Research of Software Reliability Assessment Based on Neural Net Combination Model
Yanling Xu · Jisuanji fangzhen · 2010
In order to improve the accuracy of software reliability prediction,based on analyzing the classical software reliability models and neural network model,a neural network software reliability combination model is presented.The model realizes the combination of the software reliability model and neural network by constructing the transfer function corresponding to the selected base model.The neural network combination model can use a smaller size network to obtain satisfactory generalization.The results of experiment show that the neural network combination model can effectively improve the forecasting accuracy of software reliability.