Spatial prediction with mobile sensor networks using Gaussian processes with built-in Gaussian Markov random fields

Yunfei Xu, Jongeun Choi

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

In this paper, a new class of Gaussian processes is proposed for resource-constrained mobile sensor networks. Such a Gaussian process builds on a GMRF with respect to a proximity graph over a surveillance region. The main advantages of using this class of Gaussian processes over standard Gaussian processes defined by mean and covariance functions are its numerical efficiency and scalability due to its built-in GMRF and its capability of representing a wide range of non-stationary physical processes. The formulas for predictive statistics such as predictive mean and variance are derived and a sequential field prediction algorithm is provided for sequentially sampled observations. For a special case using compactly supported weighting functions, we propose a distributed algorithm to implement field prediction by correctly fusing all observations. Simulation and experimental results illustrate the effectiveness of our approach.

Original languageEnglish
Pages (from-to)1735-1740
Number of pages6
JournalAutomatica
Volume48
Issue number8
DOIs
Publication statusPublished - 2012 Aug 1

Fingerprint

Sensor networks
Wireless networks
Parallel algorithms
Scalability
Statistics

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

@article{e58012978d324166adf46d55cf001deb,
title = "Spatial prediction with mobile sensor networks using Gaussian processes with built-in Gaussian Markov random fields",
abstract = "In this paper, a new class of Gaussian processes is proposed for resource-constrained mobile sensor networks. Such a Gaussian process builds on a GMRF with respect to a proximity graph over a surveillance region. The main advantages of using this class of Gaussian processes over standard Gaussian processes defined by mean and covariance functions are its numerical efficiency and scalability due to its built-in GMRF and its capability of representing a wide range of non-stationary physical processes. The formulas for predictive statistics such as predictive mean and variance are derived and a sequential field prediction algorithm is provided for sequentially sampled observations. For a special case using compactly supported weighting functions, we propose a distributed algorithm to implement field prediction by correctly fusing all observations. Simulation and experimental results illustrate the effectiveness of our approach.",
author = "Yunfei Xu and Jongeun Choi",
year = "2012",
month = "8",
day = "1",
doi = "10.1016/j.automatica.2012.05.029",
language = "English",
volume = "48",
pages = "1735--1740",
journal = "Automatica",
issn = "0005-1098",
publisher = "Elsevier Limited",
number = "8",

}

Spatial prediction with mobile sensor networks using Gaussian processes with built-in Gaussian Markov random fields. / Xu, Yunfei; Choi, Jongeun.

In: Automatica, Vol. 48, No. 8, 01.08.2012, p. 1735-1740.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spatial prediction with mobile sensor networks using Gaussian processes with built-in Gaussian Markov random fields

AU - Xu, Yunfei

AU - Choi, Jongeun

PY - 2012/8/1

Y1 - 2012/8/1

N2 - In this paper, a new class of Gaussian processes is proposed for resource-constrained mobile sensor networks. Such a Gaussian process builds on a GMRF with respect to a proximity graph over a surveillance region. The main advantages of using this class of Gaussian processes over standard Gaussian processes defined by mean and covariance functions are its numerical efficiency and scalability due to its built-in GMRF and its capability of representing a wide range of non-stationary physical processes. The formulas for predictive statistics such as predictive mean and variance are derived and a sequential field prediction algorithm is provided for sequentially sampled observations. For a special case using compactly supported weighting functions, we propose a distributed algorithm to implement field prediction by correctly fusing all observations. Simulation and experimental results illustrate the effectiveness of our approach.

AB - In this paper, a new class of Gaussian processes is proposed for resource-constrained mobile sensor networks. Such a Gaussian process builds on a GMRF with respect to a proximity graph over a surveillance region. The main advantages of using this class of Gaussian processes over standard Gaussian processes defined by mean and covariance functions are its numerical efficiency and scalability due to its built-in GMRF and its capability of representing a wide range of non-stationary physical processes. The formulas for predictive statistics such as predictive mean and variance are derived and a sequential field prediction algorithm is provided for sequentially sampled observations. For a special case using compactly supported weighting functions, we propose a distributed algorithm to implement field prediction by correctly fusing all observations. Simulation and experimental results illustrate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84864423997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864423997&partnerID=8YFLogxK

U2 - 10.1016/j.automatica.2012.05.029

DO - 10.1016/j.automatica.2012.05.029

M3 - Article

VL - 48

SP - 1735

EP - 1740

JO - Automatica

JF - Automatica

SN - 0005-1098

IS - 8

ER -