PCNN Forecasting Model Based on Wavelet Transform and Its Application
Qiang Fu, Yan Feng, Deng-chao Feng · 2007
Pulse Coupled Neural Network (PCNN) is widely used in image processing for its basic characteristics of coupling mechanism and achieved some results.PCNN model has been improved as follows: Firstly, correlation coefficient is used to control the bonding strength.Secondly, the threshold setting is adjusted by the least error.Thirdly, A Trous transform is combined with PCNN model to form the combination forecasting model.The improved combination model was implemented in annual rainfall forecasting to check its feasibility.