Change search
ReferencesLink to record
Permanent link

Direct link
Outlier robust system identification: A Bayesian kernel-based approach
KTH, School of Electrical Engineering (EES), Automatic Control.
KTH, School of Electrical Engineering (EES), Automatic Control.ORCID iD: 0000-0002-9368-3079
2014 (English)In: IFAC Proceedings Volumes (IFAC-PapersOnline), IFAC Papers Online, 2014, 1073-1078 p.Conference paper (Refereed)
Abstract [en]

In this paper, we propose an outlier-robust regularized kernel-based method for linear system identification. The unknown impulse response is modeled as a zero-mean Gaussian process whose covariance (kernel) is given by the recently proposed stable spline kernel, which encodes information on regularity and exponential stability. To build robustness to outliers, we model the measurement noise as realizations of independent Laplacian random variables. The identification problem is cast in a Bayesian framework, and solved by a new Markov Chain Monte Carlo (MCMC) scheme. In particular, exploiting the representation of the Laplacian random variables as scale mixtures of Gaussians, we design a Gibbs sampler which quickly converges to the target distribution. Numerical simulations show a substantial improvement in the accuracy of the estimates over state-of-the-art kernel-based methods.

Place, publisher, year, edition, pages
IFAC Papers Online, 2014. 1073-1078 p.
National Category
Control Engineering
URN: urn:nbn:se:kth:diva-175122DOI: 10.3182/20140824-6-ZA-1003.01587ScopusID: 2-s2.0-84929727146ISBN: 9783902823625OAI: diva2:876186
19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014, 24 August 2014 through 29 August 2014

QC 20151202

Available from: 2015-12-02 Created: 2015-10-09 Last updated: 2015-12-02Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Bottegal, GiulioHjalmarsson, Håkan
By organisation
Automatic Control
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 14 hits
ReferencesLink to record
Permanent link

Direct link