基于遗传优化支持向量机的软件缺陷预测模型  

Software defect prediction model based on support vector machine optimized by genetic algorithm

作　　者：王男帅[1] 薛静锋[2] 胡昌振[2] 单纯[2] 李志强[2] 

机构地区：[1]北京理工大学计算机学院,北京100081 [2]北京理工大学软件学院,北京100081

出　　处：《中国科技论文》2015年第2期159-163,共5页China Sciencepaper

基　　金：高等学校博士学科点专项科研基金资助项目(20131101120043);国防基础科研计划项目(B1120132031)

摘　　要：有效的软件缺陷预测能够显著提高软件安全测试的效率,确保软件质量,支持向量机(support vector machine,SVM)具有非线性运算能力,是建立软件缺陷预测模型的较好方法,但其缺少统一有效的参数寻优方法。本文针对该问题提出一种基于遗传优化支持向量机的软件缺陷预测模型,将支持向量机作为软件缺陷预测的分类器,利用遗传算法进行最优度量属性的选择和支持向量机最优参数的计算。实验结果表明,基于遗传优化支持向量机的软件缺陷预测模型具有较高的预测准确度。Effective software defect prediction can improve the efficiency of software testing greatly,and is an important approach for guaranteeing the quality of software.Since support vector machine(SVM)is designed for nonlinear calculation,it is a good method to build software defect prediction model.But there is still lack unified and effective method for SVM's parameter optimization.In this paper,a software defect prediction model based on SVM optimized by genetic algorithm(GA)is proposed,in which the SVM is applied as the prediction classifier and the GA is used to select the optimal metric attributes and calculate the optimal parameters of SVM.Experimental results show that proposed model presents higher prediction accuracy on software defect prediction than the traditional models.

关 键 词：软件安全 软件缺陷预测 支持向量机 遗传算法 

分 类 号：TP311.53[自动化与计算机技术—计算机软件与理论]