 2020, 9(2): 116-123. https://doi.org/10.12677/SEA.2020.92014

参考文献

[1] 张志武. 基于机器学习的软件缺陷预测方法研究[D]: [博士学位论文]. 南京: 南京邮电大学, 2018.
[2] 黄琳. 基于度量元的静态跨项目软件缺陷预测技术研究[D]: [硕士学位论文]. 南京: 南京邮电大学, 2019.
[3] 李梦奇. 基于机器学习的软件缺陷预测方案研究[D]: [硕士学位论文]. 北京: 北京邮电大学, 2019.
[4] Zhang, F., Hassan, A.E., Mclntosh, S., et al. (2017) The Use of Summation to Aggregate Software Metrics Hinders the Performance of Defect Prediction Models. IEEE Transactions on Software Engineering, 43, 476-491. [Google Scholar] [CrossRef] 
[5] Yu, Q., Jiang, S., Wang, R., et al. (2017) A Feature Se-lection Approach Based on a Similarity Measure for Software Defect Prediction. Frontiers of Infornation Technology & Electronic Engineering, 18, 1744-1753. [Google Scholar] [CrossRef] 
[6] Ryu, D., Jang, J. and Baik. J. (2017) A Transfer Cost-Sensitive Boosting Approach for Cross-Project defect Prediction. Software Quality Journal, 25, 235-272. [Google Scholar] [CrossRef] 
[7] Shi, Y., Li, M., Arndt, S., et al. (2017) Metric-Based Software Reliability Prediction Approach and Its Applocation. Emprical Software Engineering, 22, 1579-1633. [Google Scholar] [CrossRef] 
[8] Jing, X.Y., Wu, F., Dong, X., et al. (2017) An Improved SDA Based Defect Prediction Framework for Both Within-Project and Cross-Project Class-Imbalance Problems. IEEE Transactions on Software Engineering, 43, 321-339. [Google Scholar] [CrossRef] 
[9] 何清. 基于半监督学习和投票决策理论的软件缺陷预测[D]: [硕士学位论文]. 上海: 上海交通大学, 2017.

为你推荐