Distributed estimation of gaussmarkov random fields with one-bit quantized data

Jun Fang, Hongbin Li

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We consider the problem of distributed estimation of a GaussMarkov random field using a wireless sensor network (WSN), where due to the stringent power and communication constraints, each sensor has to quantize its data before transmission. In this case, the convergence of conventional iterative matrix-splitting algorithms is hindered by the quantization errors. To address this issue, we propose a one-bit adaptive quantization approach which leads to decaying quantization errors. Numerical results show that even with one bit quantization, the proposed approach achieves a superior mean square deviation performance (with respect to the global linear minimum mean-square error estimate) within a moderate number of iterations.

Original languageEnglish (US)
Article number5411756
Pages (from-to)449-452
Number of pages4
JournalIEEE Signal Processing Letters
Volume17
Issue number5
DOIs
StatePublished - Apr 7 2010

Fingerprint

Distributed Estimation
Random Field
Quantization
Mean square error
Data communication systems
Wireless sensor networks
Matrix Splitting
Minimum Mean Square Error
Communication
Sensors
Mean Square
Wireless Sensor Networks
Error Estimates
Deviation
Iteration
Numerical Results
Sensor

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{eb439f267d484a2084db4441b5383627,
title = "Distributed estimation of gaussmarkov random fields with one-bit quantized data",
abstract = "We consider the problem of distributed estimation of a GaussMarkov random field using a wireless sensor network (WSN), where due to the stringent power and communication constraints, each sensor has to quantize its data before transmission. In this case, the convergence of conventional iterative matrix-splitting algorithms is hindered by the quantization errors. To address this issue, we propose a one-bit adaptive quantization approach which leads to decaying quantization errors. Numerical results show that even with one bit quantization, the proposed approach achieves a superior mean square deviation performance (with respect to the global linear minimum mean-square error estimate) within a moderate number of iterations.",
author = "Jun Fang and Hongbin Li",
year = "2010",
month = "4",
day = "7",
doi = "https://doi.org/10.1109/LSP.2010.2043157",
language = "English (US)",
volume = "17",
pages = "449--452",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

Distributed estimation of gaussmarkov random fields with one-bit quantized data. / Fang, Jun; Li, Hongbin.

In: IEEE Signal Processing Letters, Vol. 17, No. 5, 5411756, 07.04.2010, p. 449-452.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Distributed estimation of gaussmarkov random fields with one-bit quantized data

AU - Fang, Jun

AU - Li, Hongbin

PY - 2010/4/7

Y1 - 2010/4/7

N2 - We consider the problem of distributed estimation of a GaussMarkov random field using a wireless sensor network (WSN), where due to the stringent power and communication constraints, each sensor has to quantize its data before transmission. In this case, the convergence of conventional iterative matrix-splitting algorithms is hindered by the quantization errors. To address this issue, we propose a one-bit adaptive quantization approach which leads to decaying quantization errors. Numerical results show that even with one bit quantization, the proposed approach achieves a superior mean square deviation performance (with respect to the global linear minimum mean-square error estimate) within a moderate number of iterations.

AB - We consider the problem of distributed estimation of a GaussMarkov random field using a wireless sensor network (WSN), where due to the stringent power and communication constraints, each sensor has to quantize its data before transmission. In this case, the convergence of conventional iterative matrix-splitting algorithms is hindered by the quantization errors. To address this issue, we propose a one-bit adaptive quantization approach which leads to decaying quantization errors. Numerical results show that even with one bit quantization, the proposed approach achieves a superior mean square deviation performance (with respect to the global linear minimum mean-square error estimate) within a moderate number of iterations.

UR - http://www.scopus.com/inward/record.url?scp=77950315556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950315556&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/LSP.2010.2043157

DO - https://doi.org/10.1109/LSP.2010.2043157

M3 - Article

VL - 17

SP - 449

EP - 452

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 5

M1 - 5411756

ER -