An advanced evolutionary algorithm for parameter estimation of the discrete kalman filter

Zeke S.H. Chan; H. W. Ngan; Y. F. Fung; A. B. Rad

doi:10.1016/S0010-4655(01)00332-0

An advanced evolutionary algorithm for parameter estimation of the discrete kalman filter

Zeke S.H. Chan
, H. W. Ngan
, Y. F. Fung
, A. B. Rad

Research output: Journal article publication › Journal article › Academic research › peer-review

8 Citations (Scopus)

Abstract

In this work we design an advanced Evolutionary Algorithm (EA) for optimizing the discrete Kalman filter (KF) model. The EA employs parallel architecture and an advanced mutation operator called the "Selection Follower". Its performance is benchmarked with that of the Expectation-Maximization algorithm (EM) in minimizing the mean-square-error of the KF prediction. Experimental results show that the EA consistently outperforms the EM and runs significantly faster under the same number of function evaluations.

Original language	English
Pages (from-to)	248-254
Number of pages	7
Journal	Computer Physics Communications
Volume	142
Issue number	1-3
DOIs	https://doi.org/10.1016/S0010-4655(01)00332-0
Publication status	Published - 15 Dec 2001

Keywords

Adaptive mutation
Evolutionary algorithm
Genetic algorithm
Kalman filter
Load forecasting

ASJC Scopus subject areas

Hardware and Architecture
General Physics and Astronomy

More information

10.1016/S0010-4655(01)00332-0

Cite this

@article{79521188d903469e80c77571caee36b5,

title = "An advanced evolutionary algorithm for parameter estimation of the discrete kalman filter",

abstract = "In this work we design an advanced Evolutionary Algorithm (EA) for optimizing the discrete Kalman filter (KF) model. The EA employs parallel architecture and an advanced mutation operator called the {"}Selection Follower{"}. Its performance is benchmarked with that of the Expectation-Maximization algorithm (EM) in minimizing the mean-square-error of the KF prediction. Experimental results show that the EA consistently outperforms the EM and runs significantly faster under the same number of function evaluations.",

keywords = "Adaptive mutation, Evolutionary algorithm, Genetic algorithm, Kalman filter, Load forecasting",

author = "Chan, \{Zeke S.H.\} and Ngan, \{H. W.\} and Fung, \{Y. F.\} and Rad, \{A. B.\}",

year = "2001",

month = dec,

day = "15",

doi = "10.1016/S0010-4655(01)00332-0",

language = "English",

volume = "142",

pages = "248--254",

journal = "Computer Physics Communications",

issn = "0010-4655",

publisher = "Elsevier B.V.",

number = "1-3",

}

TY - JOUR

T1 - An advanced evolutionary algorithm for parameter estimation of the discrete kalman filter

AU - Chan, Zeke S.H.

AU - Ngan, H. W.

AU - Fung, Y. F.

AU - Rad, A. B.

PY - 2001/12/15

Y1 - 2001/12/15

N2 - In this work we design an advanced Evolutionary Algorithm (EA) for optimizing the discrete Kalman filter (KF) model. The EA employs parallel architecture and an advanced mutation operator called the "Selection Follower". Its performance is benchmarked with that of the Expectation-Maximization algorithm (EM) in minimizing the mean-square-error of the KF prediction. Experimental results show that the EA consistently outperforms the EM and runs significantly faster under the same number of function evaluations.

AB - In this work we design an advanced Evolutionary Algorithm (EA) for optimizing the discrete Kalman filter (KF) model. The EA employs parallel architecture and an advanced mutation operator called the "Selection Follower". Its performance is benchmarked with that of the Expectation-Maximization algorithm (EM) in minimizing the mean-square-error of the KF prediction. Experimental results show that the EA consistently outperforms the EM and runs significantly faster under the same number of function evaluations.

KW - Adaptive mutation

KW - Evolutionary algorithm

KW - Genetic algorithm

KW - Kalman filter

KW - Load forecasting

UR - https://www.scopus.com/pages/publications/0035892834

U2 - 10.1016/S0010-4655(01)00332-0

DO - 10.1016/S0010-4655(01)00332-0

M3 - Journal article

AN - SCOPUS:0035892834

SN - 0010-4655

VL - 142

SP - 248

EP - 254

JO - Computer Physics Communications

JF - Computer Physics Communications

IS - 1-3

ER -

An advanced evolutionary algorithm for parameter estimation of the discrete kalman filter

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this