Wavelet Neural Networks Based on Fuzzy C-Means Clustering and its Application in the Runoff Forecast
Xu Jin, Wei Zhong · Shuxue de shijian yu renshi · 2012
A new method of a runoff forecast based on fuzzy clustering analysis for forecasting factor sets is presented.The historical runoff data are divided into four categories using the fuzzy C-means clustering.Then the part forecasting model between forecasting factor's class variable characteristic value and observation value is established by use of wavelet neural network model.Designed the categorized recognizer of characteristic value can automatically search adapting network model to forecast.As an example,a comparison is made between single wavelet neural model and forecasting model proposed in this paper. The results show that the forecasting precision of the latter is higher than that of former.