A new lower bound based on weighted fourier transform of the likelihood ratio function

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

In this paper, a new lower bound on the mean-square-error of unbiased estimators of deterministic parameters is developed. The proposed bound is derived from a class of bounds presented in our recent work using the kernel of the Fourier transform, multiplied by a "weighting" function. The "weighting" function is defined on the parameter space and its significance in the parameter space and frequency domain is discussed throughout the paper. We show that the proposed bound is computationally manageable and can be easily implemented using the fast Fourier transform. The proposed bound is applied for the problem of direction-of-arrival estimation. It is shown by simulations that in comparison to other existing bounds in the literature, the proposed bound provides better prediction of the signal-to-noise ratio threshold region, exhibited by the maximum-likelihood estimator.

Original languageEnglish
Title of host publicationSAM 2008 - 5th IEEE Sensor Array and Multichannel Signal Processing Workshop
Pages428-432
Number of pages5
DOIs
StatePublished - 6 Oct 2008
EventSAM 2008 - 5th IEEE Sensor Array and Multichannel Signal Processing Workshop - Darmstadt, Germany
Duration: 21 Jul 200823 Jul 2008

Publication series

NameSAM 2008 - 5th IEEE Sensor Array and Multichannel Signal Processing Workshop

Conference

ConferenceSAM 2008 - 5th IEEE Sensor Array and Multichannel Signal Processing Workshop
Country/TerritoryGermany
CityDarmstadt
Period21/07/0823/07/08

Fingerprint

Dive into the research topics of 'A new lower bound based on weighted fourier transform of the likelihood ratio function'. Together they form a unique fingerprint.

Cite this