The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo discute a aplicação de uma rede neural fuzzy-ARTMAP para equalização de canais de comunicação digital. Esta abordagem fornece novas soluções para resolver problemas, como complexidade e longo treinamento, encontrados na implementação dos equalizadores de base neural desenvolvidos anteriormente. O equalizador fuzzy-ARTMAP proposto é rápido e fácil de treinar e inclui recursos não encontrados em outras abordagens de redes neurais; um pequeno número de parâmetros, sem requisitos para a escolha de pesos iniciais, aumento automático de unidades ocultas, sem risco de ficar preso em mínimos locais e a capacidade de adicionar novos dados sem treinar novamente os dados previamente treinados. Nos estudos de simulação, os sinais binários foram gerados aleatoriamente em um canal linear com ruído gaussiano. O desempenho do equalizador proposto é comparado com outros equalizadores de base de rede neural, especificamente equalizadores MLP e RBF.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Jungsik LEE, Yeonsung CHOI, Jaewan LEE, Soowhan HAN, "Channel Equalization Using Fuzzy-ARTMAP" in IEICE TRANSACTIONS on Communications,
vol. E85-B, no. 4, pp. 826-830, April 2002, doi: .
Abstract: This paper discusses the application of a fuzzy-ARTMAP neural network to digital communications channel equalization. This approach provides new solutions for solving the problems, such as complexity and long training, which found when implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches; a small number of parameters, no requirements for the choice of initial weights, automatic increase of hidden units, no risk of getting trapped in local minima, and the capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random in a linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, specifically MLP and RBF equalizers.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e85-b_4_826/_p
Copiar
@ARTICLE{e85-b_4_826,
author={Jungsik LEE, Yeonsung CHOI, Jaewan LEE, Soowhan HAN, },
journal={IEICE TRANSACTIONS on Communications},
title={Channel Equalization Using Fuzzy-ARTMAP},
year={2002},
volume={E85-B},
number={4},
pages={826-830},
abstract={This paper discusses the application of a fuzzy-ARTMAP neural network to digital communications channel equalization. This approach provides new solutions for solving the problems, such as complexity and long training, which found when implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches; a small number of parameters, no requirements for the choice of initial weights, automatic increase of hidden units, no risk of getting trapped in local minima, and the capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random in a linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, specifically MLP and RBF equalizers.},
keywords={},
doi={},
ISSN={},
month={April},}
Copiar
TY - JOUR
TI - Channel Equalization Using Fuzzy-ARTMAP
T2 - IEICE TRANSACTIONS on Communications
SP - 826
EP - 830
AU - Jungsik LEE
AU - Yeonsung CHOI
AU - Jaewan LEE
AU - Soowhan HAN
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E85-B
IS - 4
JA - IEICE TRANSACTIONS on Communications
Y1 - April 2002
AB - This paper discusses the application of a fuzzy-ARTMAP neural network to digital communications channel equalization. This approach provides new solutions for solving the problems, such as complexity and long training, which found when implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches; a small number of parameters, no requirements for the choice of initial weights, automatic increase of hidden units, no risk of getting trapped in local minima, and the capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random in a linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, specifically MLP and RBF equalizers.
ER -