Use este identificador para citar ou linkar para este item:
https://repositorio.ufba.br/handle/ri/6595
Registro completo de metadados
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Jongsoo, Choi | - |
dc.contributor.author | Lima, Antonio Cezar de Castro | - |
dc.contributor.author | Haykin, Simon | - |
dc.creator | Jongsoo, Choi | - |
dc.creator | Lima, Antonio Cezar de Castro | - |
dc.creator | Haykin, Simon | - |
dc.date.accessioned | 2012-08-15T19:34:55Z | - |
dc.date.issued | 2005-03 | - |
dc.identifier.issn | 0090-6778 | - |
dc.identifier.uri | http://www.repositorio.ufba.br/ri/handle/ri/6595 | - |
dc.description | Trabalho completo: acesso restrito, p. 472-480 | pt_BR |
dc.description.abstract | Recurrent 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. | pt_BR |
dc.language.iso | en | pt_BR |
dc.publisher | Institute of Electrical and Electronics Engineers | pt_BR |
dc.source | http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1413591 | pt_BR |
dc.subject | Channel equalization | pt_BR |
dc.subject | extended Kalman filter (EKF) | pt_BR |
dc.subject | recurrent neural network (RNN) | pt_BR |
dc.subject | time-varying channel | pt_BR |
dc.subject | unscented Kalman filter (UKF) | pt_BR |
dc.title | Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels | pt_BR |
dc.title.alternative | IEEE Transactions on Communications | pt_BR |
dc.type | Artigo de Periódico | pt_BR |
dc.identifier.number | v. 53, n. 3 | pt_BR |
dc.embargo.liftdate | 10000-01-01 | - |
Aparece nas coleções: | Artigo Publicado em Periódico (PPGEE) |
Arquivos associados a este item:
Arquivo | Descrição | Tamanho | Formato | |
---|---|---|---|---|
(160).pdf Restricted Access | 564,16 kB | Adobe PDF | Visualizar/Abrir Solicitar uma cópia |
Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.