组合核相关向量机的软件可靠性预测模型

Software Reliability Prediction Model Based on Hybrid Kernels RVM

可靠性作为衡量软件质量的一种重要特性,对软件管理具有重要的意义。针对单一核函数的缺陷,提出一种组合核函数相关向量机的软件可靠性预测模型。首先对当前软件可靠性研究现状进行分析,然后采用组合核函数相关向量机对训练集进行学习和建模,最后通过具体实例对模型的预测性能进行分析。结果表明,本模型获得了理想的软件可靠性预测结果,且其预测性能要优于单一核函数模型,在软件可靠性预测中有重要的应用价值。

Reliability as an important measure of software quality,is of great significance to software management.A software reliability prediction model by using hybrid kernel function relevance vector machine was proposed in this paper to solve defects of single kernel function.Firstly,research status of software reliability is analyzed.Secondly,training samples are studied and modeled by using hybrid kernel function relevance vector machine.Finally,the prediction performance is analyzed with some specific examples.The results show that the proposed model can obtain ideal software reliability prediction results,and the performance is better than the single kernel function models,so it has important practical application value in software reliability prediction.