(27) * << * >> * Russian * English * Content * All Issues

Identification based on a small number of observations using the criterion of relative consistency of estimates

A.V. Gavrilov 1, V.A. Soifer 1, 2, V.A. Fursov 1, 2
1Samara State Aerospace University (SSAU)
2Image Processing Systems Institute of RAS

 PDF, 122 kB

Pages: 138-141.

Full text of article: Russian language.

Abstract:
The paper considers the problem of parametric identification by a small number of observations. An approach is being developed based on the so-called principle of consistency of estimates. The idea is to search the observations for a more noise-free subset. The so-called criterion of relative consistency is studied, which allows toform these subsets without the a priori information.

Keywords:
small number of observations, so-called principle, noise-free subset, a priori information.

Citation:
Gavrilov AV, Soifer VA, Fursov VA. Identification based on a small number of observations using the criterion of relative consistency of estimates. Computer Optics 2005; 27: 138-141.

Acknowledgements:
This work was carried out as part of the Russian-American program “Basic Research and Higher Education”, with the support of the Russian Federal Property Fund (grants No. 03-01-00109 and 04-07-90149) and a grant from the President of the Russian Federation No. НШ-1007.2003.01.

References:
  1. Soifer VA, ed. Methods for computer design of diffractive optical elements. New York: John Willey and Sons Inc; 2002. ISBN: 978-0-471-09533-0.
  2. Graupe D. Identification of systems. Krieger Pub Co; 1976. ISBN: 978-0882753591.
  3. Fursov VA. Identification of models of imaging systems for the small number of observations [In Russian]. Samara: SSAU Publisher; 1998.
  4. Kalman PE. Identification of systems with noise [In Russian]. Uspekhi Matematicheskikh Nauk 1985; 40(4:244): 27-41.
  5. Fursov VA, Gavrilov AV. Conforming identification of the controlled object. Conforming identification of the controlled object. Proceeding of the 2nd International Conference on Computing, Communications and Control Technologies 2004; 326-330.
  6. Björck Å. Least squares methods. In Book: Ciarlet PG, Lions J-L, eds. Handbook of numerical analysis, Vol 1. Finite difference methods (Part 1), Solutions of equations in Rn (Part 1). Amsterdam, New York: Elsevier/North-Holland; 1990: 465-652. DOI: 10.1016/S1570-8659(05)80036-5.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20