Comparing deep learning architectures on gamma-spectroscopy analysis for nuclear waste characterization

Página do item simplificado
dc.contributor.authorOTERO, A.G.L.pt_BR
dc.contributor.authorPOTIENS JUNIOR, A.J.pt_BR
dc.contributor.authorMARUMO, J.T.pt_BR
dc.coverageNacionalpt_BR
dc.date.accessioned2021-08-02T16:42:56Z
dc.date.available2021-08-02T16:42:56Z
dc.date.issued2021pt_BR
dc.description.abstractNeural networks, particularly deep neural networks, are used nowadays with great success in several tasks, such as image classification, image segmentation, translation, text to speech, speech to text, achieving super-human performance. In this study, the capabilities of deep learning are explored on a new field: gamma-spectroscopy analysis, comparing the classification performance of different deep neural network architectures. The following architectures where tested: VGG-16, VGG-19, Xception, ResNet, InceptionV3, and MobileNet, which are available through the Keras Deep Learning framework to identify several different radionuclides (Am-241, Ba133, Cd-109, Co-60, Cs-137, Eu-152, Mn-54, Na-24, and Pb-210). Using an HPGe detector to acquire several gamma spectra from different sealed sources to create a dataset used for the training and validation of the neural network's comparison. This study demonstrates the strengths and weaknesses of applying deep learning on gamma-spectroscopy analysis for nuclear waste characterization.pt_BR
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsorshipIDCAPES: 001pt_BR
dc.format.extent1-8pt_BR
dc.identifier.citationOTERO, A.G.L.; POTIENS JUNIOR, A.J.; MARUMO, J.T. Comparing deep learning architectures on gamma-spectroscopy analysis for nuclear waste characterization. <b>Brazilian Journal of Radiation Sciences</b>, v. 9, n. 1A, p. 1-8, 2021. DOI: <a href="https://dx.doi.org/10.15392/bjrs.v9i1A.1257">10.15392/bjrs.v9i1A.1257</a>. Disponível em: http://repositorio.ipen.br/handle/123456789/32082.
dc.identifier.doi10.15392/bjrs.v9i1A.1257pt_BR
dc.identifier.fasciculo1Apt_BR
dc.identifier.issn2319-0612pt_BR
dc.identifier.orcid0000-0003-3010-9691pt_BR
dc.identifier.orcid0000-0002-4098-0272pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0003-3010-9691
dc.identifier.percentilfiSem Percentilpt_BR
dc.identifier.urihttp://repositorio.ipen.br/handle/123456789/32082
dc.identifier.vol9pt_BR
dc.relation.ispartofBrazilian Journal of Radiation Sciencespt_BR
dc.rightsopenAccesspt_BR
dc.sourceMeeting on Nuclear Applications (ENAN), 14th, October 21-25, 2019, Santos, SPpt_BR
dc.subjectartificial intelligence
dc.subjectcomputer architecture
dc.subjectgamma spectroscopy
dc.subjecthigh-purity ge detectors
dc.subjectneural networks
dc.subjectradioactive waste management
dc.subjectradioactive wastes
dc.subjectradioisotopes
dc.subjectsealed sources
dc.titleComparing deep learning architectures on gamma-spectroscopy analysis for nuclear waste characterizationpt_BR
dc.typeArtigo de periódicopt_BR
dspace.entity.typePublication
ipen.autorJULIO TAKEHIRO MARUMO
ipen.autorADEMAR JOSE POTIENS JUNIOR
ipen.autorANDRE GOMES LAMAS OTERO
ipen.codigoautor826
ipen.codigoautor734
ipen.codigoautor14881
ipen.contributor.ipenauthorJULIO TAKEHIRO MARUMO
ipen.contributor.ipenauthorADEMAR JOSE POTIENS JUNIOR
ipen.contributor.ipenauthorANDRE GOMES LAMAS OTERO
ipen.date.recebimento21-08
ipen.identifier.fiSem F.I.pt_BR
ipen.identifier.ipendoc27853pt_BR
ipen.type.genreArtigo
relation.isAuthorOfPublication4555167f-0f50-4308-be74-c5a0f15d5dda
relation.isAuthorOfPublication9426362d-f495-4433-9b46-c4ecc014a459
relation.isAuthorOfPublicationdf15944c-4ab4-4b10-a2e9-ff5e965f5e20
relation.isAuthorOfPublication.latestForDiscoverydf15944c-4ab4-4b10-a2e9-ff5e965f5e20
sigepi.autor.atividadeMARUMO, J.T.:826:1120:Npt_BR
sigepi.autor.atividadePOTIENS JUNIOR, A.J.:734:1120:Npt_BR
sigepi.autor.atividadeOTERO, A.G.L.:14881:1120:Spt_BR
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
27853.pdf
Tamanho:
951.9 KB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Licença do Pacote
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
license.txt
Tamanho:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Baixar
Coleções
Periódicos