%0 Journal Article
%T 基于光滑样条回归的软件可靠性模型<br>Software Reliability Model Based on Smooth Splines Regression
%A 仇正霞
%A 杨剑锋
%A 胡文生
%A 黄嘉悦
%J Modeling and Simulation
%P 5156-5164
%@ 2324-870X
%D 2023
%I Hans Publishing
%R 10.12677/MOS.2023.126469
%X 随着软件产品在各行各业的广泛使用，其高可靠、高安全成为衡量一个软件质量的重要属性。本文引入了一种基于光滑样条回归的软件可靠性模型，并将其与传统的软件可靠性模型进行比较。此外，使用了最小二乘估计方法来估计模型中的参数。最后，基于开源软件Tomcat3-11服务器的真实失效数据，利用R软件对这4类可靠性模型进行性能对比分析，结果表明光滑样条回归模型的拟合与预测效果较好。<br />
With the widespread use of software products in various industries, their high reliability and secu-rity have become important attributes for assessing software quality. This paper introduces a soft-ware reliability model based on smooth spline regression and compares it with traditional software reliability models. In addition, the least squares estimation method is used to estimate the param-eters in the model. Finally, real failure data from the open-source Tomcat 3-11 server is used to perform a performance comparison analysis of these four types of reliability models using the R software. The results show that the smooth spline regression model provides better fitting and pre-dictive performance.
%K 光滑样条回归，软件可靠性模型，开源软件，失效数据<br>Smooth Spline Regression
%K Software Reliability Model
%K Open-Source Software
%K Failure Data
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=74998