Study on Construction of Kernel Function and Parameter Optimization in Support Vector Regression

被引：0

作者：

Tian, Jin ^{[1
]}

机构：

[1] Capital Univ Econ & Business, Informat Coll, Beijing, Peoples R China

来源：

MANUFACTURING, DESIGN SCIENCE AND INFORMATION ENGINEERING, VOLS I AND II | 2015年

关键词：

support vector regression; machine learning; kernel function; parameter optimization; MACHINE;

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Based on machine learning concepts this paper puts forward the two key problems of the application of support vector regression: the selection of forecast factors and the quality of sample set is the prerequisite foundation; the selection of the optimal function is the key core. The solutions to these problems are given. Mainly according to different characteristics of the sample data the schemes of the selection and structure of kernel function and parameter optimization methods are proposed.

引用

页码：1434 / 1442

页数：9

共 13 条

[1]

Hongqiao W. yanning C., 2014, MULTIPLE KERNERL MET

[2]

Jun S., 2011, QUANTUM BEHAV PARTIC

[3]

Meyer D., 2002, 78 VIENN U EC BUS AD, P23

[4]

Tao W., 2003, THESIS

[5] Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization [J].

Üstün, B ;

Melssen, WJ ;

Oudenhuijzen, M ;

Buydens, LMC .

ANALYTICA CHIMICA ACTA, 2005, 544 (1-2) :292-305

[6]

Vladimir N. V., 2004, STAT LEARNING THEORY

[7]

Wei C., 2011, APPL RES COMPUTERS, V28, P182

[8]

Wenjian W., 2014, SUPPORT VECTOR MACHI

[9]

Yanfang Y., 2010, THESIS

[10]

Yang Z, 2006, LECT NOTES COMPUT SC, V3971, P1030

← 1 2 →