Research of Software Failure Prediction Based on Support Vector Regression

摘要：

　　Software failure prediction is eurrentiy a hot subject of research all over the world.The support vector regressions (SVRs) are very efficiency for solving regression problems.The parameters just as C 、ε 、γ performs very important roles in the generalization of SVR,and its hard for beginner to choose them.But in formar models,they dident care about this problem.A SVR-based generic model adaptive to the characteristic of the given data set is used for software failure time prediction.We also compare the prediction accuracy of software reliability prediction models based on 1-norm SVM,2-norm SVM,v-SVM and artificial neural network (ANN).Experimental results by four data sets show that the new software reliability prediction model could achieve higher prediction accuracy than that of the ANN-based or SVM-based models.

关键词： Software Reliability Prediction Support Vector Regression Artificial Neural Network

作者: Zheng Qiuhong

作者单位: College of Computer Science and Information Technology Zhejiang Wanli University Ningbo, China

会议类型: 国际会议

会议名称: 2012 2nd International Conference on Computer Application and System Modeling(2012第二届计算机应用与系统建模国际会议)(ICCASM-2012)

会议地点: 沈阳

会议语种:英文

页码: 1289-1292

在线出版日期: 2012-07-27（万方平台首次上网日期，不代表论文的发表时间）