Optimal Bayesian parameter estimation with periodic criteria

Author

Routtenberg, Tirza ; Tabrikian, Joseph

Author_Institution

Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

fYear

2010

fDate

4-7 Oct. 2010

Firstpage

53

Lastpage

56

Abstract

In this paper, a new method for Bayesian periodic parameter estimation is derived using periodic cost functions. The estimation procedure is evaluated using Fourier series representation of the periodic cost functions. The minimum cyclic and the minimum periodic mean-square-error (MSE) estimators are derived. The proposed periodic estimators are applied to direction-of-arrival (DOA) estimation problem and their performance are compared with the minimum mean-square-error (MMSE) and maximum a-posteriori probability (MAP) estimators in terms of periodic MSE (PMSE).

Keywords

Bayes methods; Fourier series; direction-of-arrival estimation; least mean squares methods; maximum likelihood estimation; parameter estimation; Fourier series representation; direction-of-arrival estimation problem; maximum a-posteriori probability estimators; minimum mean-square-error estimators; minimum periodic mean-square-error estimators; optimal bayesian parameter estimation; periodic cost functions; Bayesian methods; Cost function; Direction of arrival estimation; Estimation; Fourier series; Signal to noise ratio;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensor Array and Multichannel Signal Processing Workshop (SAM), 2010 IEEE

Conference_Location

Jerusalem

ISSN

1551-2282

Print_ISBN

978-1-4244-8978-7

Electronic_ISBN

1551-2282

Type

conf

DOI

10.1109/SAM.2010.5606760

Filename

5606760