Deep learning design for joint antenna selection and hybrid beamforming in massive MIMO

Basit Öğe Kaydı
dc.contributor.authorElbir, Ahmet Musab
dc.contributor.authorMishra, Kumar Vijay
dc.date.accessioned2020-04-30T13:32:16Z
dc.date.available2020-04-30T13:32:16Z
dc.date.issued2019
dc.departmentDÜ, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.descriptionIEEE Antennas and Propagation Society (APS); The Institute of Electrical and Electronics Engineers (IEEE)en_US
dc.description2019 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, APSURSI 2019 -- 7 July 2019 through 12 July 2019 -- 153911en_US
dc.description.abstractIn this paper, we propose a deep-learning-based for joint antenna selection and hybrid beamformer design problem in mmWave massive MIMO systems. In this respect, we treat both problems as a classification problem. We design two convolutional neural networks (CNNs) which accept the input as the channel matrix and it yields the output as the optimum antenna subarray. The selected part of channel matrix is fed to the second CNN which gives the output as the analog and baseband beamformers. We evaluate the performance of the proposed approach through numerical simulations and show that our CNN framework provides significantly better performance as compared to the conventional techniques such as orthogonal matching pursuit. © 2019 IEEE.en_US
dc.identifier.doi10.1109/APUSNCURSINRSM.2019.8888753en_US
dc.identifier.endpage1586en_US
dc.identifier.isbn9781728106922
dc.identifier.startpage1585en_US
dc.identifier.urihttps://dx.doi.org/10.1109/APUSNCURSINRSM.2019.8888753
dc.identifier.urihttps://hdl.handle.net/20.500.12684/203
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartof2019 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, APSURSI 2019 - Proceedingsen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.titleDeep learning design for joint antenna selection and hybrid beamforming in massive MIMOen_US
dc.typeConference Objecten_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
0203.pdf
Boyut:
360.09 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Bildiri Koleksiyonu