Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels

Detalhes bibliográficos
Autor(a) principal: Jongsoo, Choi
Data de Publicação: 2005
Outros Autores: Lima, Antonio Cezar de Castro, Haykin, Simon
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFBA
Texto Completo: http://www.repositorio.ufba.br/ri/handle/ri/6595
Resumo: Trabalho completo: acesso restrito, p. 472-480
id UFBA-2_6849a2033c8072fe1eac47404fd5d726
oai_identifier_str oai:repositorio.ufba.br:ri/6595
network_acronym_str UFBA-2
network_name_str Repositório Institucional da UFBA
repository_id_str 1932
spelling Jongsoo, ChoiLima, Antonio Cezar de CastroHaykin, SimonJongsoo, ChoiLima, Antonio Cezar de CastroHaykin, Simon2012-08-15T19:34:55Z2005-030090-6778http://www.repositorio.ufba.br/ri/handle/ri/6595v. 53, n. 3Trabalho completo: acesso restrito, p. 472-480Recurrent neural networks (RNNs) have been successfully applied to communications channel equalization because of their modeling capability for nonlinear dynamic systems. Major problems of gradient-descent learning techniques commonly employed to train RNNs are slow convergence rates and long training sequences required for satisfactory performance. This paper presents decision-feedback equalizers using an RNN trained with Kalman filtering algorithms. The main features of the proposed recurrent neural equalizers, using the extended Kalman filter(EKF) and unscented Kalman filter (UKF), are fast convergence and good performance using relatively short training symbols. Experimental results for various time-varying channels are presented to evaluate the performance of the proposed approaches over a conventional recurrent neural equalizer.Submitted by Bruna Lessa (lessbruna@gmail.com) on 2012-08-15T19:34:55Z No. of bitstreams: 1 (160).pdf: 577702 bytes, checksum: d8eb0a291ec031f53114d7f5ce6a56e8 (MD5)Made available in DSpace on 2012-08-15T19:34:55Z (GMT). No. of bitstreams: 1 (160).pdf: 577702 bytes, checksum: d8eb0a291ec031f53114d7f5ce6a56e8 (MD5) Previous issue date: 2005-03Institute of Electrical and Electronics Engineershttp://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1413591reponame:Repositório Institucional da UFBAinstname:Universidade Federal da Bahia (UFBA)instacron:UFBAChannel equalizationextended Kalman filter (EKF)recurrent neural network (RNN)time-varying channelunscented Kalman filter (UKF)Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying ChannelsIEEE Transactions on Communicationsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article10000-01-01enginfo:eu-repo/semantics/openAccessLICENSElicense.txtlicense.txttext/plain1762https://repositorio.ufba.br/bitstream/ri/6595/2/license.txt1b89a9a0548218172d7c829f87a0eab9MD52ORIGINAL(160).pdf(160).pdfapplication/pdf577702https://repositorio.ufba.br/bitstream/ri/6595/1/%28160%29.pdfd8eb0a291ec031f53114d7f5ce6a56e8MD51TEXT(160).pdf.txt(160).pdf.txtExtracted texttext/plain37576https://repositorio.ufba.br/bitstream/ri/6595/3/%28160%29.pdf.txt905ffee84b1796834b6c34e6563ac6cbMD53ri/65952022-07-05 14:03:44.341oai:repositorio.ufba.br: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Repositório InstitucionalPUBhttp://192.188.11.11:8080/oai/requestopendoar:19322022-07-05T17:03:44Repositório Institucional da UFBA - Universidade Federal da Bahia (UFBA)false
dc.title.pt_BR.fl_str_mv Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
dc.title.alternative.pt_BR.fl_str_mv IEEE Transactions on Communications
title Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
spellingShingle Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
Jongsoo, Choi
Channel equalization
extended Kalman filter (EKF)
recurrent neural network (RNN)
time-varying channel
unscented Kalman filter (UKF)
title_short Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
title_full Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
title_fullStr Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
title_full_unstemmed Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
title_sort Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels
author Jongsoo, Choi
author_facet Jongsoo, Choi
Lima, Antonio Cezar de Castro
Haykin, Simon
author_role author
author2 Lima, Antonio Cezar de Castro
Haykin, Simon
author2_role author
author
dc.contributor.author.fl_str_mv Jongsoo, Choi
Lima, Antonio Cezar de Castro
Haykin, Simon
Jongsoo, Choi
Lima, Antonio Cezar de Castro
Haykin, Simon
dc.subject.por.fl_str_mv Channel equalization
extended Kalman filter (EKF)
recurrent neural network (RNN)
time-varying channel
unscented Kalman filter (UKF)
topic Channel equalization
extended Kalman filter (EKF)
recurrent neural network (RNN)
time-varying channel
unscented Kalman filter (UKF)
description Trabalho completo: acesso restrito, p. 472-480
publishDate 2005
dc.date.issued.fl_str_mv 2005-03
dc.date.accessioned.fl_str_mv 2012-08-15T19:34:55Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://www.repositorio.ufba.br/ri/handle/ri/6595
dc.identifier.issn.none.fl_str_mv 0090-6778
dc.identifier.number.pt_BR.fl_str_mv v. 53, n. 3
identifier_str_mv 0090-6778
v. 53, n. 3
url http://www.repositorio.ufba.br/ri/handle/ri/6595
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.pt_BR.fl_str_mv http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1413591
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFBA
instname:Universidade Federal da Bahia (UFBA)
instacron:UFBA
instname_str Universidade Federal da Bahia (UFBA)
instacron_str UFBA
institution UFBA
reponame_str Repositório Institucional da UFBA
collection Repositório Institucional da UFBA
bitstream.url.fl_str_mv https://repositorio.ufba.br/bitstream/ri/6595/2/license.txt
https://repositorio.ufba.br/bitstream/ri/6595/1/%28160%29.pdf
https://repositorio.ufba.br/bitstream/ri/6595/3/%28160%29.pdf.txt
bitstream.checksum.fl_str_mv 1b89a9a0548218172d7c829f87a0eab9
d8eb0a291ec031f53114d7f5ce6a56e8
905ffee84b1796834b6c34e6563ac6cb
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFBA - Universidade Federal da Bahia (UFBA)
repository.mail.fl_str_mv
_version_ 1808459405442678784