A Weighted Least-Squares Approach to Parameter Estimation Problems Based on Binary Measurements

Abstract : We present a new approach to parameter estimation problems based on binary measurements, motivated by the need to add integrated low-cost self-test features to microfabricated devices. This approach is based on the use of original weighted least-squares criteria: as opposed to other existing methods, it requires no dithering signal and it does not rely on an approximation of the quantizer. In this paper, we focus on a simple choice for the weights and establish some asymptotical properties of the corresponding criterion. To achieve this, the assumption that the quantizer's input is Gaussian and centered is made. In this context, we prove that the proposed criterion is locally convex and that it is possible to use a simple gradient descent to find a consistent estimate of the unknown system parameters, regardless of the presence of measurement noise at the quantizer's input.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00450295
Contributor : Karine El Rassi <>
Submitted on : Tuesday, January 26, 2010 - 10:20:10 AM
Last modification on : Monday, February 25, 2019 - 4:34:17 PM
Long-term archiving on : Thursday, June 17, 2010 - 9:33:43 PM

File

BIMBO_JJ_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00450295, version 1

Collections

Citation

Eric Colinet, Jérôme Juillard. A Weighted Least-Squares Approach to Parameter Estimation Problems Based on Binary Measurements. IEEE Transactions on Automatic Control, Institute of Electrical and Electronics Engineers, 2010, 55 (1), pp.148-152. ⟨hal-00450295⟩

Share

Metrics

Record views

302

Files downloads

271