Model selection via worts-case criterion for nonlinear bounded-error estimation

Abstract : In this paper the problem of model selection for measurement purpose is studied. A new selcetion procedure in a deterministic framework is proposed. The problem of nonlinear bounded-error estimation is viewed as a set inversion procedure. As each candidate model structure leads to a specific set of admissible values of the measurement vector, the worts-case criterion is used to select the optimal model. The selection procedure is applied to a real measurement problem, grooves dimensioning using Remote Field Eddy Current (RFEC) inspection.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00844628
Contributor : Marie-Françoise Gerard <>
Submitted on : Monday, July 15, 2013 - 4:14:21 PM
Last modification on : Thursday, April 4, 2019 - 10:18:04 AM
Document(s) archivé(s) le : Wednesday, October 16, 2013 - 4:18:25 AM

File

IEEEmodelSelect_LISA1999.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00844628, version 1

Citation

S. Brahim-Belhouari, Michel Kieffer, G. Fleury, Luc Jaulin, Eric Walter. Model selection via worts-case criterion for nonlinear bounded-error estimation. 16th IEEE Instrumentation and Measurement, May 1999, Venise, Italy. pp.1075-1080. ⟨hal-00844628⟩

Share

Metrics

Record views

598

Files downloads

162