Nonlinear system identification with composite relevance vector machines

被引：22

作者：

Camps-Valls, Gustavo ^{[1
]}

Martinez-Ramon, Manel

Rojo-Alvarez, Jose Luis

Munoz-Mari, Jordi

机构：

[1] Univ Valencia, Escola Tecn Super Engn, Dept Elect Engn, Valencia 46100, Spain

[2] Univ Carlos III Madrid, Dept Teoria Senal & Comunicac, Madrid, Spain

来源：

IEEE SIGNAL PROCESSING LETTERS | 2007年 / 14卷 / 04期

关键词：

composite kernels; nonlinear system identification; relevance vector machine (RVM);

D O I：

10.1109/LSP.2006.885290

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Nonlinear system identification based on relevance vector machines (RVMs) has been traditionally addressed by stacking the input and/or output regressors and then performing standard RVM regression. This letter introduces a full family of composite kernels in order to integrate the input and output information in the mapping function efficiently and hence generalize the standard approach. An improved trade-off between accuracy and sparsity is obtained in several benchmark problems. Also, the RVM yields confidence intervals for the predictions, and it is less sensitive to free parameter selection.

引用

页码：279 / 282

页数：4

共 19 条

[1]

[Anonymous], ADV NEURAL INFORM PR

[2] Composite kernels for hyperspectral image classification [J].

Camps-Valls, G ;

Gomez-Chova, L ;

Muñoz-Marí, J ;

Vila-Francés, J ;

Calpe-Maravilla, J .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) :93-97

[3]

CHEN S, 1992, INT J CONTROL, V56, P319, DOI [10.1080/00207179208934317, 10.1080/00207179008934126]

[4] Kernel based partially linear models and nonlinear identification [J].

Espinoza, M ;

Suykens, JAK ;

De Moor, B .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2005, 50 (10) :1602-1606

[5]

Ljung L, 1999, SYSTEM IDENTIFICATIO

[6]

MAK B, 2004, P IEEE INT C AC SPEE, V1, P325

[7] Support vector machines for nonlinear kernel ARMA system identification [J].

Martinez-Ramon, Martel ;

Rojo-Alvarez, Jose Luis ;

Camps-Valls, Gustavo ;

Munoz-Mari, Jordi ;

Navia-Vazquez, Angel ;

Soria-Olivas, Emilio ;

Figueiras-Vidal, Anibal R. .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06) :1617-1622

[8]

NELLES O., 2002, Nonlinear system identification

[9]

O'Hagan A., 1994, BAYESIAN INFERENCE B, V2B

[10]

PELCKMANS K, 2005, SUPPORT VECTOR MACHI

← 1 2 →