基于和声搜索优化支持向量回归的软件可靠性预测

Software Reliability Prediction Based on Harmony Search Optimization Support Vector Regression

为了提高软件可靠性预测的精确率,采用支持向量机理论对软件可靠性建模,并对支持向量回归中参数优化难的问题,使用和声搜索算法优化支持向量回归中的参数,提出了一种基于和声搜索优化支持向量回归的软件可靠性预测模型。使用两组真实数据对提出的模型进行实验,并将实验结果与经典软件可靠性模型(G-O模型和M-O模型)进行比较,结果表明:基于和声搜索优化支持向量回归的软件可靠性预测模型的预测精度更高。

In order to improve the accuracy of software reliability prediction,the support vector machine theory is used to model software reliability.And for the difficulty of parameter optimization in support vector regression,the harmony search algorithm is used to optimize the parameters in support vector regression,and a software reliability prediction model based on harmony search optimization support vector is proposed.Two groups of real data are used to test the proposed model,and the experimental results are compared with the classical softwares(G-O model and M-O model).The experimental results show that the software reliability prediction model based on harmony search optimization support vector regression has higher prediction accuracy.