A delay-range-dependent approach to design state estimator for discrete-time recurrent neural networks with interval time-varying delay

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

This paper deals with the problem of state estimation for discrete-time recurrent neural networks with interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. A delay-range-dependent condition for the existence of state estimators is proposed. Via available output measurements and solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. Two illustrative examples are given to demonstrate the effectiveness and applicability.

Original languageEnglish
Pages (from-to)1163-1167
Number of pages5
JournalIEEE Transactions on Circuits and Systems II: Express Briefs
Volume55
Issue number11
DOIs
Publication statusPublished - 2008 Dec 30

Fingerprint

Recurrent neural networks
State estimation
Asymptotic stability
Linear matrix inequalities
Chemical activation

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{1cdde6377dd74d3b9f051f9aff42946c,
title = "A delay-range-dependent approach to design state estimator for discrete-time recurrent neural networks with interval time-varying delay",
abstract = "This paper deals with the problem of state estimation for discrete-time recurrent neural networks with interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. A delay-range-dependent condition for the existence of state estimators is proposed. Via available output measurements and solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. Two illustrative examples are given to demonstrate the effectiveness and applicability.",
author = "Lu, {Chien Yu}",
year = "2008",
month = "12",
day = "30",
doi = "10.1109/TCSII.2008.2001988",
language = "English",
volume = "55",
pages = "1163--1167",
journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",
issn = "1549-7747",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - A delay-range-dependent approach to design state estimator for discrete-time recurrent neural networks with interval time-varying delay

AU - Lu, Chien Yu

PY - 2008/12/30

Y1 - 2008/12/30

N2 - This paper deals with the problem of state estimation for discrete-time recurrent neural networks with interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. A delay-range-dependent condition for the existence of state estimators is proposed. Via available output measurements and solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. Two illustrative examples are given to demonstrate the effectiveness and applicability.

AB - This paper deals with the problem of state estimation for discrete-time recurrent neural networks with interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. A delay-range-dependent condition for the existence of state estimators is proposed. Via available output measurements and solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. Two illustrative examples are given to demonstrate the effectiveness and applicability.

UR - http://www.scopus.com/inward/record.url?scp=57949115389&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57949115389&partnerID=8YFLogxK

U2 - 10.1109/TCSII.2008.2001988

DO - 10.1109/TCSII.2008.2001988

M3 - Article

AN - SCOPUS:57949115389

VL - 55

SP - 1163

EP - 1167

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

SN - 1549-7747

IS - 11

ER -