KPCA feature extraction based on CBPSO algorithm
基于文化粒子群算法的KPCA特征提取*

How to choose the best or near kernel function to reduce test error rate is the key of KPCA applied to feature extraction.In order to the optimization of kernel function,increased the ability of feature extraction and decrease the test error rate,on the basis of research of CA,PSO,this paper proposed a program flow of CBPSO used for training kernel function and built CBPSO-KPCA.This approach could effectively optimize kernel function.Compared CBPSO-KPCA simulation results with GA-KPCA simulation results,it ...