Entropy-Based Two-Dimensional Software Reliability Growth Modeling for Open-Source Software Incorporating Change-Point

Abstract

This study provides an analytical model to predict the fixing pattern of issues in the open-source software (OSS) packages to assist developers in software development and maintenance. Moreover, the continuous evolution of software due to bugs removal, new features addition or existing features modification results in the source code complexity. The proposed model quantifies the complexity in the source code using the Shannon entropy measure. In addition, the issues fixing growth behavior is viewed as a function of continuation time of the software in the field environment and amount of uncertainty or complexity present in the source code. Therefore, a two-dimensional function called Cobb–Douglas production function is applied to model the intensity function of the issues fixing rate. Furthermore, the rate of fixing the different issue types is considered variable that may alter after certain time points. Thus, this study incorporates the concept of multiple change-points to predict and assess the fixing behavior of issues in the software system. The performance of the proposed model is validated by fitting the proposed model to the actual issues data of three open-source projects. Findings of the data analysis exhibit excellent prediction and estimation capability of the model.

A novel CRITIC‐TOPSIS approach for optimal selection of software reliability growth model (SRGM)

“…The calculated results are shown in Table 13 for data set 1. Finally, Relative closeness (𝑡 𝑚 )of each SRGM is obtained by using Equation (11) as shown in Table 13. SRGMs are ranked using the numerical values of Relative closeness.…”

Open source software reliability model with nonlinear fault detection and fault introduction

“…Experimental results showed that the fitting performance of the proposed models was better than those of traditional closed software reliability models. Similarly, Kapur et al 34 proposed a two-dimensional reliability model of OSS-based entropy and changing-point. Utkin and Coolen 35 proposed an imprecise weight software reliability models-based support vector regression.…”

Software reliability prediction and release time management with coverage

“…Change point is that time point at which the hazard function of fault detection modifies. This change can be attributed to various factors such as an alteration in the testing environment, resource allocation, testing strategy and integration testing (Zhao et al, 2006;Kapur et al, 2020). In the present study, the strategic software timeto-market policy based on cost-reliability criteria is suggested.…”

“…These models are based on the presumption that defects identified in the testing phase are removed instantly with no debugging time delay, no new defect generation, and software used in the user environment is like the one used in the development process. So far, more than a hundred of SRGMs have been proposed by relaxing the assumptions of initial studies (Kapur and Garg, 1992;Kapur et al, 2011bKapur et al, , 2020Yamada, 2014;Kumar et al, 2018b;Asraful Haque and Ahmad, 2021;Nafreen and Fiondella, 2021). Some efforts have been made to incorporate the concept of imperfect debugging and error generation in the fault detection phenomenon to reflect a realistic testing process (Xie and Yang, 2003;Kapur et al, 2011a;Wang et al, 2015;Verma et al, 2021).…”

“…Change point refers to a time point at which the model parameters encounter discontinuity. Recently, Kapur et al (2020) incorporated the concept of multiple change points to predict and assess the fixing behavior of issues in the Open Source Software (OSS) system.…”