遗传优化支持向量机在软件缺陷预测中的应用  

The application of genetic algorithm support vector machine in software defect prediction

作　　者：王培[1] 金聪[1] 

机构地区：[1]华中师范大学计算机科学系,武汉430079

出　　处：《电子测量技术》2012年第2期126-129,共4页Electronic Measurement Technology

基　　金：教育部人文社会科学研究规划基金(No.11YJAZH040)资助项目

摘　　要：软件开发过程中对软件模块的可靠性进行预测可以有效地提高软件的质量。支持向量机可应用于建立软件缺陷预测模型。为提高预测模型的分类准确度,利用遗传优化算法选择出最优属性子集,从而降低数据样本中冗余属性带来的不利影响,利用支持向量机建立了一种高效的软件缺陷预测模型。实验结果表明,基于遗传算法和支持向量机建立的预测模型能够为软件缺陷预测提供较高的预测精度和效率,有着良好的应用前景。Predicting defect-prone software modules accurately and effectively is a useful way to improve the quality of a software system during software development.Support vector machine（SVM） can be applied in building software defect prediction model.An approach based on Support vector machine has been used to establish the high efficient software defect prediction model.Genetic algorithm（GA） is introduced to improve the accuracy of the prediction model by selecting the optimal feature subset.It helps eliminating the adverse effect caused by redundant features in datasets.The experiment results show that all the classifiers achieve higher accuracy and performance by using the proposed approach based on genetic algorithm and support vector machine.

关 键 词：软件缺陷预测 支持向量机 遗传算法 属性选择 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]