Repository logo
 
Publication

An ubiquitous 2.6 GHz radio propagation model for wireless networks using self-supervised learning from satellite images

2022-07-25Journal article Open access
Simple item page
dc.contributor.authorSousa, Marco
dc.contributor.authorVieira, Pedro
dc.contributor.authorQueluz, Maria Paula
dc.contributor.authorRodrigues, António
dc.date.accessioned2023-05-11T09:52:15Z
dc.date.available2023-05-11T09:52:15Z
dc.date.issued2022-07-25
dc.description.abstractThe performance of any Mobile Wireless Network (MWN) is dependent on the appropriate level of radio coverage, with Path Loss (PL) models being a valuable resource for its evaluation. Recently, advancements in Machine Learning (ML) and Deep Neural Networks (DNNs) have been applied to radio propagation to produce new data-driven PL models. Notoriously, these advancements have also allowed the inclusion of non-classical inputs, such as satellite images. However, data-driven PL models are often developed under the assumption that training and test data distributions are similar, which is a weak assumption in real-world scenarios. Thus, generalization (i.e., the model’s ability to perform on different data distributions) is a crucial aspect of data-driven PL models in the context of Mobile Network Operators (MNOs). This paper proposes a new data-driven PL model, the Ubiquitous Satellite Aided Radio Propagation (USARP) model, developed to enhance the geographical generalization capabilities of empirical PL models, by using satellite images. The USARP model considers self-supervised learning to extract general data representations of the radio environment from satellite images, improving the PL prediction Root Mean Square Error (RMSE) of the 3rd Generation Partnership Project (3GPP) PL model in the order of 9 dB, and for a data distribution distinct from the training data. Moreover, it was demonstrated the potential of the USARP model in terms of geographical and radio environment generalization. Although the generalization capabilities of ML regression algorithms are limited, the chosen USARP architecture and the use of regularization techniques had a positive impact on its geographical generalization performance.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationSOUSA, Marco; [et al] – An ubiquitous 2.6 GHz radio propagation model for wireless networks using self-supervised learning from satellite images. IEEE Access. ISSN 2169-3536. Vol. 10 (2022), pp. 78597-78615.pt_PT
dc.identifier.doi10.1109/ACCESS.2022.3193486pt_PT
dc.identifier.issn2169-3536
dc.identifier.urihttp://hdl.handle.net/10400.21/16006
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherIEEEpt_PT
dc.relation.publisherversionhttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9837897pt_PT
dc.subjectWireless networkspt_PT
dc.subjectRadio propagationpt_PT
dc.subjectPath loss modelspt_PT
dc.subjectSatellite datapt_PT
dc.subjectDeep learningpt_PT
dc.subjectSelf-supervised learningpt_PT
dc.subjectConvolutional neural networkspt_PT
dc.titleAn ubiquitous 2.6 GHz radio propagation model for wireless networks using self-supervised learning from satellite imagespt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage78615pt_PT
oaire.citation.startPage78597pt_PT
oaire.citation.titleIEEE Accesspt_PT
oaire.citation.volume10pt_PT
person.familyNameSousa
person.familyNameVieira
person.familyNameQueluz
person.familyNameRodrigues
person.givenNameMarco
person.givenNamePedro
person.givenNameMaria Paula
person.givenNameAntónio
person.identifier.ciencia-idCB11-BB4E-3C79
person.identifier.ciencia-id071B-9A70-15B8
person.identifier.ciencia-idC210-DAC9-D03A
person.identifier.ciencia-idC810-67D6-FD83
person.identifier.orcid0000-0002-2471-170X
person.identifier.orcid0000-0003-0279-8741
person.identifier.orcid0000-0003-0266-4022
person.identifier.orcid0000-0003-2115-7245
person.identifier.ridB-5234-2016
person.identifier.scopus-author-id57202674941
person.identifier.scopus-author-id7004567421
person.identifier.scopus-author-id6602528040
person.identifier.scopus-author-id35495905500
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication22a6fbb3-76b6-4e5f-a8c9-207bdb2ada78
relation.isAuthorOfPublication51ae3527-d4ea-46f4-b6c9-62c7b77ac728
relation.isAuthorOfPublication59d5af5d-9c01-4147-a3a9-c1ea74ef3a4d
relation.isAuthorOfPublicationb3d3cc84-a511-485a-a329-9c444b1fa33d
relation.isAuthorOfPublication.latestForDiscovery59d5af5d-9c01-4147-a3a9-c1ea74ef3a4d

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
An ubiquitous_PVieira.pdf
Size:
3.68 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Artigos