Por favor, use este identificador para citar o enlazar este ítem:
https://repositorio.ufba.br/handle/ri/6595
metadata.dc.type: | Artigo de Periódico |
Título : | Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels |
Otros títulos : | IEEE Transactions on Communications |
Autor : | Jongsoo, Choi Lima, Antonio Cezar de Castro Haykin, Simon |
metadata.dc.creator: | Jongsoo, Choi Lima, Antonio Cezar de Castro Haykin, Simon |
Resumen : | 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. |
Palabras clave : | Channel equalization extended Kalman filter (EKF) recurrent neural network (RNN) time-varying channel unscented Kalman filter (UKF) |
Editorial : | Institute of Electrical and Electronics Engineers |
URI : | http://www.repositorio.ufba.br/ri/handle/ri/6595 |
Fecha de publicación : | mar-2005 |
Aparece en las colecciones: | Artigo Publicado em Periódico (PPGEE) |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
(160).pdf Restricted Access | 564,16 kB | Adobe PDF | Visualizar/Abrir Request a copy |
Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.