Support estimation of a sample space-time covariance matrix

Connor Delaosa; Jennifer Pestana; Nicholas J. Goddard; Samuel D. Somasundaram; Stephan Weiss

Support estimation of a sample space-time covariance matrix

Connor Delaosa, Jennifer Pestana, Nicholas J. Goddard, Samuel D. Somasundaram, Stephan Weiss

Research output: Contribution to conference › Paper › peer-review

67 Downloads (Pure)

Abstract

The ensemble-optimum support for a sample space-time covariance matrix can be determined from the ground truth space-time covariance, and the variance of the estimator. In this paper we provide approximations that permit the estimation of the sample-optimum support from the estimate itself, given a suitable detection threshold. In simulations, we provide some insight into the (in)sensitivity and dependencies of this threshold.

Original language	English
Number of pages	5
Publication status	Accepted/In press - 1 Mar 2019
Event	Sensor Signal Processing for Defence 2019 - Brighton, United Kingdom Duration: 9 May 2019 → 10 May 2019

Conference

Conference	Sensor Signal Processing for Defence 2019
Abbreviated title	SSPD'19
Country/Territory	United Kingdom
City	Brighton
Period	9/05/19 → 10/05/19

Keywords

space-time covariance matrix
parahermitian matrix
cross-correlation
estimation

Access to Document

Delaosa-etal-SSPC2019-Support-estimation-of-a-sample-space-time-covariance-matrixAccepted author manuscript, 588 KB

Cite this

@conference{432e09e060de4b6981372c35063c026b,

title = "Support estimation of a sample space-time covariance matrix",

abstract = "The ensemble-optimum support for a sample space-time covariance matrix can be determined from the ground truth space-time covariance, and the variance of the estimator. In this paper we provide approximations that permit the estimation of the sample-optimum support from the estimate itself, given a suitable detection threshold. In simulations, we provide some insight into the (in)sensitivity and dependencies of this threshold.",

keywords = "space-time covariance matrix, parahermitian matrix, cross-correlation, estimation",

author = "Connor Delaosa and Jennifer Pestana and Goddard, \{Nicholas J.\} and Somasundaram, \{Samuel D.\} and Stephan Weiss",

note = "{\textcopyright} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; Sensor Signal Processing for Defence 2019, SSPD'19 ; Conference date: 09-05-2019 Through 10-05-2019",

year = "2019",

month = mar,

day = "1",

language = "English",

}

TY - CONF

T1 - Support estimation of a sample space-time covariance matrix

AU - Delaosa, Connor

AU - Pestana, Jennifer

AU - Goddard, Nicholas J.

AU - Somasundaram, Samuel D.

AU - Weiss, Stephan

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - The ensemble-optimum support for a sample space-time covariance matrix can be determined from the ground truth space-time covariance, and the variance of the estimator. In this paper we provide approximations that permit the estimation of the sample-optimum support from the estimate itself, given a suitable detection threshold. In simulations, we provide some insight into the (in)sensitivity and dependencies of this threshold.

AB - The ensemble-optimum support for a sample space-time covariance matrix can be determined from the ground truth space-time covariance, and the variance of the estimator. In this paper we provide approximations that permit the estimation of the sample-optimum support from the estimate itself, given a suitable detection threshold. In simulations, we provide some insight into the (in)sensitivity and dependencies of this threshold.

KW - space-time covariance matrix

KW - parahermitian matrix

KW - cross-correlation

KW - estimation

UR - https://sspd.eng.ed.ac.uk/

M3 - Paper

T2 - Sensor Signal Processing for Defence 2019

Y2 - 9 May 2019 through 10 May 2019

ER -

Support estimation of a sample space-time covariance matrix

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Signal Processing in the Information Age (UDRC III)

Cite this

Support estimation of a sample space-time covariance matrix

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Signal Processing in the Information Age (UDRC III)

Cite this