Distributed Gaussian process regression under localization uncertainty

Sungjoon Choi, Mahdi Jadaliha, Jongeun Choi, Songhwai Oh

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In this paper, we propose distributed Gaussian process regression (GPR) for resource-constrained distributed sensor networks under localization uncertainty. The proposed distributed algorithm, which combines Jacobi over-relaxation (JOR) and discrete-time average consensus (DAC), can effectively handle localization uncertainty as well as limited communication and computation capabilities of distributed sensor networks. We also extend the proposed method hierarchically using sparse GPR to improve its scalability. The performance of the proposed method is verified in numerical simulations against the centralized maximum a posteriori (MAP) solution and a quick-and-dirty solution. We show that the proposed method outperforms the quick-and-dirty solution and achieve an accuracy comparable to the centralized solution.

Original languageEnglish
Article number031002
JournalJournal of Dynamic Systems, Measurement and Control, Transactions of the ASME
Volume137
Issue number3
DOIs
Publication statusPublished - 2015 Mar 1

Fingerprint

regression analysis
Sensor networks
sensors
Parallel algorithms
Scalability
resources
communication
Uncertainty
Communication
Computer simulation
simulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Information Systems
  • Instrumentation
  • Mechanical Engineering
  • Computer Science Applications

Cite this

@article{7c0160acbb0342e79782dcf42f7868ff,
title = "Distributed Gaussian process regression under localization uncertainty",
abstract = "In this paper, we propose distributed Gaussian process regression (GPR) for resource-constrained distributed sensor networks under localization uncertainty. The proposed distributed algorithm, which combines Jacobi over-relaxation (JOR) and discrete-time average consensus (DAC), can effectively handle localization uncertainty as well as limited communication and computation capabilities of distributed sensor networks. We also extend the proposed method hierarchically using sparse GPR to improve its scalability. The performance of the proposed method is verified in numerical simulations against the centralized maximum a posteriori (MAP) solution and a quick-and-dirty solution. We show that the proposed method outperforms the quick-and-dirty solution and achieve an accuracy comparable to the centralized solution.",
author = "Sungjoon Choi and Mahdi Jadaliha and Jongeun Choi and Songhwai Oh",
year = "2015",
month = "3",
day = "1",
doi = "10.1115/1.4028148",
language = "English",
volume = "137",
journal = "Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME",
issn = "0022-0434",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "3",

}

Distributed Gaussian process regression under localization uncertainty. / Choi, Sungjoon; Jadaliha, Mahdi; Choi, Jongeun; Oh, Songhwai.

In: Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, Vol. 137, No. 3, 031002, 01.03.2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Distributed Gaussian process regression under localization uncertainty

AU - Choi, Sungjoon

AU - Jadaliha, Mahdi

AU - Choi, Jongeun

AU - Oh, Songhwai

PY - 2015/3/1

Y1 - 2015/3/1

N2 - In this paper, we propose distributed Gaussian process regression (GPR) for resource-constrained distributed sensor networks under localization uncertainty. The proposed distributed algorithm, which combines Jacobi over-relaxation (JOR) and discrete-time average consensus (DAC), can effectively handle localization uncertainty as well as limited communication and computation capabilities of distributed sensor networks. We also extend the proposed method hierarchically using sparse GPR to improve its scalability. The performance of the proposed method is verified in numerical simulations against the centralized maximum a posteriori (MAP) solution and a quick-and-dirty solution. We show that the proposed method outperforms the quick-and-dirty solution and achieve an accuracy comparable to the centralized solution.

AB - In this paper, we propose distributed Gaussian process regression (GPR) for resource-constrained distributed sensor networks under localization uncertainty. The proposed distributed algorithm, which combines Jacobi over-relaxation (JOR) and discrete-time average consensus (DAC), can effectively handle localization uncertainty as well as limited communication and computation capabilities of distributed sensor networks. We also extend the proposed method hierarchically using sparse GPR to improve its scalability. The performance of the proposed method is verified in numerical simulations against the centralized maximum a posteriori (MAP) solution and a quick-and-dirty solution. We show that the proposed method outperforms the quick-and-dirty solution and achieve an accuracy comparable to the centralized solution.

UR - http://www.scopus.com/inward/record.url?scp=84929623600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929623600&partnerID=8YFLogxK

U2 - 10.1115/1.4028148

DO - 10.1115/1.4028148

M3 - Article

AN - SCOPUS:84929623600

VL - 137

JO - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

JF - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

SN - 0022-0434

IS - 3

M1 - 031002

ER -