State Estimation for Recurrent Neural Networks With Intermittent Transmission

被引：4

作者：

Liu, Chang ^{[1
]}

Rao, Hongxia ^{[1
]}

Yu, Xinxin ^{[1
]}

Xu, Yong ^{[1
]}

Su, Chun-Yi ^{[1
,2
]}

机构：

[1] Guangdong Univ Technol, Sch Automat, Guangdong Prov Key Lab Intelligent Decis & Cooper, Guangzhou 510006, Peoples R China

[2] Concordia Univ, Dept Mech Engn, Montreal, PQ H3G 1M8, Canada

来源：

IEEE TRANSACTIONS ON CYBERNETICS | 2024年 / 54卷 / 05期

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Recurrent neural networks; State estimation; Biological neural networks; Protocols; Estimation error; Neurons; Communication channels; Dissipative performance; intermittent transmission; recurrent neural networks; state estimation; COMPLEX NETWORKS; SYSTEMS; STABILITY;

D O I：

10.1109/TCYB.2023.3239368

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 work addresses the state estimation problem for recurrent neural networks over capacity-constrained communication channels. The intermittent transmission protocol is used to reduce the communication load, where a stochastic variable with a given distribution is used to describe the transmission interval. A corresponding transmission interval-dependent estimator is designed, and an estimation error system based on it is also derived, whose mean-square stability is proved by constructing an interval-dependent function. By analyzing the performance in each transmission interval, sufficient conditions of the mean-square stability and the strict (Q, S, R)-gamma-dissipativity are established for the estimation error system. Finally, the correctness and the superiority of the developed result are illustrated by a numerical example.

引用

页码：2891 / 2900

页数：10

共 50 条

[1] Exponential state estimation for recurrent neural networks with distributed delays
Li, Tao
Fei, Shu-Min
NEUROCOMPUTING, 2007, 71 (1-3) : 428 - 438
[2] COMPARISON OF FEEDFORWARD AND RECURRENT NEURAL NETWORKS FOR BIOPROCESS STATE ESTIMATION
KARIM, MN
RIVERA, SL
COMPUTERS & CHEMICAL ENGINEERING, 1992, 16 : S369 - S377
[3] Reduced-order state estimation of delayed recurrent neural networks
Huang, He
Huang, Tingwen
Chen, Xiaoping
NEURAL NETWORKS, 2018, 98 : 59 - 64
[4] Exponentially convergent state estimation for delayed switched recurrent neural networks
Ahn, Choon Ki
EUROPEAN PHYSICAL JOURNAL E, 2011, 34 (11):
[5] Comparative Study of State-of-Charge Estimation with Recurrent Neural Networks
Wassiliadis, Nikolaos
Herrmann, Thomas
Wildfeuer, Leo
Reiter, Christoph
Lienkamp, Markus
2019 IEEE TRANSPORTATION ELECTRIFICATION CONFERENCE AND EXPO (ITEC), 2019,
[6] Exponentially convergent state estimation for delayed switched recurrent neural networks
Choon Ki Ahn
The European Physical Journal E, 2011, 34
[7] State estimation for jumping recurrent neural networks with discrete and distributed delays
Wang, Zidong
Liu, Yurong
Liu, Xiaohui
NEURAL NETWORKS, 2009, 22 (01) : 41 - 48
[8] State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks
Chaoui, Hicham
Ibe-Ekeocha, Chinemerem Christopher
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2017, 66 (10) : 8773 - 8783
[9] Exponential state estimation for delayed recurrent neural networks with sampled-data
Li, Nan
Hu, Jiawen
Hu, Jiming
Li, Lin
NONLINEAR DYNAMICS, 2012, 69 (1-2) : 555 - 564
[10] State estimation for recurrent neural networks with unknown delays: A robust analysis approach
Wang, Zhanshan
Wang, Jidong
Wu, Yanming
NEUROCOMPUTING, 2017, 227 : 29 - 36

← 1 2 3 4 5 →