Asynchronous Filtering for Markov Jump Neural Networks With Quantized Outputs

被引：95

作者：

Shen, Ying ^{[1
]}

Wu, Zheng-Guang ^{[1
]}

Shi, Peng ^{[2
,3
]}

Su, Hongye ^{[1
]}

Huang, Tingwen ^{[4
]}

机构：

[1] Zhejiang Univ, Inst Cyber Syst & Control, State Key Lab Ind Control Technol, Hangzhou 310027, Zhejiang, Peoples R China

[2] Univ Adelaide, Sch Elect & Elect Engn, Adelaide, SA 5005, Australia

[3] Victoria Univ, Coll Engn & Sci, Melbourne, Vic 8001, Australia

[4] Texas A&M Univ Qatar, Dept Sci Program, Doha 23874, Qatar

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS | 2019年 / 49卷 / 02期

基金：

中国国家自然科学基金; 澳大利亚研究理事会;

关键词：

Asynchronous filter; asynchronous quantization; dissipativity; hidden Markov model; Markov jump neural networks (MJNNs); MIXED H-INFINITY; EXPONENTIAL STABILITY; SYSTEMS; TIME; DISCRETE; STABILIZATION;

D O I：

10.1109/TSMC.2017.2789180

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, an asynchronous filter is proposed for Markov jump neural networks (NNs) with time delay and quantized measurements where a logarithmic quantizer is employed. The filter and quantizer arc both mode-dependent and their modes are asynchronous with that of the NN, which is described by hidden Markov models. By the Lyapunov-Krasovskii functional approach, a sufficient condition is derived and a filter is then designed such that the filtering error dynamics are stochastically mean square stable and strictly (u, g, v)-dissipative. Finally, the effectiveness and practicability of the theoretical results are verified by two examples, including a biological network.

引用

页码：433 / 443

页数：11

共 46 条

[1] Neural network applications in power electronics and motor drives- An introduction and perspective [J].

Bose, Bimal K. .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2007, 54 (01) :14-33

[2] Segmented-Memory Recurrent Neural Networks [J].

Chen, Jinmiao ;

Chaudhari, Narendra S. .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (08) :1267-1280

[3] A Flexible Terminal Approach to Sampled-Data Exponentially Synchronization of Markovian Neural Networks With Time-Varying Delayed Signals [J].

Cheng, Jun ;

Park, Ju H. ;

Karimi, Hamid Reza ;

Shen, Hao .

IEEE TRANSACTIONS ON CYBERNETICS, 2018, 48 (08) :2232-2244

[4]

Cui J., 2012, INT J INNOV COMPUT I, V13, P809

[5] Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition [J].

Dahl, George E. ;

Yu, Dong ;

Deng, Li ;

Acero, Alex .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (01) :30-42

[6] Mode-independent H∞ filters for Markovian jump linear systems [J].

de Souza, Carlos E. ;

Trofino, Alexandre ;

Barbosa, Karina A. .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2006, 51 (11) :1837-1841

[7] Stabilization of linear systems with limited information [J].

Elia, N ;

Mitter, SK .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (09) :1384-1400

[8] α-Dissipativity analysis of singular time-delay systems [J].

Feng, Zhiguang ;

Lam, James ;

Gao, Huijun .

AUTOMATICA, 2011, 47 (11) :2548-2552

[9] The sector bound approach to quantized feedback control [J].

Fu, MY ;

Xie, LH .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2005, 50 (11) :1698-1711

[10] Quantization [J].

Gray, RM ;

Neuhoff, DL .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1998, 44 (06) :2325-2383

← 1 2 3 4 5 →