Decentralized estimation with correlated additive noise: Does dependency always imply redundancy?

Fangrong Peng, Biao Chen

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

4 Citations (Scopus)

Abstract

This paper studies decentralized estimation with correlated observations. Focusing on the additive model with correlated Gaussian noises, we attempt to answer several distinct yet related questions in decentralized estimation: 1. When does correlation imply redundancy, i.e., incur performance degradation compared with that of independent observations; 2. What is the optimal quantizer structure that maximizes the Fisher information at the fusion center; 3. What is the preferred communication direction in a tandem fusion network involving correlated observations? It is shown that there exist different correlation regimes whose impacts on the estimation performance are in sharp contrast with each other. For the Gaussian model, it is established that quantizing the observation is optimal regardless of the correlation coefficients; this is true despite the fact that subsequent estimators may differ at the fusion center. Finally, it is always beneficial to have the better sensor (i.e., that has a higher SNR) to serve as a fusion center in a tandem fusion network for all correlation regimes.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
PublisherIEEE Computer Society
Pages677-681
Number of pages5
ISBN (Print)9781479923908
DOIs
StatePublished - 2013
Event2013 47th Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 3 2013Nov 6 2013

Other

Other2013 47th Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/3/1311/6/13

Fingerprint

Additive noise
Redundancy
Fusion reactions
Degradation
Communication
Sensors

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Peng, F., & Chen, B. (2013). Decentralized estimation with correlated additive noise: Does dependency always imply redundancy? In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 677-681). [6810368] IEEE Computer Society. https://doi.org/10.1109/ACSSC.2013.6810368

Decentralized estimation with correlated additive noise : Does dependency always imply redundancy? / Peng, Fangrong; Chen, Biao.

Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society, 2013. p. 677-681 6810368.

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

Peng, F & Chen, B 2013, Decentralized estimation with correlated additive noise: Does dependency always imply redundancy? in Conference Record - Asilomar Conference on Signals, Systems and Computers., 6810368, IEEE Computer Society, pp. 677-681, 2013 47th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/3/13. https://doi.org/10.1109/ACSSC.2013.6810368
Peng F, Chen B. Decentralized estimation with correlated additive noise: Does dependency always imply redundancy? In Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society. 2013. p. 677-681. 6810368 https://doi.org/10.1109/ACSSC.2013.6810368
Peng, Fangrong ; Chen, Biao. / Decentralized estimation with correlated additive noise : Does dependency always imply redundancy?. Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society, 2013. pp. 677-681
@inproceedings{36514156cedf457492c7f0422bab48b7,
title = "Decentralized estimation with correlated additive noise: Does dependency always imply redundancy?",
abstract = "This paper studies decentralized estimation with correlated observations. Focusing on the additive model with correlated Gaussian noises, we attempt to answer several distinct yet related questions in decentralized estimation: 1. When does correlation imply redundancy, i.e., incur performance degradation compared with that of independent observations; 2. What is the optimal quantizer structure that maximizes the Fisher information at the fusion center; 3. What is the preferred communication direction in a tandem fusion network involving correlated observations? It is shown that there exist different correlation regimes whose impacts on the estimation performance are in sharp contrast with each other. For the Gaussian model, it is established that quantizing the observation is optimal regardless of the correlation coefficients; this is true despite the fact that subsequent estimators may differ at the fusion center. Finally, it is always beneficial to have the better sensor (i.e., that has a higher SNR) to serve as a fusion center in a tandem fusion network for all correlation regimes.",
author = "Fangrong Peng and Biao Chen",
year = "2013",
doi = "10.1109/ACSSC.2013.6810368",
language = "English (US)",
isbn = "9781479923908",
pages = "677--681",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Decentralized estimation with correlated additive noise

T2 - Does dependency always imply redundancy?

AU - Peng, Fangrong

AU - Chen, Biao

PY - 2013

Y1 - 2013

N2 - This paper studies decentralized estimation with correlated observations. Focusing on the additive model with correlated Gaussian noises, we attempt to answer several distinct yet related questions in decentralized estimation: 1. When does correlation imply redundancy, i.e., incur performance degradation compared with that of independent observations; 2. What is the optimal quantizer structure that maximizes the Fisher information at the fusion center; 3. What is the preferred communication direction in a tandem fusion network involving correlated observations? It is shown that there exist different correlation regimes whose impacts on the estimation performance are in sharp contrast with each other. For the Gaussian model, it is established that quantizing the observation is optimal regardless of the correlation coefficients; this is true despite the fact that subsequent estimators may differ at the fusion center. Finally, it is always beneficial to have the better sensor (i.e., that has a higher SNR) to serve as a fusion center in a tandem fusion network for all correlation regimes.

AB - This paper studies decentralized estimation with correlated observations. Focusing on the additive model with correlated Gaussian noises, we attempt to answer several distinct yet related questions in decentralized estimation: 1. When does correlation imply redundancy, i.e., incur performance degradation compared with that of independent observations; 2. What is the optimal quantizer structure that maximizes the Fisher information at the fusion center; 3. What is the preferred communication direction in a tandem fusion network involving correlated observations? It is shown that there exist different correlation regimes whose impacts on the estimation performance are in sharp contrast with each other. For the Gaussian model, it is established that quantizing the observation is optimal regardless of the correlation coefficients; this is true despite the fact that subsequent estimators may differ at the fusion center. Finally, it is always beneficial to have the better sensor (i.e., that has a higher SNR) to serve as a fusion center in a tandem fusion network for all correlation regimes.

UR - http://www.scopus.com/inward/record.url?scp=84901260858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901260858&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2013.6810368

DO - 10.1109/ACSSC.2013.6810368

M3 - Conference contribution

AN - SCOPUS:84901260858

SN - 9781479923908

SP - 677

EP - 681

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

PB - IEEE Computer Society

ER -