Neural network based dynamic prediction of software reliability in integrated navigation system
Jiahai Zhang · Ha'erbin gongye daxue xuebao · 2005
Accurately predicting the number of faults in program modules is a major problem in quality control of a large scale integrated navigation software system.Based on software test records,the use of neural networks as a tool for dynamically predicting the number of faults in a program is explored.It indicates that the neural networks did produce models with better quality of fit and predictive quality than the traditional G-O model.