Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l₂$-$l∞$ Performances

Hyun Duck Choi, Choon Ki Ahn, Hamid Reza Karimi, Myo Taeg Lim

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

This paper studies delay-dependent exponential dissipative and l₂-l∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l₂-l∞ senses. The design of the desired exponential dissipative and l₂-l∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.

Original languageEnglish
JournalIEEE Transactions on Cybernetics
DOIs
Publication statusAccepted/In press - 2017 Jan 31

Fingerprint

Linear matrix inequalities
Neural networks
Computer simulation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{fb573ebafd29409e815ff71200389f65,
title = "Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l₂$-$l∞$ Performances",
abstract = "This paper studies delay-dependent exponential dissipative and l₂-l∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l₂-l∞ senses. The design of the desired exponential dissipative and l₂-l∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.",
author = "Choi, {Hyun Duck} and Ahn, {Choon Ki} and Karimi, {Hamid Reza} and Lim, {Myo Taeg}",
year = "2017",
month = "1",
day = "31",
doi = "10.1109/TCYB.2017.2655725",
language = "English",
journal = "IEEE Transactions on Cybernetics",
issn = "2168-2267",
publisher = "IEEE Advancing Technology for Humanity",

}

TY - JOUR

T1 - Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l₂$-$l∞$ Performances

AU - Choi, Hyun Duck

AU - Ahn, Choon Ki

AU - Karimi, Hamid Reza

AU - Lim, Myo Taeg

PY - 2017/1/31

Y1 - 2017/1/31

N2 - This paper studies delay-dependent exponential dissipative and l₂-l∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l₂-l∞ senses. The design of the desired exponential dissipative and l₂-l∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.

AB - This paper studies delay-dependent exponential dissipative and l₂-l∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l₂-l∞ senses. The design of the desired exponential dissipative and l₂-l∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.

UR - http://www.scopus.com/inward/record.url?scp=85011665785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011665785&partnerID=8YFLogxK

U2 - 10.1109/TCYB.2017.2655725

DO - 10.1109/TCYB.2017.2655725

M3 - Article

C2 - 28166518

AN - SCOPUS:85011665785

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

SN - 2168-2267

ER -