A Unique Procedure for Accurate Recognition of Software Failures: A Software Reliability Growth Model Based on Special Case of Generalized Gamma Mixture Model
Jagadeesh Medapati1, Anand Chandulal Jasti2, TV Rajinikanth3
1Jagadeesh Medapati*, Department of Computer Science and Engineering, GITAM University, Visakhapatnam, Andhra Pradesh, India.
2Anand Chandulal Jasti, Department of Computer Science and Engineering, GITAM University, Visakhapatnam, Andhra Pradesh, India.
3TV Rajinikanth, Department of Computer Science and Engineering, Srinidhi Institute of Technology, Hyderabad, Telangana, India.
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 1932-1938 | Volume-8 Issue-6, August 2019. | Retrieval Number:F7926088619/2019©BEIESP| DOI: 10.35940/ijeat.F7926.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper pinpoints to detect and eliminate the actual software failures efficiently. The approach fit in a particular case of Generalized Gamma Mixture Model (GGMM), namely Weibull distribution. The approach estimates two parameters using Maximum Likelihood Estimate (MLE). Standard Evaluation metrics like Mean Square Error (MSE), Coefficient of Determination (R2), Sum of Squares (SSE), and Root Means Square Error (RMSE) were calculated. For the justification of the model selection and goodness of fit various model selection frameworks like Chi-Square Goodness of Fit, Wald’s Test, Akaike Information Criteria (AIC), AICc and Schwarz criterion (SBC) were also estimated. The experimentation was carried out on five benchmark datasets which interpret the considered novel technique identifies the actual failures on par with the existing models. This paper presents a novel software reliability growth model which is more effectual in the identification of the failures significantly and help the present software organizations in the release of software free from bugs just in time.
Keywords: Benchmark Datasets, Error, Generalized Gaussian Mixture Model, Reviews, Software Reliability.