Exponentially convergent state estimation for delayed switched recurrent neural networks

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This paper deals with the delay-dependent exponentially convergent state estimation problem for delayed switched neural networks. A set of delay-dependent criteria is derived under which the resulting estimation error system is exponentially stable. It is shown that the gain matrix of the proposed state estimator is characterised in terms of the solution to a set of linear matrix inequalities (LMIs), which can be checked readily by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator.

Original languageEnglish
Article number122
JournalEuropean Physical Journal E
Volume34
Issue number11
DOIs
Publication statusPublished - 2011 Nov 1
Externally publishedYes

Fingerprint

state estimation
Recurrent neural networks
State estimation
Linear matrix inequalities
estimators
Error analysis
Neural networks
matrices

ASJC Scopus subject areas

  • Materials Science(all)
  • Surfaces and Interfaces
  • Chemistry(all)
  • Biophysics
  • Biotechnology

Cite this

Exponentially convergent state estimation for delayed switched recurrent neural networks. / Ahn, Choon Ki.

In: European Physical Journal E, Vol. 34, No. 11, 122, 01.11.2011.

Research output: Contribution to journalArticle

@article{516c86ae9924442ca3ee66015d9bb544,
title = "Exponentially convergent state estimation for delayed switched recurrent neural networks",
abstract = "This paper deals with the delay-dependent exponentially convergent state estimation problem for delayed switched neural networks. A set of delay-dependent criteria is derived under which the resulting estimation error system is exponentially stable. It is shown that the gain matrix of the proposed state estimator is characterised in terms of the solution to a set of linear matrix inequalities (LMIs), which can be checked readily by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator.",
author = "Ahn, {Choon Ki}",
year = "2011",
month = "11",
day = "1",
doi = "10.1140/epje/i2011-11122-8",
language = "English",
volume = "34",
journal = "European Physical Journal E",
issn = "1292-8941",
publisher = "Springer New York",
number = "11",

}

TY - JOUR

T1 - Exponentially convergent state estimation for delayed switched recurrent neural networks

AU - Ahn, Choon Ki

PY - 2011/11/1

Y1 - 2011/11/1

N2 - This paper deals with the delay-dependent exponentially convergent state estimation problem for delayed switched neural networks. A set of delay-dependent criteria is derived under which the resulting estimation error system is exponentially stable. It is shown that the gain matrix of the proposed state estimator is characterised in terms of the solution to a set of linear matrix inequalities (LMIs), which can be checked readily by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator.

AB - This paper deals with the delay-dependent exponentially convergent state estimation problem for delayed switched neural networks. A set of delay-dependent criteria is derived under which the resulting estimation error system is exponentially stable. It is shown that the gain matrix of the proposed state estimator is characterised in terms of the solution to a set of linear matrix inequalities (LMIs), which can be checked readily by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator.

UR - http://www.scopus.com/inward/record.url?scp=84855825309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855825309&partnerID=8YFLogxK

U2 - 10.1140/epje/i2011-11122-8

DO - 10.1140/epje/i2011-11122-8

M3 - Article

C2 - 22101508

AN - SCOPUS:84855825309

VL - 34

JO - European Physical Journal E

JF - European Physical Journal E

SN - 1292-8941

IS - 11

M1 - 122

ER -