Aviso de indisponibilidade temporária do RI

Informamos que o Repositório Institucional da UFMG está temporariamente indisponível devido à manutenção!

O acesso será restabelecido em breve.

Deep-learning-based denoising approach to enhance Raman spectroscopy in mass-produced graphene

Página do item simplificado
dc.creatorLucas Resende Pellegrinelli Machado
dc.creatorMariana de Oliveira Santos Silva
dc.creatorJoão Luiz Elias Campos
dc.creatorDiego Edison Lopez Silva
dc.creatorLuiz Gustavo de Oliveira Lopes Cançado
dc.creatorOmar Paranaiba Vilela Neto
dc.date.accessioned2025-04-15T15:03:16Z
dc.date.accessioned2025-09-09T00:31:43Z
dc.date.available2025-04-15T15:03:16Z
dc.date.issued2022
dc.description.sponsorshipCNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico
dc.description.sponsorshipFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais
dc.description.sponsorshipCAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
dc.description.sponsorshipOutra Agência
dc.identifier.doihttps://doi.org/10.1002/jrs.6317
dc.identifier.issn1097-4555
dc.identifier.urihttps://hdl.handle.net/1843/81607
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofThe journal of Raman spectroscopy
dc.rightsAcesso Restrito
dc.subjectAprendizado profundo
dc.subjectGrafeno
dc.subjectRedes neurais
dc.subjectEspectroscopia de Raman
dc.subject.otherDeep-learning
dc.subject.otherMass-produced graphene
dc.subject.otherNeural networks
dc.subject.otherSpectra denoising
dc.titleDeep-learning-based denoising approach to enhance Raman spectroscopy in mass-produced graphene
dc.typeArtigo de periódico
local.citation.epage871
local.citation.issue5
local.citation.spage863
local.citation.volume53
local.description.resumoThe inherently weak signal present in Raman spectroscopy makes spectral resolution susceptible to noise. Hence, efficient denoising techniques for post-processing of spectral data are required. We introduce two efficient approaches to remove noise from graphene Raman spectra, based on deep neural network architectures using supervised and unsupervised learning. We compared the performance of these approaches with three traditional noise removal methods. The experimental results demonstrate the effectiveness of deep-learning models in the denoising task, which is crucial in interpreting characterization data of mass-produced graphene. Overall, our supervised approach outperforms all considered baselines, as well as the unsupervised method, providing significant improvement in noise reduction.
local.identifier.orcidhttps://orcid.org/0000-0002-1630-8005
local.identifier.orcidhttps://orcid.org/0000-0002-8071-0525
local.identifier.orcidhttps://orcid.org/0000-0002-7073-1226
local.identifier.orcidhttps://orcid.org/0000-0003-0816-0888
local.identifier.orcidhttps://orcid.org/0000-0003-1769-0629
local.publisher.countryBrasil
local.publisher.departmentICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO
local.publisher.departmentICX - DEPARTAMENTO DE FÍSICA
local.publisher.initialsUFMG
local.url.externahttps://analyticalsciencejournals.onlinelibrary.wiley.com/doi/10.1002/jrs.6317

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG