Abstract
An evolutionary neural network modeling approach for software cumulative failure prediction based on feed-forward neural network is proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training a neural network established by Aljahdali S.. In this paper we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train feed-forward neural network. We describe the genetic algorithm and we also experimentally compare our approach with the back propagation learning algorithm for the regression model order 4. Numerical results show that both the goodness-of-fit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure compared to other approaches.