Approximate Reliability Function Based on Wavelet Latin Hypercube Sampling and Bee Recurrent Neural Network

Yeh, W; Hsieh, T; Chih, M; Liu, S; Ping, S

Approximate Reliability Function Based on Wavelet Latin Hypercube Sampling and Bee Recurrent Neural Network

Yeh, W Hsieh, T Chih, M Liu, S Ping, S

Permalink

Publisher:: IEEE Reliability Society
Publication Type:: Journal Article
Citation:: Yeh Wei-Chang et al. 2011, 'Approximate Reliability Function Based on Wavelet Latin Hypercube Sampling and Bee Recurrent Neural Network', IEEE Reliability Society, vol. 60, no. 2, pp. 404-414.
Issue Date:: 2011

Closed Access

	Filename	Description	Size
	2011004301OK.pdf		341.8 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	Yeh, W	en_US
dc.contributor.author	Hsieh, T	en_US
dc.contributor.author	Chih, M	en_US
dc.contributor.author	Liu, S	en_US
dc.contributor.author	Ping, S	en_US
dc.date.accessioned	2012-10-12T03:33:48Z
dc.date.available	2012-10-12T03:33:48Z
dc.date.issued	2011	en_US
dc.identifier	2011004301	en_US
dc.identifier.citation	Yeh Wei-Chang et al. 2011, 'Approximate Reliability Function Based on Wavelet Latin Hypercube Sampling and Bee Recurrent Neural Network', IEEE Reliability Society, vol. 60, no. 2, pp. 404-414.	en_US
dc.identifier.issn	0018-9529	en_US
dc.identifier.other	C1	en_US
dc.identifier.uri	http://hdl.handle.net/10453/18299
dc.description.abstract	This work combines a Bee Recurrent Neural Network (BRNN) optimized by the Artificial Bee Colony (ABC) algorithm with Monte Carlo Simulation (MCS) to generate a novel approximate model for predicting network reliability. We utilize the Wavelet Transform (WT)-based Latin Hypercube Sampling (LHS) (WLHS) to select input training data, and open the black box of neural networks by constructing a limited space reliability function from neural network parameters. Furthermore, the proposed method compares favorably with existing methods in literature based on experimental results for a benchmark example. The result reveals that the novel WLHS-MCS based on BRNN (WLHS-BRNN-MCS for short) is an excellent estimator of the reliability function.	en_US
dc.publisher	IEEE Reliability Society	en_US
dc.relation.ispartof	Verified OK	en_US
dc.relation.ispartof	IEEE Transactions on Reliability	en_US
dc.relation.isbasedon	http://dx.doi.org/10.1109/TR.2011.2134190	en_US
dc.rights	© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.subject	Artificial neural networks , Hypercubes , Recurrent neural networks , Telecommunication network reliability , Wavelet transforms	en_US
dc.subject.classification	Computer Software	en_US
dc.title	Approximate Reliability Function Based on Wavelet Latin Hypercube Sampling and Bee Recurrent Neural Network	en_US
dc.type	Journal article
utslib.citation.volume	60	en_US
utslib.citation.number	2	en_US
utslib.location	Piscataway, USA	en_US
utslib.citation.startpage	404	en_US
utslib.citation.endpage	414	en_US
utslib.identifier.org	FEIT.Faculty of Engineering & Information Technology	en_US
utslib.for	080300	en_US
utslib.percentage	000050	en_US
utslib.copyright.status	closed_access

Abstract:

This work combines a Bee Recurrent Neural Network (BRNN) optimized by the Artificial Bee Colony (ABC) algorithm with Monte Carlo Simulation (MCS) to generate a novel approximate model for predicting network reliability. We utilize the Wavelet Transform (WT)-based Latin Hypercube Sampling (LHS) (WLHS) to select input training data, and open the black box of neural networks by constructing a limited space reliability function from neural network parameters. Furthermore, the proposed method compares favorably with existing methods in literature based on experimental results for a benchmark example. The result reveals that the novel WLHS-MCS based on BRNN (WLHS-BRNN-MCS for short) is an excellent estimator of the reliability function.

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

http://hdl.handle.net/10453/18299