期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2013
卷号：10
期号：4
出版社：IJCSI Press
摘要：Due to the growth in demand for software with high reliability and safety, software reliability prediction becomes more and more essential. Software reliability is a key part of software quality. Over the years, many software reliability models have been successfully utilized in practical software reliability engineering, however, no single model can obtain accurate prediction for all cases. So in order to improve the accuracy of software reliability prediction the proposed model combine the software reliability models with the neural networks (NN). Particle swarm optimization (PSO) algorithm has been chosen and applied for learning process to select the best architecture of the neural network. The applicability of the proposed model is demonstrated through three software failure data sets. The results show that the proposed model has good prediction capability and more applicable for software reliability prediction.
