Advanced Search

Show simple item record

dc.contributor.authorBal, Mustafa
dc.contributor.authorMarey, Ahmed
dc.contributor.authorAtes, Hasan F.
dc.contributor.authorBaykas, Tuncer
dc.contributor.authorGunturk, Bahadir K.
dc.date.accessioned2023-10-19T15:11:55Z
dc.date.available2023-10-19T15:11:55Z
dc.date.issued2022
dc.identifier.issn1536-1225
dc.identifier.issn1548-5757
dc.identifier.urihttps://doi.org/10.1109/LAWP.2022.3174357
dc.identifier.urihttps://hdl.handle.net/20.500.12469/5274
dc.description.abstractPath loss exponent and shadowing factor are among important wireless channel parameters. These parameters can be estimated using field measurements or ray-tracing simulations, which are costly and time-consuming. In this letter, we take a deep neural network-based approach, which takes either satellite image or height map of a target region as input, and estimates the desired channel parameters. We use the well-known VGG-16 architecture, pretrained on the ImageNet dataset, as the backbone to extract image features, modify it as a regression network to produce channel parameters, and retrain it on our dataset, which consists of satellite image or height map as input and channel parameters as target values. We demonstrate that deep networks can be successfully utilized in estimating path loss exponent and shadowing factor of a region, simply from the region's satellite image or height map. The trained models and test codes are publicly available on a Github page.en_US
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [215E324]en_US
dc.description.sponsorshipThis work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Grant 215E324.en_US
dc.language.isoengen_US
dc.publisherIEEE-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Antennas and Wireless Propagation Lettersen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectFixed Wireless AccessEn_Us
dc.subjectImagesEn_Us
dc.subjectModelsEn_Us
dc.subjectSatellitesen_US
dc.subjectShadow mappingen_US
dc.subjectTrainingen_US
dc.subjectSolid modelingen_US
dc.subjectDeep learningen_US
dc.subjectWireless communicationen_US
dc.subjectReceiversen_US
dc.subjectDeep learningen_US
dc.subjectheight mapen_US
dc.subjectregressionen_US
dc.subjectwireless channel parameter estimationen_US
dc.titleRegression of Large-Scale Path Loss Parameters Using Deep Neural Networksen_US
dc.typearticleen_US
dc.identifier.startpage1562en_US
dc.identifier.endpage1566en_US
dc.authoridGunturk, Bahadir/0000-0003-0779-9620
dc.authoridAtes, Hasan/0000-0002-6842-1528
dc.authoridMarey, Ahmed/0000-0002-4566-4551
dc.authoridBAL, MUSTAFA/0000-0002-0151-0067
dc.identifier.issue8en_US
dc.identifier.volume21en_US
dc.departmentN/Aen_US
dc.identifier.wosWOS:000835774100014en_US
dc.identifier.doi10.1109/LAWP.2022.3174357en_US
dc.identifier.scopus2-s2.0-85132524371en_US
dc.institutionauthorN/A
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.authorwosidGunturk, Bahadir/G-1609-2019
dc.authorwosidAtes, Hasan/M-5160-2013
dc.khas20231019-WoSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record