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
Récemment, les réseaux de neurones (NN) ont été largement appliqués à de nombreux problèmes de traitement du signal en raison de leur capacité robuste à former des régions de décision complexes. En particulier, les réseaux de neurones ajoutent de la flexibilité à la conception d'égaliseurs pour les systèmes de communication numérique. Le réseau neuronal récurrent (RNN) est une sorte de réseau neuronal avec une ou plusieurs boucles de rétroaction, tandis que la carte auto-organisée (SOM) se caractérise par la formation d'une carte topographique des modèles d'entrée dans lesquels les emplacements spatiaux (c'est-à-dire les coordonnées) des neurones dans le réseau sont révélateurs de caractéristiques statistiques intrinsèques contenues dans les modèles d'entrée. Dans cet article, nous proposons une nouvelle structure de récepteur combinant un égaliseur RNN adaptatif avec un détecteur SOM sous ISI grave et distorsion non linéaire dans le système QAM. Selon les résultats de l'analyse théorique et de la simulation informatique, les performances du schéma proposé se révèlent très efficaces dans l'égalisation des canaux sous distorsion non linéaire.
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.
Copier
Xiaoqiu WANG, Hua LIN, Jianming LU, Takashi YAHAGI, "Combining Recurrent Neural Networks with Self-Organizing Map for Channel Equalization" in IEICE TRANSACTIONS on Communications,
vol. E85-B, no. 10, pp. 2227-2235, October 2002, doi: .
Abstract: Recently, neural networks (NNs) have been extensively applied to many signal processing problem due to their robust abilities to form complex decision regions. In particular, neural networks add flexibility to the design of equalizers for digital communication systems. Recurrent neural network (RNN) is a kind of neural network with one or more feedback loops, whereas self-organizing map (SOM) is characterized by the formation of a topographic map of the input patterns in which the spatial locations (i.e., coordinates) of the neurons in the lattice are indicative of intrinsic statistical features contained in the input patterns. In this paper, we propose a novel receiver structure by combining adaptive RNN equalizer with a SOM detector under serious ISI and nonlinear distortion in QAM system. According to the theoretical analysis and computer simulation results, the performance of the proposed scheme is shown to be quite effective in channel equalization under nonlinear distortion.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e85-b_10_2227/_p
Copier
@ARTICLE{e85-b_10_2227,
author={Xiaoqiu WANG, Hua LIN, Jianming LU, Takashi YAHAGI, },
journal={IEICE TRANSACTIONS on Communications},
title={Combining Recurrent Neural Networks with Self-Organizing Map for Channel Equalization},
year={2002},
volume={E85-B},
number={10},
pages={2227-2235},
abstract={Recently, neural networks (NNs) have been extensively applied to many signal processing problem due to their robust abilities to form complex decision regions. In particular, neural networks add flexibility to the design of equalizers for digital communication systems. Recurrent neural network (RNN) is a kind of neural network with one or more feedback loops, whereas self-organizing map (SOM) is characterized by the formation of a topographic map of the input patterns in which the spatial locations (i.e., coordinates) of the neurons in the lattice are indicative of intrinsic statistical features contained in the input patterns. In this paper, we propose a novel receiver structure by combining adaptive RNN equalizer with a SOM detector under serious ISI and nonlinear distortion in QAM system. According to the theoretical analysis and computer simulation results, the performance of the proposed scheme is shown to be quite effective in channel equalization under nonlinear distortion.},
keywords={},
doi={},
ISSN={},
month={October},}
Copier
TY - JOUR
TI - Combining Recurrent Neural Networks with Self-Organizing Map for Channel Equalization
T2 - IEICE TRANSACTIONS on Communications
SP - 2227
EP - 2235
AU - Xiaoqiu WANG
AU - Hua LIN
AU - Jianming LU
AU - Takashi YAHAGI
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E85-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2002
AB - Recently, neural networks (NNs) have been extensively applied to many signal processing problem due to their robust abilities to form complex decision regions. In particular, neural networks add flexibility to the design of equalizers for digital communication systems. Recurrent neural network (RNN) is a kind of neural network with one or more feedback loops, whereas self-organizing map (SOM) is characterized by the formation of a topographic map of the input patterns in which the spatial locations (i.e., coordinates) of the neurons in the lattice are indicative of intrinsic statistical features contained in the input patterns. In this paper, we propose a novel receiver structure by combining adaptive RNN equalizer with a SOM detector under serious ISI and nonlinear distortion in QAM system. According to the theoretical analysis and computer simulation results, the performance of the proposed scheme is shown to be quite effective in channel equalization under nonlinear distortion.
ER -