A polynomial smooth epsilon-support vector regression based on cubic spline interpolation  

作　　者：任斌 He Chunhong Liu Huijie Yang Lei Xie Guobo 

机构地区：[1]School of Electronic Engineering,Dongguan University of Technology [2]Guangdong Somens Electronic Technology CO.LTD [3]School of Computer,Guangdong University of Technology

出　　处：《High Technology Letters》2014年第2期187-194,共8页高技术通讯（英文版）

基　　金：Supported by Guangdong Natural Science Foundation Project(No.S2011010002144);Province and Ministry Production and Research Projects(No.2012B091100497,2012B091100191,2012B091100383);Guangdong Province Enterprise Laboratory Project(No.2011A091000046);Guangdong Province Science and Technology Major Project(No.2012A080103010)

摘　　要：Regression analysis is often formulated as an optimization problem with squared loss functions. Facing the challenge of the selection of the proper function class with polynomial smooth techniques applied to support vector regression models, this study takes cubic spline interpolation to generate a new polynomial smooth function ｜×｜ε^ 2, in g-insensitive support vector regression. Theoretical analysis shows that Sε^2 -function is better than pε^2 -function in properties, and the approximation accuracy of the proposed smoothing function is two order higher than that of classical pε^2 -function. The experimental data shows the efficiency of the new approach.Regression analysis is often formulated as an optimization problem with squared loss functions.Facing the challenge of the selection of the proper function class with polynomial smooth techniques applied to support vector regression models,this study takes cubic spline interpolation to generate a new polynomial smooth function |x|_ε~2 in ε-insensitive support vector regression.Theoretical analysis shows that S_ε~2-function is better than p_ε~2-function in properties,and the approximation accuracy of the proposed smoothing function is two order higher than that of classical p_ε~2-function.The experimental data shows the efficiency of the new approach.

关 键 词：support vector regression ε-insensitive loss function SMOOTH polynomial function cubic spline interpolation 

分 类 号：O241.3[理学—计算数学]