The use of nonnegative garrote for order selection of ARX models

Lyzell, Christian; Roll, Jacob; Ljung, Lennart

doi:10.1109/cdc.2008.4738836

Cited by 9 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In dynamical linear models, the parameters are naturally ordered by their memory length [11]. In the nonlinear case, the parameters are not only ordered by memory length, but also by their nonlinearity order.…”

Section: B Modification On Original Nng Methodsmentioning

confidence: 99%

“…At first it is considered as a coefficient shrinkage method for linear regression models in statistics. Recently this method is modified and used for order selection of ARX (AutoRegressive with eXogenous input) models in [11]. The NNG method penalizes the model parameters by attaching weights to it, which in turn are regularized.…”

Section: Modified Nonnegative Garrote Methods a The Nonnegative mentioning

confidence: 99%

“…In order to provide more information about identified model to help user making selection, a fitness function is defined as [11]     …”

Section: B Evaluation Of Modelmentioning

confidence: 99%

See 2 more Smart Citations

A Modified Nonnegative Garrote Method for Identification of Brushless DC Motors

Jin¹,

Lu²,

Zhu³

2014

Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science

View full text Add to dashboard Cite

Abstract-An effective identification framework has presented to build a more accurate nonlinear model for brushless DC motors, which are frequently used as drive systems of micro electromechanical unmanned aerial vehicles. The identification method uses a two-step procedure to obtain a fully parametric model. First, the initial model of system is estimated. Next, a coefficient shrinkage method is used for model structure selection. There are two main highlight processes in this paper. One is the use of Hammerstein series models for identification, which leads to a trade-off between model accuracy and complexity. Another is the use of modified nonnegative garrote method for model reduction and finding the true model order. The proposed method is validated on simulated system and finally used to identify a brushless DC motor system. The obtained nonlinear model of brushless DC motor is of high performance and controllable model complexity.

show abstract

Section: B Modification On Original Nng Methodsmentioning

confidence: 99%

Section: Modified Nonnegative Garrote Methods a The Nonnegative mentioning

confidence: 99%

See 1 more Smart Citation

A Modified Nonnegative Garrote Method for Identification of Brushless DC Motors

Jin¹,

Lu²,

Zhu³

2014

Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science

View full text Add to dashboard Cite

show abstract

“…The fit itself can be calculated in terms of any error measure or the BIC or AIC criterion. An efficient way to implement this strategy is to use a path following parametric estimation, which calculates a piecewise affine solution path for λ [9]. The NNG is reported to be more effective in recovering the sparsity structure of θ o than the LASSO.…”

Section: B Sparse Estimators: Lasso and Nngmentioning

confidence: 99%

“…More recently, statistical regularization (shrinkage) methods have been developed like the Non-Negative Garrote (NNG) or the Least Absolute Shrinkage and Selection Operator (LASSO) [5]- [7], or the Ridge Regression and the Elastic Net methods [8]. The NNG was applied in the context of identification of Linear Time-Invariant (LTI) Auto Regressive with eXogenous input (ARX) models in [9].…”

Section: Introductionmentioning

confidence: 99%

Compressive System Identification in the Linear Time-Invariant framework

Tóth

Sanandaji

Poolla

et al. 2011

IEEE Conference on Decision and Control and European Control Conference

View full text Add to dashboard Cite

Abstract-Selection of an efficient model parametrization (model order, delay, etc.) has crucial importance in parametric system identification. It navigates a trade-off between representation capabilities of the model (structural bias) and effects of over-parametrization (variance increase of the estimates). There exists many approaches to this widely studied problem in terms of statistical regularization methods and information criteria. In this paper, an alternative ℓ1 regularization scheme is proposed for estimation of sparse linear-regression models based on recent results in compressive sensing. It is shown that the proposed scheme provides consistent estimation of sparse models in terms of the so-called oracle property, it is computationally attractive for large-scale over-parameterized models and it is applicable in case of small data sets, i.e., underdetermined estimation problems. The performance of the approach w.r.t. other regularization schemes is demonstrated in an extensive Monte Carlo study.

show abstract

Order and structural dependence selection of LPV-ARX models using a nonnegative garrote approach

Tóth

Lyzell

Enqvist

et al. 2009

Proceedings of the 48h IEEE Conference on Decision and Control (CDC) Held Jointly With 2009 28th Chinese Control Conference

View full text Add to dashboard Cite

Van den, P. M. J. (2009). Order and structural dependence selection of LPV-ARX models using a nonnegative Garrote approach. In Proceedings of the 48th IEEE Conference on Decision and Control (CDC 2009), 16-18 December 2009 Please check the document version of this publication:• A submitted manuscript is the version of the article upon submission and before peer-review. There can be important differences between the submitted version and the official published version of record. People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website.• The final author version and the galley proof are versions of the publication after peer review.• The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research.• You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. Abstract-In order to accurately identify Linear ParameterVarying (LPV) systems, order selection of LPV linear regression models has prime importance. Existing identification approaches in this context suffer from the drawback that a set of functional dependencies needs to be chosen a priori for the parametrization of the model coefficients. However in a black-box setting, it has not been possible so far to decide which functions from a given set are required for the parametrization and which are not. To provide a practical solution, a nonnegative garrote approach is applied. It is shown that using only a measured data record of the plant, both the order selection and the selection of structural coefficient dependence can be solved by the proposed method.

show abstract

The use of nonnegative garrote for order selection of ARX models

Cited by 9 publications

References 10 publications

A Modified Nonnegative Garrote Method for Identification of Brushless DC Motors

A Modified Nonnegative Garrote Method for Identification of Brushless DC Motors

Compressive System Identification in the Linear Time-Invariant framework

Order and structural dependence selection of LPV-ARX models using a nonnegative garrote approach

Contact Info

Product

Resources

About