Persistent Link:
http://hdl.handle.net/10150/606193
Title:
MIMO Channel Prediction Using Recurrent Neural Networks
Author:
Potter, Chris; Kosbar, Kurt; Panagos, Adam
Affiliation:
Missouri University of Science and Technology; Dynetics, Inc.
Issue Date:
2008-10
Rights:
Copyright © held by the author; distribution rights International Foundation for Telemetering
Collection Information:
Proceedings from the International Telemetering Conference are made available by the International Foundation for Telemetering and the University of Arizona Libraries. Visit http://www.telemetry.org/index.php/contact-us if you have questions about items in this collection.
Publisher:
International Foundation for Telemetering
Journal:
International Telemetering Conference Proceedings
Abstract:
Adaptive modulation is a communication technique capable of maximizing throughput while guaranteeing a fixed symbol error rate (SER). However, this technique requires instantaneous channel state information at the transmitter. This can be obtained by predicting channel states at the receiver and feeding them back to the transmitter. Existing algorithms used to predict single-input single-output (SISO) channels with recurrent neural networks (RNN) are extended to multiple-input multiple-output (MIMO) channels for use with adaptive modulation and their performance is demonstrated in several examples.
Keywords:
Multiple-input multiple-output (MIMO); Channel prediction; Recurrent neural networks; Online training; Adaptive modulation; Flat fading
Sponsors:
International Foundation for Telemetering
ISSN:
0884-5123; 0074-9079
Additional Links:
http://www.telemetry.org/

Full metadata record

DC FieldValue Language
dc.language.isoen_USen
dc.titleMIMO Channel Prediction Using Recurrent Neural Networksen_US
dc.contributor.authorPotter, Chrisen
dc.contributor.authorKosbar, Kurten
dc.contributor.authorPanagos, Adamen
dc.contributor.departmentMissouri University of Science and Technologyen
dc.contributor.departmentDynetics, Inc.en
dc.date.issued2008-10en
dc.rightsCopyright © held by the author; distribution rights International Foundation for Telemeteringen
dc.description.collectioninformationProceedings from the International Telemetering Conference are made available by the International Foundation for Telemetering and the University of Arizona Libraries. Visit http://www.telemetry.org/index.php/contact-us if you have questions about items in this collection.en
dc.publisherInternational Foundation for Telemeteringen
dc.description.abstractAdaptive modulation is a communication technique capable of maximizing throughput while guaranteeing a fixed symbol error rate (SER). However, this technique requires instantaneous channel state information at the transmitter. This can be obtained by predicting channel states at the receiver and feeding them back to the transmitter. Existing algorithms used to predict single-input single-output (SISO) channels with recurrent neural networks (RNN) are extended to multiple-input multiple-output (MIMO) channels for use with adaptive modulation and their performance is demonstrated in several examples.en
dc.subjectMultiple-input multiple-output (MIMO)en
dc.subjectChannel predictionen
dc.subjectRecurrent neural networksen
dc.subjectOnline trainingen
dc.subjectAdaptive modulationen
dc.subjectFlat fadingen
dc.description.sponsorshipInternational Foundation for Telemeteringen
dc.identifier.issn0884-5123en
dc.identifier.issn0074-9079en
dc.identifier.urihttp://hdl.handle.net/10150/606193en
dc.identifier.journalInternational Telemetering Conference Proceedingsen
dc.typetexten
dc.typeProceedingsen
dc.relation.urlhttp://www.telemetry.org/en
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.