Mean Square Stabilization of Neural Networks with Weighted Try once Discard Protocol and State Observer

Qi, L; Shi, K; Yang, C; Wen, S

Mean Square Stabilization of Neural Networks with Weighted Try once Discard Protocol and State Observer

Qi, L Shi, K Yang, C Wen, S

Permalink

Publisher:: Springer
Publication Type:: Journal Article
Citation:: Neural Processing Letters, 2021, 53, (1), pp. 829-842
Issue Date:: 2021-02-01

Closed Access

	Filename	Description	Size
	Qi2021_Article_MeanSquareStabilizationOfNeura.pdf		529.1 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Qi, L
dc.contributor.author	Shi, K
dc.contributor.author	Yang, C
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.date.accessioned	2022-03-18T05:03:59Z
dc.date.available	2022-03-18T05:03:59Z
dc.date.issued	2021-02-01
dc.identifier.citation	Neural Processing Letters, 2021, 53, (1), pp. 829-842
dc.identifier.issn	1370-4621
dc.identifier.issn	1573-773X
dc.identifier.uri	http://hdl.handle.net/10453/155345
dc.description.abstract	This paper investigates mean square stabilization problem of neural networks with weighted try once discard protocol and state observer. In general, sensor nodes access conflict happens frequently in the communication transmission networks. Aiming at this problem, we have adopted weighted try once discard protocol (WTOD) to reduce the occurrence of the conflict, The strategy is applied to discontinuous time systems, and only one node can obtain the access token to update signal transmission for the network. In addition, data transmission in the channel is large -scale and packet loss often occurs. Therefore, we adopt the method of quantized signal to reduce the pressure of channel transmission and ensure the stability of network transmission. As the system state is difficult to obtain, this paper design an observer to estimate the system state, the purpose of this paper is to guarantee the system to achieve the mean square stabilization with bounded output via the action of observer of signal output and controller, then solve the optimization problem of inequality through group of reasonable parameters of the controller and the observer. Finally, an example is given to prove the effectiveness of the proposed controller and observer.
dc.language	en
dc.publisher	Springer
dc.relation	National Natural Science Foundation of China61673187
dc.relation.ispartof	Neural Processing Letters
dc.relation.isbasedon	10.1007/s11063-020-10409-2
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 1702 Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Mean Square Stabilization of Neural Networks with Weighted Try once Discard Protocol and State Observer
dc.type	Journal Article
utslib.citation.volume	53
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	1702 Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-03-18T05:03:58Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	53
utslib.citation.issue	1

Abstract:

This paper investigates mean square stabilization problem of neural networks with weighted try once discard protocol and state observer. In general, sensor nodes access conflict happens frequently in the communication transmission networks. Aiming at this problem, we have adopted weighted try once discard protocol (WTOD) to reduce the occurrence of the conflict, The strategy is applied to discontinuous time systems, and only one node can obtain the access token to update signal transmission for the network. In addition, data transmission in the channel is large -scale and packet loss often occurs. Therefore, we adopt the method of quantized signal to reduce the pressure of channel transmission and ensure the stability of network transmission. As the system state is difficult to obtain, this paper design an observer to estimate the system state, the purpose of this paper is to guarantee the system to achieve the mean square stabilization with bounded output via the action of observer of signal output and controller, then solve the optimization problem of inequality through group of reasonable parameters of the controller and the observer. Finally, an example is given to prove the effectiveness of the proposed controller and observer.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/155345