Segmentation of ARX-models using sum-of-norms regularization

被引：110

作者：

Ohlsson, Henrik ^{[1
]}

Ljung, Lennart ^{[1
]}

Boyd, Stephen ^{[2
]}

机构：

[1] Linkoping Univ, Dept Elect Engn, SE-58183 Linkoping, Sweden

[2] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA

来源：

AUTOMATICA | 2010年 / 46卷 / 06期

基金：

瑞典研究理事会;

关键词：

Segmentation; Regularization; ARX-models; REGRESSION; SELECTION;

D O I：

10.1016/j.automatica.2010.03.013

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Segmentation of time-varying systems and signals into models whose parameters are piecewise constant in time is an important and well studied problem. Here it is formulated as a least-squares problem with sum-of-norms regularization over the state parameter jumps. a generalization of l(1)-regularization. A nice property of the suggested formulation is that it only has one tuning parameter, the regularization constant which is used to trade-off fit and the number of segments. (C) 2010 Elsevier Ltd. All rights reserved.

引用

页码：1107 / 1111

页数：5

共 28 条

[1]

Akaike H., 1973, 2 INT S INFORM THEOR, P267

[2] ADAPTIVE FORGETTING IN RECURSIVE-IDENTIFICATION THROUGH MULTIPLE MODELS [J].

ANDERSSON, P .

INTERNATIONAL JOURNAL OF CONTROL, 1985, 42 (05) :1175-1193

[3]

[Anonymous], 2006, Journal of the Royal Statistical Society, Series B

[4]

[Anonymous], 1999, SYSTEM IDENTIFICATIO

[5]

[Anonymous], 2004, P IEEE INT S COMPUTE

[6]

Bassevill M., 1993, DIGITAL SIGNAL PROCE

[7]

Bertsekas D., 2003, Convex Analysis and Optimization

[8] THE INTERACTING MULTIPLE MODEL ALGORITHM FOR SYSTEMS WITH MARKOVIAN SWITCHING COEFFICIENTS [J].

BLOM, HAP ;

BARSHALOM, Y .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1988, 33 (08) :780-783

[9] FEATURE EXTRACTION FROM ELECTROENCEPHALOGRAM BY ADAPTIVE SEGMENTATION [J].

BODENSTEIN, G ;

PRAETORIUS, HM .

PROCEEDINGS OF THE IEEE, 1977, 65 (05) :642-652

[10]

Borwein Jonathan, 2006, Convex Analysis and Nonlinear Optimization: Theory and Examples, DOI DOI 10.1007/978-0-387-31256-9

← 1 2 3 →