An Analysis of Software Reliability Assessment with Neuro-Fuzzy based Expert Systems

We propose software reliability assessment methods by using neuro-fuzzy based systems and their effectiveness in assessing the Software Reliability. Also, we make a comparison between the neural networks based software reliability growth model and the fuzzy logic based software reliability growth models based on a homogeneous Poisson process applied to software reliability assessment of the entire system composed of several software components. Moreover, we analyze software fault count data to show numerical examples of software reliability assessment with the implementation of Neuro-Fuzzy systems based approach. Furthermore, we investigate the performance of an efficient software reliability assessment methods in this context. Also, we had shown the implementation of the approach by using Java programming language with some programs. We used the normalized root mean square error (NRMSE) as evaluation criteria. The experiments show that the non-parametric models are superior when compared to the parametric models in their ability to provide an accurate estimate when historical data is missing. A comparison among the neural network and fuzzy logic models are provided. (C) 2015 The Authors, Published by Elsevier B.V.