Software Reliability Prediction using Neural Network with Encoded Input

Abstract

A neural network based software reliability model to predict the cumulative number of failures based on Feed Forward architecture is proposed in this paper. Depending upon the available software failure count data, the execution time is encoded using Exponential and Logarithmic function in order to provide the encoded value as the input to the neural network. The effect of encoding and the effect of different encoding parameter on prediction accuracy have been studied. The effect of architecture of the neural network in terms of hidden nodes has also been studied. The performance of the proposed approach has been tested using eighteen software failure data sets. Numerical results show that the proposed approach is giving acceptable results across different software projects. The performance of the approach has been compared with some statistical models and statistical models with change point considering three datasets. The comparison results show that the proposed model has a good prediction capability. General TermsSoftware reliability prediction, fault count prediction, neural network modeling.

Software development efforts prediction using artificial neural network

“…The learning process of ANN becomes complex using the original input variables. Logarithmic scaling function is used to capture the non-linear behaviour of software failure process in some models [42,43] for better ANN training. The ANN inputs are scaled into the range [0, 1] in different models for better learning in ANN [26,27,[44][45][46].…”

“…The ANN inputs are scaled into the range [0, 1] in different models for better learning in ANN [26,27,[44][45][46]. In the proposed ANN architecture, the same logarithmic function used in [42,43,47] is used as activation function in the additional input encoding layer. The logarithmic function is used to scale input values in the range of sigmoid transfer function.…”

Software Reliability Modeling using Soft Computing Techniques: Critical Review

“…Manjubala Bisi et al [33] proposed a neural network based software reliability model to predict the cumulative number of failures based on Feed Forward architecture. The effect of encoding and the effect of different encoding parameter on prediction accuracy have been studied and its performance is tested using eighteen software failure data sets.…”