An LMI based state estimator for delayed Hopfield neural networks

Yun Chen; Wei Xing Zheng

doi:10.1109/ISCAS.2011.5938157

An LMI based state estimator for delayed Hopfield neural networks

Yun Chen, Wei Xing Zheng

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

2 Citations (Scopus)

Abstract

The problem of state estimation for Markovian jumping Hopfield neural networks (MJHNNs) with delays is addressed in this paper. It is assumed that sector- bounded conditions are obeyed by the neuron activation function and perturbed function of the measurement equation. An LMI (linear matrix inequality) based state estimator and a stability criterion for delay MJHNNs are developed. It is shown that the designed estimator ensures the mean-square exponential stability of the resulting error system. Moreover, the delay-dependent sufficient conditions are derived in a simple and effective manner. Numerical results are presented which show that the proposed method is very promising for state estimation of Hopfield neural networks.

Original language	English
Title of host publication	Proceedings of the 2011 IEEE International Symposium on Circuits and Systems (ISCAS 2011), Rio de Janeiro, Brazil, 15-18 May 2011
Publisher	IEEE
Pages	2681-2684
Number of pages	4
ISBN (Print)	9781424494736
DOIs	https://doi.org/10.1109/ISCAS.2011.5938157
Publication status	Published - 2011
Event	IEEE International Symposium on Circuits and Systems - Duration: 20 May 2012 → …

Conference

Conference	IEEE International Symposium on Circuits and Systems
Period	20/05/12 → …

Access to Document

10.1109/ISCAS.2011.5938157

Cite this

@inproceedings{2ef9281113024a4baf3382e00da25e40,

title = "An LMI based state estimator for delayed Hopfield neural networks",

abstract = "The problem of state estimation for Markovian jumping Hopfield neural networks (MJHNNs) with delays is addressed in this paper. It is assumed that sector- bounded conditions are obeyed by the neuron activation function and perturbed function of the measurement equation. An LMI (linear matrix inequality) based state estimator and a stability criterion for delay MJHNNs are developed. It is shown that the designed estimator ensures the mean-square exponential stability of the resulting error system. Moreover, the delay-dependent sufficient conditions are derived in a simple and effective manner. Numerical results are presented which show that the proposed method is very promising for state estimation of Hopfield neural networks.",

author = "Yun Chen and Zheng, {Wei Xing}",

year = "2011",

doi = "10.1109/ISCAS.2011.5938157",

language = "English",

isbn = "9781424494736",

pages = "2681--2684",

booktitle = "Proceedings of the 2011 IEEE International Symposium on Circuits and Systems (ISCAS 2011), Rio de Janeiro, Brazil, 15-18 May 2011",

publisher = "IEEE",

note = "IEEE International Symposium on Circuits and Systems ; Conference date: 20-05-2012",

}

TY - GEN

T1 - An LMI based state estimator for delayed Hopfield neural networks

AU - Chen, Yun

AU - Zheng, Wei Xing

PY - 2011

Y1 - 2011

N2 - The problem of state estimation for Markovian jumping Hopfield neural networks (MJHNNs) with delays is addressed in this paper. It is assumed that sector- bounded conditions are obeyed by the neuron activation function and perturbed function of the measurement equation. An LMI (linear matrix inequality) based state estimator and a stability criterion for delay MJHNNs are developed. It is shown that the designed estimator ensures the mean-square exponential stability of the resulting error system. Moreover, the delay-dependent sufficient conditions are derived in a simple and effective manner. Numerical results are presented which show that the proposed method is very promising for state estimation of Hopfield neural networks.

AB - The problem of state estimation for Markovian jumping Hopfield neural networks (MJHNNs) with delays is addressed in this paper. It is assumed that sector- bounded conditions are obeyed by the neuron activation function and perturbed function of the measurement equation. An LMI (linear matrix inequality) based state estimator and a stability criterion for delay MJHNNs are developed. It is shown that the designed estimator ensures the mean-square exponential stability of the resulting error system. Moreover, the delay-dependent sufficient conditions are derived in a simple and effective manner. Numerical results are presented which show that the proposed method is very promising for state estimation of Hopfield neural networks.

UR - http://handle.uws.edu.au:8081/1959.7/544793

UR - http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=5910713

U2 - 10.1109/ISCAS.2011.5938157

DO - 10.1109/ISCAS.2011.5938157

M3 - Conference Paper

SN - 9781424494736

SP - 2681

EP - 2684

BT - Proceedings of the 2011 IEEE International Symposium on Circuits and Systems (ISCAS 2011), Rio de Janeiro, Brazil, 15-18 May 2011

PB - IEEE

T2 - IEEE International Symposium on Circuits and Systems

Y2 - 20 May 2012

ER -

An LMI based state estimator for delayed Hopfield neural networks

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this