The Application of Wavelet Neural Network Based on Orthogonal Scaling Function in Tax Forecasting
LI Huai-zu · Journal of systems management · 2006
In this paper,a wavelet-based neural network is given.The structure of this network is similar to that of the radial basis function(RBF) network,except that here the radial basis functions are replaced by orthogonal scaling functions.Furthermore,the paper proposes the algorithms for the wavelet network. Finally,a tax forecasting based on the sample of tax data(1978～2001) in China is presented,which shows that the forecasting error is less than that of BP network.