基于高斯过程回归的软件可靠性模型

A Software Reliability Model Based on Gaussian Process Regression

传统软件可靠性模型通常过于依赖假设条件,难以适应复杂的实际情况。为此,本文提出了一种基于高斯过程回归(Gaussian Process Regression, GPR)的软件可靠性非参数模型。该模型结合了机器学习和高斯过程核,从失效数据中提取样本特征之间的相关关系。与传统可靠性模型相比,本文提出的模型具有更广泛的应用效果。通过对两组真实数据进行对比分析,结果显示本文提出的可靠性模型具有更好的拟合效果和预测能力。

Traditional software reliability models often rely too much on assumptions and are difficult to adapt to complex practical situations. Therefore, this paper proposes a nonparametric model of software reliability based on Gaussian Process Regression (GPR). The model combines machine learning and Gaussian process kernels to extract correlations between sample features from failed data. Compared with the traditional reliability model, the model proposed in this paper has a wider application effect. Through the comparative analysis of the two sets of real data, the results show that the reliability model proposed in this paper has better fitting effect and prediction ability.