Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/3903
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSeyfioğlu, Mehmet Saygın-
dc.contributor.authorErol, Barış-
dc.contributor.authorGürbüz, Sevgi Zübeyde-
dc.contributor.authorAmin, Moeness G.-
dc.date.accessioned2020-10-22T16:46:32Z-
dc.date.available2020-10-22T16:46:32Z-
dc.date.issued2019-12
dc.identifier.citationSeyfioglu, M. S., Erol, B., Gurbuz, S. Z., and Amin, M. G. (2018). DNN transfer learning from diversified micro-Doppler for motion classification. IEEE Transactions on Aerospace and Electronic Systems, 55(5), 2164-2180.en_US
dc.identifier.issn1557-9603
dc.identifier.issn0018-9251
dc.identifier.urihttps://hdl.handle.net/20.500.11851/3903-
dc.identifier.urihttps://ieeexplore.ieee.org/document/8572732-
dc.description.abstractRecently, deep neural networks (DNNs) have been the subject of intense research for the classification of radio frequency signals, such as synthetic aperture radar imagery or micro-Doppler signatures. However, a fundamental challenge is the typically small amount of data available due to the high costs and resources required for measurements. Small datasets limit the depth of DNNs implementable, and limit performance. In this work, a novel method for generating diversified radar micro-Doppler signatures using Kinect-based motion capture simulations is proposed as a training database for transfer learning with DNNs. In particular, it is shown that together with residual learning, the proposed DivNet approach allows for the construction of DNNs and offers improved performance in comparison to transfer learning from optical imagery. Furthermore, it is shown that initializing the network using diversified synthetic micro-Doppler signatures enables not only robust performance for previously unseen target profiles, but also class generalization. Results are presented for 7-class and 11-class human activity recognition scenarios using a 4-GHz continuous wave software-defined radar.en_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Transactions on Aerospace and Electronic Systemsen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectSynthetic aperture radaren_US
dc.subjectTrainingen_US
dc.subjectMathematical modelen_US
dc.subjectRadar imagingen_US
dc.subjectRadar cross-sectionsen_US
dc.subjectConvolutional neural networks (CNNs)en_US
dc.subjectdeep neural networks (DNNs)en_US
dc.subjectmicro-Doppler simulationen_US
dc.subjectradar classificationen_US
dc.subjectresidual learningen_US
dc.subjecttransfer learningen_US
dc.titleDNN Transfer Learning From Diversified Micro-Doppler for Motion Classificationen_US
dc.typeArticleen_US
dc.departmentFaculties, Faculty of Engineering, Department of Electrical and Electronics Engineeringen_US
dc.departmentFakülteler, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümütr_TR
dc.identifier.volume55
dc.identifier.issue5
dc.identifier.startpage2164
dc.identifier.endpage2180
dc.authorid0000-0002-2961-4976-
dc.identifier.wosWOS:000495013100006en_US
dc.identifier.scopus2-s2.0-85058643357en_US
dc.institutionauthorSeyfioğlu, Mehmet Saygın-
dc.identifier.doi10.1109/TAES.2018.2883847-
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.scopusqualityQ1-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.openairetypeArticle-
item.cerifentitytypePublications-
item.languageiso639-1en-
Appears in Collections:Elektrik ve Elektronik Mühendisliği Bölümü / Department of Electrical & Electronics Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

23
checked on Mar 23, 2024

WEB OF SCIENCETM
Citations

72
checked on Mar 23, 2024

Page view(s)

100
checked on Mar 25, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.