A new evolutionary particle filter for the prevention of sample impoverishment

Seongkeun Park, Jae Pil Hwang, Euntai Kim, Hyung Jin Kang

Research output: Contribution to journalArticle

85 Citations (Scopus)

Abstract

Particle filters perform the nonlinear estimation and have received much attention from many engineering fields over the past decade. Unfortunately, there are some cases in which most particles are concentrated prematurely at a wrong point, thereby losing diversity and causing the estimation to fail. In this paper, genetic algorithms (GAs) are incorporated into a particle filter to overcome this drawback of the filter. By using genetic operators, the premature convergence of the particles is avoided and the search region of particles enlarged. The GA-inspired proposal distribution is proposed and the corresponding importance weight is derived to approximate the given target distribution. Finally, a computer simulation is performed to show the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)801-809
Number of pages9
JournalIEEE Transactions on Evolutionary Computation
Volume13
Issue number4
DOIs
Publication statusPublished - 2009 Jul 3

Fingerprint

Particle Filter
Genetic algorithms
Genetic Algorithm
Nonlinear Estimation
Genetic Operators
Premature Convergence
Computer simulation
Computer Simulation
Filter
Engineering
Target

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Park, Seongkeun ; Hwang, Jae Pil ; Kim, Euntai ; Kang, Hyung Jin. / A new evolutionary particle filter for the prevention of sample impoverishment. In: IEEE Transactions on Evolutionary Computation. 2009 ; Vol. 13, No. 4. pp. 801-809.
@article{ebcfeb41838d471ca22f9ac2b2e7cd3e,
title = "A new evolutionary particle filter for the prevention of sample impoverishment",
abstract = "Particle filters perform the nonlinear estimation and have received much attention from many engineering fields over the past decade. Unfortunately, there are some cases in which most particles are concentrated prematurely at a wrong point, thereby losing diversity and causing the estimation to fail. In this paper, genetic algorithms (GAs) are incorporated into a particle filter to overcome this drawback of the filter. By using genetic operators, the premature convergence of the particles is avoided and the search region of particles enlarged. The GA-inspired proposal distribution is proposed and the corresponding importance weight is derived to approximate the given target distribution. Finally, a computer simulation is performed to show the effectiveness of the proposed method.",
author = "Seongkeun Park and Hwang, {Jae Pil} and Euntai Kim and Kang, {Hyung Jin}",
year = "2009",
month = "7",
day = "3",
doi = "10.1109/TEVC.2008.2011729",
language = "English",
volume = "13",
pages = "801--809",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1089-778X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

A new evolutionary particle filter for the prevention of sample impoverishment. / Park, Seongkeun; Hwang, Jae Pil; Kim, Euntai; Kang, Hyung Jin.

In: IEEE Transactions on Evolutionary Computation, Vol. 13, No. 4, 03.07.2009, p. 801-809.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new evolutionary particle filter for the prevention of sample impoverishment

AU - Park, Seongkeun

AU - Hwang, Jae Pil

AU - Kim, Euntai

AU - Kang, Hyung Jin

PY - 2009/7/3

Y1 - 2009/7/3

N2 - Particle filters perform the nonlinear estimation and have received much attention from many engineering fields over the past decade. Unfortunately, there are some cases in which most particles are concentrated prematurely at a wrong point, thereby losing diversity and causing the estimation to fail. In this paper, genetic algorithms (GAs) are incorporated into a particle filter to overcome this drawback of the filter. By using genetic operators, the premature convergence of the particles is avoided and the search region of particles enlarged. The GA-inspired proposal distribution is proposed and the corresponding importance weight is derived to approximate the given target distribution. Finally, a computer simulation is performed to show the effectiveness of the proposed method.

AB - Particle filters perform the nonlinear estimation and have received much attention from many engineering fields over the past decade. Unfortunately, there are some cases in which most particles are concentrated prematurely at a wrong point, thereby losing diversity and causing the estimation to fail. In this paper, genetic algorithms (GAs) are incorporated into a particle filter to overcome this drawback of the filter. By using genetic operators, the premature convergence of the particles is avoided and the search region of particles enlarged. The GA-inspired proposal distribution is proposed and the corresponding importance weight is derived to approximate the given target distribution. Finally, a computer simulation is performed to show the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=69249209720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69249209720&partnerID=8YFLogxK

U2 - 10.1109/TEVC.2008.2011729

DO - 10.1109/TEVC.2008.2011729

M3 - Article

VL - 13

SP - 801

EP - 809

JO - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1089-778X

IS - 4

ER -