Kernel based partially linear models and nonlinear identification

被引：71

作者：

Espinoza, M ^{[1
]}

Suykens, JAK ^{[1
]}

De Moor, B ^{[1
]}

机构：

[1] Katholieke Univ Leuven, ESAT, SCD, Dept Elect Engn, B-3001 Heverlee, Belgium

来源：

IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2005年 / 50卷 / 10期

关键词：

kernels; least squares support vector machine (LS-SVM); nonlinear system identification; partially linear models;

D O I：

10.1109/TAC.2005.856656

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this note, we propose partially linear models with least squares support vector machines (LS-SVMs) for nonlinear ARX models. We illustrate how full black-box models can be improved when prior information about model structure is available. A real-life example, based on the Silverbox benchmark data, shows significant improvements in the generalization ability of the structured model with respect to the full black-box model, reflected also by a reduction in the effective number of parameters.

引用

页码：1602 / 1606

页数：5

共 18 条

[11] ROOT-N-CONSISTENT SEMIPARAMETRIC REGRESSION [J].

ROBINSON, PM .

ECONOMETRICA, 1988, 56 (04) :931-954

[12]

SCHOUKENS J, 2003, AUTOMATICA, V39

[13] Nonlinear black-box modeling in system identification: A unified overview [J].

Sjoberg, J ;

Zhang, QH ;

Ljung, L ;

Benveniste, A ;

Delyon, B ;

Glorennec, PY ;

Hjalmarsson, H ;

Juditsky, A .

AUTOMATICA, 1995, 31 (12) :1691-1724

[14]

SPECKMAN P, 1988, J R STAT SOC B, V50

[15]

Suykens J, 2002, Least squares support vector machine, DOI DOI 10.1142/9789812776655_0003

[16]

Vapnik V.N, 1998, Statistical learning theory

[17]

Wahba G., 1990, SPLINE MODELS OBSERV

[18]

Yu Y, 1998, NONLINEAR MODELING, P119

← 1 2 →