A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications

A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications

<p/> <p>The paper proposes a maximum likelihood sequence estimator (MLSE) receiver for satellite communications. The satellite channel model is composed of a nonlinear traveling wave tube (TWT) amplifier followed by a multipath propagation channel. The receiver is composed of a neural ne...

Full description

Bibliographic Details
Main Authors: Ibnkahla Mohamed, Yuan Jun
Format: Article
Language:English
Published: SpringerOpen 2004-01-01
Series:EURASIP Journal on Advances in Signal Processing
Subjects:
neural networks
satellite communications
high-power amplifiers
Online Access:http://dx.doi.org/10.1155/S1110865704405010
id doaj-3979d757d1484b9195946bcf0763b46a
record_format Article
spelling doaj-3979d757d1484b9195946bcf0763b46a2020-11-25T01:05:28ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802004-01-01200416394715A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite CommunicationsIbnkahla MohamedYuan Jun<p/> <p>The paper proposes a maximum likelihood sequence estimator (MLSE) receiver for satellite communications. The satellite channel model is composed of a nonlinear traveling wave tube (TWT) amplifier followed by a multipath propagation channel. The receiver is composed of a neural network channel estimator (NNCE) and a Viterbi detector. The natural gradient (NG) descent is used for training. Computer simulations show that the performance of our receiver is close to the ideal MLSE receiver in which the channel is perfectly known.</p>http://dx.doi.org/10.1155/S1110865704405010neural networkssatellite communicationshigh-power amplifiers
collection DOAJ
language English
format Article
sources DOAJ
author Ibnkahla Mohamed
Yuan Jun
spellingShingle Ibnkahla Mohamed
Yuan Jun
A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
EURASIP Journal on Advances in Signal Processing
neural networks
satellite communications
high-power amplifiers
author_facet Ibnkahla Mohamed
Yuan Jun
author_sort Ibnkahla Mohamed
title A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
title_short A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
title_full A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
title_fullStr A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
title_full_unstemmed A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications
title_sort neural network mlse receiver based on natural gradient descent: application to satellite communications
publisher SpringerOpen
series EURASIP Journal on Advances in Signal Processing
issn 1687-6172
1687-6180
publishDate 2004-01-01
description <p/> <p>The paper proposes a maximum likelihood sequence estimator (MLSE) receiver for satellite communications. The satellite channel model is composed of a nonlinear traveling wave tube (TWT) amplifier followed by a multipath propagation channel. The receiver is composed of a neural network channel estimator (NNCE) and a Viterbi detector. The natural gradient (NG) descent is used for training. Computer simulations show that the performance of our receiver is close to the ideal MLSE receiver in which the channel is perfectly known.</p>
topic neural networks
satellite communications
high-power amplifiers
url http://dx.doi.org/10.1155/S1110865704405010
work_keys_str_mv AT ibnkahlamohamed aneuralnetworkmlsereceiverbasedonnaturalgradientdescentapplicationtosatellitecommunications
AT yuanjun aneuralnetworkmlsereceiverbasedonnaturalgradientdescentapplicationtosatellitecommunications
AT ibnkahlamohamed neuralnetworkmlsereceiverbasedonnaturalgradientdescentapplicationtosatellitecommunications
AT yuanjun neuralnetworkmlsereceiverbasedonnaturalgradientdescentapplicationtosatellitecommunications
_version_ 1725194471148093440

Similar Items