Please use this identifier to cite or link to this item: http://www.repositorio.ufc.br/handle/riufc/4249
Title in Portuguese: Égalisation par prédiction Basée sur des réseaux de neurones et des fonctions objectifs obtenues à partir de la divergence de kullback-leibler et du constant modulus
Author: Cavalcante, Charles Casimiro
Mota, João César Moura
Montalvão Filho, Jugurta Rosa
Dorizzi, Bernadette
Keywords: Teleinformática
Redes neurais (Computação)
Issue Date: 2001
Publisher: Colloque GRETSI sur le traitement du signal et des images
Citation: CAVALCANTE, C. C. et al. Égalisation par prédiction Basée sur des réseaux de neurones et des fonctions objectifs obtenues à partir de la divergence de kullback-leibler et du constant modulus. In: COLLOQUE GRETSI SUR LE TRAITEMENT DU SIGNAL ET DES IMAGES, 2001, Toulouse. Anais... Toulouse: Colloque GRETSI sur le traitement du signal et des images, 2001. p. 573-576.
Abstract: A nonlinear structure of filtering for blind equalization is presented. The neural network-based structure is used in order to provide nonlinearity on the filter structure while the learning strategy is divided in two stages. The Kullback-Leibler divergence is used as the base for the cost function of a self-organized rule and constant modulus criterion for the supervised one. Simulation results illustrate the performance of the strategy compared to classical ones for adaptive equalization. The results show that the proposed strategy outperforms even trained DFE for some cases of channels.
URI: http://www.repositorio.ufc.br/handle/riufc/4249
Appears in Collections:DETE - Trabalhos apresentados em eventos

Files in This Item:
File Description SizeFormat 
2001_eve_cccavalcante.pdf250,13 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.