Applied Multiresolution B-Spline Wavelet to Neural Network Model and Its Application to Predict Some Economics Data

摘要

A Method of wavelet neural network (WNN) is a neural network method with wavelet as an activate function. The architectural design of WNN models proposed in this research is a model of WNN Plus, the WNN model coupled with stage of pre-processing data. In this model, the excellence of wavelet method in terms of denoising is used at the stage of pre-processing data, and the excellence of wavelet multi-resolution is used at the hiden layer as an activate function. For the simulation, the result of this model is applied to predict the number of tourists visiting NTB Indonesia and sales volume of PT. Semen Gresik, Tbk Indonesia.