Orthogonal least squares algorithm for the multiple-measurement vectors problem

Junhan Kim, Byonghyo Shim

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

Abstract

The multiple signal classification (MUSIC) algorithm, which was originally proposed to solve the direction of arrival (DOA) estimation problem in sensor array processing, has attracted much attention in recent years as a method to solve the multiple-measurement vectors (MMV) problem. While MUSIC reliably reconstructs the row sparse signals in the full row rank case, it performs poor in the rank deficient case. In order to overcome the limitation of MUSIC, we propose a robust greedy algorithm, henceforth referred to as an MMV orthogonal least squares (MMV-OLS) algorithm, for the MMV problem. Our analysis shows that in the full row rank case, MMV-OLS guarantees exact reconstruction of any row K-sparse signals from K + 1 measurements, which is in fact optimal since K + 1 is the smallest number of measurements to recover the row K-sparse matrices. In addition, we show that the recovery performance of MMV-OLS is competitive even in the rank deficient case by providing empirical results.

Original languageEnglish
Title of host publicationTENCON 2017 - 2017 IEEE Region 10 Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1269-1272
Number of pages4
Volume2017-December
ISBN (Electronic)9781509011339
DOIs
Publication statusPublished - 2017 Dec 19
Externally publishedYes
Event2017 IEEE Region 10 Conference, TENCON 2017 - Penang, Malaysia
Duration: 2017 Nov 52017 Nov 8

Other

Other2017 IEEE Region 10 Conference, TENCON 2017
CountryMalaysia
CityPenang
Period17/11/517/11/8

Fingerprint

Array processing
Direction of arrival
Sensor arrays
Recovery

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Kim, J., & Shim, B. (2017). Orthogonal least squares algorithm for the multiple-measurement vectors problem. In TENCON 2017 - 2017 IEEE Region 10 Conference (Vol. 2017-December, pp. 1269-1272). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TENCON.2017.8228052

Orthogonal least squares algorithm for the multiple-measurement vectors problem. / Kim, Junhan; Shim, Byonghyo.

TENCON 2017 - 2017 IEEE Region 10 Conference. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. p. 1269-1272.

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

Kim, J & Shim, B 2017, Orthogonal least squares algorithm for the multiple-measurement vectors problem. in TENCON 2017 - 2017 IEEE Region 10 Conference. vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 1269-1272, 2017 IEEE Region 10 Conference, TENCON 2017, Penang, Malaysia, 17/11/5. https://doi.org/10.1109/TENCON.2017.8228052
Kim J, Shim B. Orthogonal least squares algorithm for the multiple-measurement vectors problem. In TENCON 2017 - 2017 IEEE Region 10 Conference. Vol. 2017-December. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1269-1272 https://doi.org/10.1109/TENCON.2017.8228052
Kim, Junhan ; Shim, Byonghyo. / Orthogonal least squares algorithm for the multiple-measurement vectors problem. TENCON 2017 - 2017 IEEE Region 10 Conference. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1269-1272
@inproceedings{9029d9ddbbd7491d8ea9cc074d2d6625,
title = "Orthogonal least squares algorithm for the multiple-measurement vectors problem",
abstract = "The multiple signal classification (MUSIC) algorithm, which was originally proposed to solve the direction of arrival (DOA) estimation problem in sensor array processing, has attracted much attention in recent years as a method to solve the multiple-measurement vectors (MMV) problem. While MUSIC reliably reconstructs the row sparse signals in the full row rank case, it performs poor in the rank deficient case. In order to overcome the limitation of MUSIC, we propose a robust greedy algorithm, henceforth referred to as an MMV orthogonal least squares (MMV-OLS) algorithm, for the MMV problem. Our analysis shows that in the full row rank case, MMV-OLS guarantees exact reconstruction of any row K-sparse signals from K + 1 measurements, which is in fact optimal since K + 1 is the smallest number of measurements to recover the row K-sparse matrices. In addition, we show that the recovery performance of MMV-OLS is competitive even in the rank deficient case by providing empirical results.",
author = "Junhan Kim and Byonghyo Shim",
year = "2017",
month = "12",
day = "19",
doi = "10.1109/TENCON.2017.8228052",
language = "English",
volume = "2017-December",
pages = "1269--1272",
booktitle = "TENCON 2017 - 2017 IEEE Region 10 Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Orthogonal least squares algorithm for the multiple-measurement vectors problem

AU - Kim, Junhan

AU - Shim, Byonghyo

PY - 2017/12/19

Y1 - 2017/12/19

N2 - The multiple signal classification (MUSIC) algorithm, which was originally proposed to solve the direction of arrival (DOA) estimation problem in sensor array processing, has attracted much attention in recent years as a method to solve the multiple-measurement vectors (MMV) problem. While MUSIC reliably reconstructs the row sparse signals in the full row rank case, it performs poor in the rank deficient case. In order to overcome the limitation of MUSIC, we propose a robust greedy algorithm, henceforth referred to as an MMV orthogonal least squares (MMV-OLS) algorithm, for the MMV problem. Our analysis shows that in the full row rank case, MMV-OLS guarantees exact reconstruction of any row K-sparse signals from K + 1 measurements, which is in fact optimal since K + 1 is the smallest number of measurements to recover the row K-sparse matrices. In addition, we show that the recovery performance of MMV-OLS is competitive even in the rank deficient case by providing empirical results.

AB - The multiple signal classification (MUSIC) algorithm, which was originally proposed to solve the direction of arrival (DOA) estimation problem in sensor array processing, has attracted much attention in recent years as a method to solve the multiple-measurement vectors (MMV) problem. While MUSIC reliably reconstructs the row sparse signals in the full row rank case, it performs poor in the rank deficient case. In order to overcome the limitation of MUSIC, we propose a robust greedy algorithm, henceforth referred to as an MMV orthogonal least squares (MMV-OLS) algorithm, for the MMV problem. Our analysis shows that in the full row rank case, MMV-OLS guarantees exact reconstruction of any row K-sparse signals from K + 1 measurements, which is in fact optimal since K + 1 is the smallest number of measurements to recover the row K-sparse matrices. In addition, we show that the recovery performance of MMV-OLS is competitive even in the rank deficient case by providing empirical results.

UR - http://www.scopus.com/inward/record.url?scp=85044196526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044196526&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2017.8228052

DO - 10.1109/TENCON.2017.8228052

M3 - Conference contribution

VL - 2017-December

SP - 1269

EP - 1272

BT - TENCON 2017 - 2017 IEEE Region 10 Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -