Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices

Simple item page
dc.contributor.authorUtrilla, Ramiroen
dc.contributor.authorFonseca, Erikaen
dc.contributor.authorAraujo, Alvaroen
dc.contributor.authorDaSilva, Luiz A.en
dc.date.accessioned2022-01-04T20:37:16Zen
dc.date.available2022-01-04T20:37:16Zen
dc.date.issued2020-01-01en
dc.date.updated2022-01-04T20:37:14Zen
dc.description.abstractThe continuous increase in the number of mobile and Internet of Things (IoT) devices, as well as in the wireless data traffic they generate, represents an essential challenge in terms of spectral coexistence. As a result, these devices are now expected to make efficient and dynamic use of the spectrum by employing Cognitive Radio (CR) techniques. In this work, we focus on the Automatic Modulation Classification (AMC). AMC is essential to carry out multiple CR techniques, such as dynamic spectrum access, link adaptation and interference detection, aimed at improving communications throughput and reliability and, in turn, spectral efficiency. In recent years, multiple Deep Learning (DL) techniques have been proposed to address the AMC problem. These DL techniques have demonstrated better generalization, scalability and robustness capabilities compared to previous solutions. However, most of these techniques require high processing and storage capabilities that limit their applicability to energy- and computation-constrained enddevices. In this work, we propose a new gated recurrent unit neural network solution for AMC that has been specifically designed for resource-constrained IoT devices. We trained and tested our solution with over-the-air measurements of real radio signals. Our results show that the proposed solution has a memory footprint of 73.5 kBytes, 51.74% less than the reference model, and achieves a classification accuracy of 92.4%en
dc.description.versionPublished versionen
dc.format.extentPages 112783-112794en
dc.format.extent12 page(s)en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1109/ACCESS.2020.3002770en
dc.identifier.eissn2169-3536en
dc.identifier.issn2169-3536en
dc.identifier.urihttp://hdl.handle.net/10919/107384en
dc.identifier.volume8en
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000546414500040&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=930d57c9ac61a043676db62af60056c1en
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectTechnologyen
dc.subjectComputer Science, Information Systemsen
dc.subjectEngineering, Electrical & Electronicen
dc.subjectTelecommunicationsen
dc.subjectComputer Scienceen
dc.subjectEngineeringen
dc.subjectModulationen
dc.subjectNeural networksen
dc.subjectTrainingen
dc.subjectWireless communicationen
dc.subjectTask analysisen
dc.subjectLogic gatesen
dc.subjectInternet of Thingsen
dc.subjectCognitive radioen
dc.subjectspectrum sensingen
dc.subjectdeep learningen
dc.subjectautomatic modulation classificationen
dc.subjectrecurrent neural networken
dc.subjectgated recurrent uniten
dc.subjectIoTen
dc.subjectend-deviceen
dc.subjectedge computingen
dc.subjectsoftware-defined radioen
dc.subject08 Information and Computing Sciencesen
dc.subject09 Engineeringen
dc.subject10 Technologyen
dc.titleGated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devicesen
dc.title.serialIEEE Accessen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
dc.type.otherJournalen
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/University Research Institutesen
pubs.organisational-group/Virginia Tech/All T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
utrilla_ieeeaccess2020.pdf
Size:
1.74 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

All Faculty Deposits
Scholarly Works, Electrical and Computer Engineering