Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems

Peng Shi; Fanbiao Li; Ligang Wu; Cheng Chew Lim

doi:10.1109/TNNLS.2016.2573853

Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems

Peng Shi
, Fanbiao Li^*
, Ligang Wu
, Cheng Chew Lim

^*Corresponding author for this work

School of Astronautics

University of Adelaide
Victoria University
Central South University

Research output: Contribution to journal › Article › peer-review

273 Scopus citations

Abstract

This paper investigates the problem of exponential passive filtering for a class of stochastic neutral-type neural networks with both semi-Markovian jump parameters and mixed time delays. Our aim is to estimate the states by designing a Luenberger-type observer, such that the filter error dynamics are mean-square exponentially stable with an expected decay rate and an attenuation level. Sufficient conditions for the existence of passive filters are obtained, and a convex optimization algorithm for the filter design is given. In addition, a cone complementarity linearization procedure is employed to cast the nonconvex feasibility problem into a sequential minimization problem, which can be readily solved by the existing optimization techniques. Numerical examples are given to demonstrate the effectiveness of the proposed techniques.

Original language	English
Article number	7491305
Pages (from-to)	2101-2114
Number of pages	14
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	28
Issue number	9
DOIs	https://doi.org/10.1109/TNNLS.2016.2573853
State	Published - Sep 2017

Keywords

Filtering
neural networks (NNs)
semi-Markovian jump systems (S-MJSs)
time delay

Access to Document

10.1109/TNNLS.2016.2573853

Cite this

@article{0d88183fbc84420b8efef818c1f8ca0f,

title = "Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems",

abstract = "This paper investigates the problem of exponential passive filtering for a class of stochastic neutral-type neural networks with both semi-Markovian jump parameters and mixed time delays. Our aim is to estimate the states by designing a Luenberger-type observer, such that the filter error dynamics are mean-square exponentially stable with an expected decay rate and an attenuation level. Sufficient conditions for the existence of passive filters are obtained, and a convex optimization algorithm for the filter design is given. In addition, a cone complementarity linearization procedure is employed to cast the nonconvex feasibility problem into a sequential minimization problem, which can be readily solved by the existing optimization techniques. Numerical examples are given to demonstrate the effectiveness of the proposed techniques.",

keywords = "Filtering, neural networks (NNs), semi-Markovian jump systems (S-MJSs), time delay",

author = "Peng Shi and Fanbiao Li and Ligang Wu and Lim, \{Cheng Chew\}",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2017",

month = sep,

doi = "10.1109/TNNLS.2016.2573853",

language = "英语",

volume = "28",

pages = "2101--2114",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "9",

}

TY - JOUR

T1 - Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems

AU - Shi, Peng

AU - Li, Fanbiao

AU - Wu, Ligang

AU - Lim, Cheng Chew

PY - 2017/9

Y1 - 2017/9

N2 - This paper investigates the problem of exponential passive filtering for a class of stochastic neutral-type neural networks with both semi-Markovian jump parameters and mixed time delays. Our aim is to estimate the states by designing a Luenberger-type observer, such that the filter error dynamics are mean-square exponentially stable with an expected decay rate and an attenuation level. Sufficient conditions for the existence of passive filters are obtained, and a convex optimization algorithm for the filter design is given. In addition, a cone complementarity linearization procedure is employed to cast the nonconvex feasibility problem into a sequential minimization problem, which can be readily solved by the existing optimization techniques. Numerical examples are given to demonstrate the effectiveness of the proposed techniques.

AB - This paper investigates the problem of exponential passive filtering for a class of stochastic neutral-type neural networks with both semi-Markovian jump parameters and mixed time delays. Our aim is to estimate the states by designing a Luenberger-type observer, such that the filter error dynamics are mean-square exponentially stable with an expected decay rate and an attenuation level. Sufficient conditions for the existence of passive filters are obtained, and a convex optimization algorithm for the filter design is given. In addition, a cone complementarity linearization procedure is employed to cast the nonconvex feasibility problem into a sequential minimization problem, which can be readily solved by the existing optimization techniques. Numerical examples are given to demonstrate the effectiveness of the proposed techniques.

KW - Filtering

KW - neural networks (NNs)

KW - semi-Markovian jump systems (S-MJSs)

KW - time delay

UR - https://www.scopus.com/pages/publications/84974856554

U2 - 10.1109/TNNLS.2016.2573853

DO - 10.1109/TNNLS.2016.2573853

M3 - 文章

C2 - 27323377

AN - SCOPUS:84974856554

SN - 2162-237X

VL - 28

SP - 2101

EP - 2114

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 9

M1 - 7491305

ER -

Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this