Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/109077
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Neural network-based passive filtering for delayed neutral-type semi-Markovian jump systems |
Author: | Shi, P. Li, F. Wu, L. Lim, C. |
Citation: | IEEE Transactions on Neural Networks and Learning Systems, 2017; 28(9):2101-2114 |
Publisher: | IEEE |
Issue Date: | 2017 |
ISSN: | 2162-237X 2162-2388 |
Statement of Responsibility: | Peng Shi, Fanbiao Li, Ligang Wu and Cheng-Chew Lim |
Abstract: | This paper investigates the problem of exponential passive filtering for a class of stochastic neutral-type neural networks with both semi-Markovian jump parameters and mixed time delays. Our aim is to estimate the states by designing a Luenberger-type observer, such that the filter error dynamics are mean-square exponentially stable with an expected decay rate and an attenuation level. Sufficient conditions for the existence of passive filters are obtained, and a convex optimization algorithm for the filter design is given. In addition, a cone complementarity linearization procedure is employed to cast the nonconvex feasibility problem into a sequential minimization problem, which can be readily solved by the existing optimization techniques. Numerical examples are given to demonstrate the effectiveness of the proposed techniques. |
Keywords: | Filtering; neural networks (NNs); semi-Markovian jump systems (S-MJSs); time delay |
Rights: | © 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. |
DOI: | 10.1109/TNNLS.2016.2573853 |
Grant ID: | http://purl.org/au-research/grants/arc/DP140102180 http://purl.org/au-research/grants/arc/LP140100471 |
Published version: | http://dx.doi.org/10.1109/tnnls.2016.2573853 |
Appears in Collections: | Aurora harvest 8 Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.