Perspectives of orthonormal basis functions based kernels in Bayesian system identification

M.A.H. Darwish, G. Pillonetto, Roland Toth

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

5 Citaten (Scopus)

Samenvatting

Kernel-based regularization approaches for lin- ear time-invariant system identification have been introduced recently. This class of methods corresponds to a particu- lar regularized least-squares methodology that may achieve a favorable bias/variance trade-off compared with classical Prediction Error Minimization (PEM) methods. However, to fully exploit this property, the kernel function itself needs to be appropriately designed for the identification problem at hand to be able to successfully capture all relevant aspects of the data- generating system. Hence, there is a need for a methodology that can accomplish this design step without affecting the simplicity of these approaches. In this paper, we propose a systematic kernel construction mechanism to capture dynamic system behavior via the use of orthonormal basis functions (OBFs). Two special cases are investigated as an illustration of the construction mechanism, namely Laguerre and Kautz based kernel structures. Monte-Carlo simulations show that OBFs- based kernels with Laguerre basis perform well compared with stable spline/TC kernels, especially for slow systems with dominant poles close to the unit circle. Moreover, the capability of Kautz basis to model resonant systems is also shown.
Originele taal-2Engels
Titel54th IEEE Conference on Decision and Control (CDC 2015), 15-18 December 2015, Osaka, Japan
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's2713-2718
Aantal pagina's6
ISBN van elektronische versie978-1-4799-7885-4
ISBN van geprinte versie978-1-4799-7884-7
DOI's
StatusGepubliceerd - 2015
Evenement54th IEEE Conference on Decision and Control (CDC 2015) - "Osaka International Convention Center", Osaka, Japan
Duur: 15 dec 201518 dec 2015
Congresnummer: 54
http://www.cdc2015.ctrl.titech.ac.jp/

Congres

Congres54th IEEE Conference on Decision and Control (CDC 2015)
Verkorte titelCDC 2015
Land/RegioJapan
StadOsaka
Periode15/12/1518/12/15
Anderthe 54th IEEE Conference on Decision and Control
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Perspectives of orthonormal basis functions based kernels in Bayesian system identification'. Samen vormen ze een unieke vingerafdruk.

Citeer dit