Please use this identifier to cite or link to this item: https://doi.org/10.1007/s10915-008-9231-7
DC FieldValue
dc.titleA robust high-order mixed L2-linfty estimation for linear-in-the-parameters models
dc.contributor.authorZhu, Q.
dc.contributor.authorQiao, Y.
dc.contributor.authorTan, S.
dc.date.accessioned2014-06-16T09:34:52Z
dc.date.available2014-06-16T09:34:52Z
dc.date.issued2009-02
dc.identifier.citationZhu, Q., Qiao, Y., Tan, S. (2009-02). A robust high-order mixed L2-linfty estimation for linear-in-the-parameters models. Journal of Scientific Computing 38 (2) : 185-206. ScholarBank@NUS Repository. https://doi.org/10.1007/s10915-008-9231-7
dc.identifier.issn08857474
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/54794
dc.description.abstractA new algorithm called Mixed L2-Linfty (ML2) estimation is proposed in this paper; it combines both the weighted least squares and the worst-case parameter estimations together as the cost function and strikes the right balance between them. A robust ML2 algorithm and a practical approximate robust ML2 algorithm are also developed under disturbance signals. The properties of the new robust ML2 algorithm are analyzed and the simulation results are given to show the convergence and the validity. © 2008 Springer Science+Business Media, LLC.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1007/s10915-008-9231-7
dc.sourceScopus
dc.subjectHigh-order
dc.subjectL2-Linfty
dc.subjectParameter estimation
dc.subjectSystem identification
dc.typeArticle
dc.contributor.departmentELECTRICAL ENGINEERING
dc.description.doi10.1007/s10915-008-9231-7
dc.description.sourcetitleJournal of Scientific Computing
dc.description.volume38
dc.description.issue2
dc.description.page185-206
dc.description.codenJSCOE
dc.identifier.isiut000261958000004
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

238
checked on Jan 26, 2023

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.