A SVM regress forecasting method based on the fuzzy recognition theory

This paper first introduces the support vector machine(SVM)regression forecasting method into hydrological fore-casting.Further,based on the fuzzy recognition theory proposed by Prof. Chen Shou-yu,a new kind of kernel function of SVM is proposed in the paper. The kernel function has a more reasonable physical significance. At the end,the results of a study case show that the SVM regression hydrological forecasting method and the kernel function of fuzzy pattern recognition is rea-sonable and feasible.