Prior mismatch in Bayesian direction of arrival estimation for sparse arrays

Joshua M. Kantor, Christ Richmond, Bill Correll, Daniel Bliss

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We study the mean-squared-error (MSE) performance of Bayesian direction-of-arrival (DOA) estimation for sparse linear arrays in which prior belief about the target location is incorporated into the estimation process. We utilize a recent extension of the method of interval errors (MIE) to the case of maximum a posteriori (MAP) direction-of-arrival estimation to more accurately predict low-medium MSE values in the presence of prior mismatch. We also develop a misspecified Cramér-Rao bound on MAP estimation that can improve the performance of MIE. We specialize to log-periodic arrays to conduct a notional trade study in which we consider the trade in improved estimation performance potentially possible with larger sparser arrays vs the increased sensitivity to incorrectly specified priors.

Original languageEnglish (US)
Title of host publicationIEEE National Radar Conference - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages811-816
Number of pages6
Volume2015-June
EditionJune
DOIs
StatePublished - Jun 22 2015
Event2015 IEEE International Radar Conference, RadarCon 2015 - Arlington, United States
Duration: May 10 2015May 15 2015

Other

Other2015 IEEE International Radar Conference, RadarCon 2015
CountryUnited States
CityArlington
Period5/10/155/15/15

Fingerprint

Direction of arrival

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Kantor, J. M., Richmond, C., Correll, B., & Bliss, D. (2015). Prior mismatch in Bayesian direction of arrival estimation for sparse arrays. In IEEE National Radar Conference - Proceedings (June ed., Vol. 2015-June, pp. 811-816). [7131107] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RADAR.2015.7131107

Prior mismatch in Bayesian direction of arrival estimation for sparse arrays. / Kantor, Joshua M.; Richmond, Christ; Correll, Bill; Bliss, Daniel.

IEEE National Radar Conference - Proceedings. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. p. 811-816 7131107.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kantor, JM, Richmond, C, Correll, B & Bliss, D 2015, Prior mismatch in Bayesian direction of arrival estimation for sparse arrays. in IEEE National Radar Conference - Proceedings. June edn, vol. 2015-June, 7131107, Institute of Electrical and Electronics Engineers Inc., pp. 811-816, 2015 IEEE International Radar Conference, RadarCon 2015, Arlington, United States, 5/10/15. https://doi.org/10.1109/RADAR.2015.7131107
Kantor JM, Richmond C, Correll B, Bliss D. Prior mismatch in Bayesian direction of arrival estimation for sparse arrays. In IEEE National Radar Conference - Proceedings. June ed. Vol. 2015-June. Institute of Electrical and Electronics Engineers Inc. 2015. p. 811-816. 7131107 https://doi.org/10.1109/RADAR.2015.7131107
Kantor, Joshua M. ; Richmond, Christ ; Correll, Bill ; Bliss, Daniel. / Prior mismatch in Bayesian direction of arrival estimation for sparse arrays. IEEE National Radar Conference - Proceedings. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 811-816
@inproceedings{3bf52a14647e4539bdd394ef62c0e3f4,
title = "Prior mismatch in Bayesian direction of arrival estimation for sparse arrays",
abstract = "We study the mean-squared-error (MSE) performance of Bayesian direction-of-arrival (DOA) estimation for sparse linear arrays in which prior belief about the target location is incorporated into the estimation process. We utilize a recent extension of the method of interval errors (MIE) to the case of maximum a posteriori (MAP) direction-of-arrival estimation to more accurately predict low-medium MSE values in the presence of prior mismatch. We also develop a misspecified Cram{\'e}r-Rao bound on MAP estimation that can improve the performance of MIE. We specialize to log-periodic arrays to conduct a notional trade study in which we consider the trade in improved estimation performance potentially possible with larger sparser arrays vs the increased sensitivity to incorrectly specified priors.",
author = "Kantor, {Joshua M.} and Christ Richmond and Bill Correll and Daniel Bliss",
year = "2015",
month = "6",
day = "22",
doi = "10.1109/RADAR.2015.7131107",
language = "English (US)",
volume = "2015-June",
pages = "811--816",
booktitle = "IEEE National Radar Conference - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
edition = "June",

}

TY - GEN

T1 - Prior mismatch in Bayesian direction of arrival estimation for sparse arrays

AU - Kantor, Joshua M.

AU - Richmond, Christ

AU - Correll, Bill

AU - Bliss, Daniel

PY - 2015/6/22

Y1 - 2015/6/22

N2 - We study the mean-squared-error (MSE) performance of Bayesian direction-of-arrival (DOA) estimation for sparse linear arrays in which prior belief about the target location is incorporated into the estimation process. We utilize a recent extension of the method of interval errors (MIE) to the case of maximum a posteriori (MAP) direction-of-arrival estimation to more accurately predict low-medium MSE values in the presence of prior mismatch. We also develop a misspecified Cramér-Rao bound on MAP estimation that can improve the performance of MIE. We specialize to log-periodic arrays to conduct a notional trade study in which we consider the trade in improved estimation performance potentially possible with larger sparser arrays vs the increased sensitivity to incorrectly specified priors.

AB - We study the mean-squared-error (MSE) performance of Bayesian direction-of-arrival (DOA) estimation for sparse linear arrays in which prior belief about the target location is incorporated into the estimation process. We utilize a recent extension of the method of interval errors (MIE) to the case of maximum a posteriori (MAP) direction-of-arrival estimation to more accurately predict low-medium MSE values in the presence of prior mismatch. We also develop a misspecified Cramér-Rao bound on MAP estimation that can improve the performance of MIE. We specialize to log-periodic arrays to conduct a notional trade study in which we consider the trade in improved estimation performance potentially possible with larger sparser arrays vs the increased sensitivity to incorrectly specified priors.

UR - http://www.scopus.com/inward/record.url?scp=84937961020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937961020&partnerID=8YFLogxK

U2 - 10.1109/RADAR.2015.7131107

DO - 10.1109/RADAR.2015.7131107

M3 - Conference contribution

AN - SCOPUS:84937961020

VL - 2015-June

SP - 811

EP - 816

BT - IEEE National Radar Conference - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -