Worst-case Cramer-Rao bound for parametric estimation of superimposed signals

Author

Yau, Sze ; Bresler, Yoram

Author_Institution

Dept. of Electr. & Comput Eng., Illinois Univ., Urbana-Champaign, IL, USA

fYear

1990

fDate

10-12 Oct. 1990

Firstpage

187

Lastpage

191

Abstract

The problem of parameter estimation of superimposed signals in white Gaussian noise is considered and the effect of the amplitude correlation structure on the Cramer-Rao bounds is studied. The best and worst conditions are found using various criteria, and closed form expressions for the bounds, which are free from the nuisance parameters of correlation structure, are derived. The results are applied to the example of parameter estimation of superimposed sinusoids, or plan-wave direction finding in white Gaussian noise, determining best and worst conditions on the signal cross-correlation and relative phases.<>

Keywords

parameter estimation; signal processing; white noise; Cramer-Rao bounds; amplitude correlation structure; best conditions; closed form expressions; parameter estimation; parametric estimation; plan-wave direction finding; relative phases; signal cross-correlation; superimposed signals; superimposed sinusoids; white Gaussian noise; worst conditions; Amplitude estimation; Gaussian noise; Government; Maximum likelihood estimation; Parameter estimation; Phase estimation; Phase noise; Random variables; Signal resolution; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Spectrum Estimation and Modeling, 1990., Fifth ASSP Workshop on

Conference_Location

Rochester, NY, USA

Type

conf

DOI

10.1109/SPECT.1990.205572

Filename

205572