Stochastic H filtering for neural networks with leakage delay and mixed time-varying delays

M. Syed Ali, R. Saravanakumar, Choon Ki Ahn, Hamid Reza Karimi

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This paper deals with the problem of H filtering for stochastic neural networks (SNNs) with a mixed of time-varying interval delays, time-varying distributed delays, and leakage delays. A novel quintuple integral Lyapunov–Krasovskii functional (LKF) is constructed to improve the performance of the SNN. Sufficient criteria can be obtained by applying the linear matrix inequality (LMI) approach and developing a new mathematical analysis, which ensures the filtering error system is asymptotically stable in the mean square. Finally, simulation results are provided to show the superiority and usefulness of the proposed method.

Original languageEnglish
Pages (from-to)118-134
Number of pages17
JournalInformation Sciences
Volume388-389
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Stochastic Neural Networks
Time-varying Delay
Leakage
Filtering
Neural Networks
Neural networks
Distributed Delay
Lyapunov-Krasovskii Functional
Delay Time
Asymptotically Stable
Linear matrix inequalities
Mathematical Analysis
Mean Square
Matrix Inequality
Linear Inequalities
Time delay
Time-varying
Sufficient
Simulation
Time-varying delay

Keywords

  • H filtering
  • Leakage delay
  • Linear matrix inequality
  • Stochastic neural networks
  • Time-varying delay

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Software
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Stochastic H filtering for neural networks with leakage delay and mixed time-varying delays. / Syed Ali, M.; Saravanakumar, R.; Ahn, Choon Ki; Karimi, Hamid Reza.

In: Information Sciences, Vol. 388-389, 01.05.2017, p. 118-134.

Research output: Contribution to journalArticle

Syed Ali, M. ; Saravanakumar, R. ; Ahn, Choon Ki ; Karimi, Hamid Reza. / Stochastic H filtering for neural networks with leakage delay and mixed time-varying delays. In: Information Sciences. 2017 ; Vol. 388-389. pp. 118-134.
@article{97e6293f35b240ce8d2c8c8a49a174b6,
title = "Stochastic H∞ filtering for neural networks with leakage delay and mixed time-varying delays",
abstract = "This paper deals with the problem of H∞ filtering for stochastic neural networks (SNNs) with a mixed of time-varying interval delays, time-varying distributed delays, and leakage delays. A novel quintuple integral Lyapunov–Krasovskii functional (LKF) is constructed to improve the performance of the SNN. Sufficient criteria can be obtained by applying the linear matrix inequality (LMI) approach and developing a new mathematical analysis, which ensures the filtering error system is asymptotically stable in the mean square. Finally, simulation results are provided to show the superiority and usefulness of the proposed method.",
keywords = "H filtering, Leakage delay, Linear matrix inequality, Stochastic neural networks, Time-varying delay",
author = "{Syed Ali}, M. and R. Saravanakumar and Ahn, {Choon Ki} and Karimi, {Hamid Reza}",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.ins.2017.01.010",
language = "English",
volume = "388-389",
pages = "118--134",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Stochastic H∞ filtering for neural networks with leakage delay and mixed time-varying delays

AU - Syed Ali, M.

AU - Saravanakumar, R.

AU - Ahn, Choon Ki

AU - Karimi, Hamid Reza

PY - 2017/5/1

Y1 - 2017/5/1

N2 - This paper deals with the problem of H∞ filtering for stochastic neural networks (SNNs) with a mixed of time-varying interval delays, time-varying distributed delays, and leakage delays. A novel quintuple integral Lyapunov–Krasovskii functional (LKF) is constructed to improve the performance of the SNN. Sufficient criteria can be obtained by applying the linear matrix inequality (LMI) approach and developing a new mathematical analysis, which ensures the filtering error system is asymptotically stable in the mean square. Finally, simulation results are provided to show the superiority and usefulness of the proposed method.

AB - This paper deals with the problem of H∞ filtering for stochastic neural networks (SNNs) with a mixed of time-varying interval delays, time-varying distributed delays, and leakage delays. A novel quintuple integral Lyapunov–Krasovskii functional (LKF) is constructed to improve the performance of the SNN. Sufficient criteria can be obtained by applying the linear matrix inequality (LMI) approach and developing a new mathematical analysis, which ensures the filtering error system is asymptotically stable in the mean square. Finally, simulation results are provided to show the superiority and usefulness of the proposed method.

KW - H filtering

KW - Leakage delay

KW - Linear matrix inequality

KW - Stochastic neural networks

KW - Time-varying delay

UR - http://www.scopus.com/inward/record.url?scp=85009518319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009518319&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2017.01.010

DO - 10.1016/j.ins.2017.01.010

M3 - Article

AN - SCOPUS:85009518319

VL - 388-389

SP - 118

EP - 134

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -