Publication:
Practical implementation of RIS-Aided spectrum sensing: a deep-learning-based solution

dc.contributor.coauthorHokelek, I (Hokelek, Ibrahim)
dc.contributor.coauthorGorcin, A (Gorcin, Ali)
dc.contributor.departmentDepartment of Electrical and Electronics Engineering
dc.contributor.departmentCoreLab (Communications Research and Innovation Laboratory)
dc.contributor.kuauthorBaşar, Ertuğrul
dc.contributor.kuauthorYıldırım, İbrahim
dc.contributor.kuauthorKayraklık, Sefa
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.contributor.schoolcollegeinstituteLaboratory
dc.date.accessioned2025-03-06T21:01:39Z
dc.date.issued2024
dc.description.abstractThis article presents reconfigurable intelligent surface (RIS)-aided deep learning (DL)-based spectrum sensing for next-generation cognitive radios (CRs). To that end, the secondary user (SU) monitors the primary transmitter (PT) signal, where the RIS plays a pivotal role in increasing the strength of the PT signal at the SU. The spectrograms of the synthesized dataset, including the fourth-generation long-term evolution and fifth-generation new radio signals, are mapped to images utilized for training the state-of-the-art object detection approaches, namely, Detectron2 and YOLOv7. By conducting extensive experiments using a real RIS prototype, we demonstrate that the RIS can consistently and significantly improve the performance of the DL detectors to identify the PT signal type along with its time and frequency utilization. This study also paves the way for optimizing spectrum utilization through RIS-assisted CR application in next-generation wireless communication systems.
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.identifier.doi10.1109/JSYST.2024.3376986
dc.identifier.eissn1937-9234
dc.identifier.issn1932-8184
dc.identifier.issue2
dc.identifier.quartileQ1
dc.identifier.scopus2-s2.0-85189331385
dc.identifier.urihttps://doi.org/10.1109/JSYST.2024.3376986
dc.identifier.urihttps://hdl.handle.net/20.500.14288/28019
dc.identifier.volume18
dc.identifier.wos1193669300001
dc.keywordsSensors Spectrogram
dc.keywordsTraining Detectors
dc.keywordsSignal processing
dc.keywordsVectors
dc.keywordsTask analysis
dc.keywordsDetectron2
dc.keywordsReconfigurable intelligent surface (RIS)
dc.keywordsSmart radio environment
dc.keywordsSpectrum sensing
dc.keywordsYOLOv7
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofIEEE Systems Journal
dc.subjectComputer Science
dc.subjectTelecommunications
dc.titlePractical implementation of RIS-Aided spectrum sensing: a deep-learning-based solution
dc.typeJournal Article
dspace.entity.typePublication
local.publication.orgunit1College of Engineering
local.publication.orgunit1Laboratory
local.publication.orgunit2Department of Electrical and Electronics Engineering
local.publication.orgunit2CoreLab (Communications Research and Innovation Laboratory)
relation.isOrgUnitOfPublication21598063-a7c5-420d-91ba-0cc9b2db0ea0
relation.isOrgUnitOfPublication65c7c6b7-d90c-4bb1-a1cb-054f13135330
relation.isOrgUnitOfPublication.latestForDiscovery21598063-a7c5-420d-91ba-0cc9b2db0ea0
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication20385dee-35e7-484b-8da6-ddcc08271d96
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files