Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and l2-l8 Performances

被引：85

作者：

Choi, Hyun Duck ^{[1
]}

Ahn, Choon Ki ^{[1
]}

Karimi, Hamid Reza ^{[2
]}

Lim, Myo Taeg ^{[1
]}

机构：

[1] Korea Univ, Sch Elect Engn, Seoul 136701, South Korea

[2] Politecn Milan, Dept Mech Engn, I-20156 Milan, Italy

来源：

IEEE TRANSACTIONS ON CYBERNETICS | 2017年 / 47卷 / 10期

基金：

新加坡国家研究基金会;

关键词：

l(2)-l(8) filtering; discrete Wirtinger-type inequality; discrete-time switched neural networks (DSNNs); dissipative filtering; exponential stability; INFINITY STATE ESTIMATION; AVERAGE DWELL TIME; H-INFINITY; STABILITY ANALYSIS; ROBUST STABILITY; DISTURBANCE ATTENUATION; LINEAR-SYSTEMS; DELAY; STABILIZATION; DESIGN;

D O I：

10.1109/TCYB.2017.2655725

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper studies delay-dependent exponential dissipative and l(2)-l(8) 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 l(2)-l(8) senses. The design of the desired exponential dissipative and l(2)-l(8) 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.

引用

页码：3195 / 3207

页数：13

共 59 条

[1] Deadbeat Dissipative FIR Filtering [J].

Ahn, Choon Ki ;

Shi, Peng ;

Basin, Michael V. .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2016, 63 (08) :1210-1221

[2] Stochastic stability analysis for 2-D Roesser systems with multiplicative noise [J].

Ahn, Choon Ki ;

Wu, Ligang ;

Shi, Peng .

AUTOMATICA, 2016, 69 :356-363

[3] Receding Horizon Stabilization and Disturbance Attenuation for Neural Networks With Time-Varying Delay [J].

Ahn, Choon Ki ;

Shi, Peng ;

Wu, Ligang .

IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (12) :2680-2692

[4] Two-Dimensional Dissipative Control and Filtering for Roesser Model [J].

Ahn, Choon Ki ;

Shi, Peng ;

Basin, Michael V. .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2015, 60 (07) :1745-1759

[5] Receding horizon disturbance attenuation for Takagi-Sugeno fuzzy switched dynamic neural networks [J].

Ahn, Choon Ki .

INFORMATION SCIENCES, 2014, 280 :53-63

[6] l2 - l∞ Elimination of Overflow Oscillations in 2-D Digital Filters Described by Roesser Model With External Interference [J].

Ahn, Choon Ki .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2013, 60 (06) :361-365

[7] Linear Matrix Inequality Optimization Approach to Exponential Robust Filtering for Switched Hopfield Neural Networks [J].

Ahn, Choon Ki .

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2012, 154 (02) :573-587

[8] Switched exponential state estimation of neural networks based on passivity theory [J].

Ahn, Choon Ki .

NONLINEAR DYNAMICS, 2012, 67 (01) :573-586

[9] Novel H∞ state estimation of static neural networks with interval time-varying delays via augmented Lyapunov-Krasovskii functional [J].

Ali, M. Syed ;

Saravanakumar, R. ;

Arik, Sabri .

NEUROCOMPUTING, 2016, 171 :949-954

[10] State estimation for switched discrete-time stochastic BAM neural networks with time varying delay [J].

Arunkumar, A. ;

Sakthivel, R. ;

Mathiyalagan, K. ;

Anthoni, S. Marshal .

NONLINEAR DYNAMICS, 2013, 73 (03) :1565-1585

← 1 2 3 4 5 6 →