Software fault prediction based on grey neural network

Abstract

Considering determining the number of software fault is an uncertain non-linear problem with only small sample, a novel software fault prediction method based on grey neural network is put forward. Firstly, constructing the grey neural network topological structure according the small sample sequence is necessary, and then the network learning algorithm is discussed. Finally, the grey neural network prediction model based on the grey theory and artificial neural network is proposed. The sample fault sequences of some software project are used to verify the precision of this method. Comparison with GM(1,1), the proposed model can reduce the prediction relative error effectively.