A Delay-Range-Dependent Approach to Design State Estimator for Discrete-Time Recurrent Neural Networks With Interval Time-Varying Delay

Author

Lu, Chien-Yu

Author_Institution

Dept. of Ind. Educ. & Technol., Nat. Changhua Univ. of Educ., Changhua

Volume

55

Issue

11

fYear

2008

Firstpage

1163

Lastpage

1167

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.

Keywords

asymptotic stability; delays; discrete time systems; matrix algebra; recurrent neural nets; state estimation; time-varying systems; activation function; delay-range-dependent approach; design state estimator; discrete-time recurrent neural network; general full-order state estimator; globally Lipschitz continuous; globally asymptotic stability; interval time-varying delay; linear matrix inequalities; Asymptotic stability; Biomedical signal processing; Delay effects; Delay estimation; Delay lines; Linear matrix inequalities; Neural networks; Neurons; Recurrent neural networks; State estimation; Delay-range-dependent; interval time-varying delay; linear matrix inequality; state estimator;

fLanguage

English

Journal_Title

Circuits and Systems II: Express Briefs, IEEE Transactions on

Publisher

ieee

ISSN

1549-7747

Type

jour

DOI

10.1109/TCSII.2008.2001988

Filename

4703516