Impact of filtering on CYGNO experiment

dc.contributor.advisor-co1Costa, Igor Abritta
dc.contributor.advisor-co1Latteshttp://lattes.cnpq.br/0457548532296002pt_BR
dc.contributor.advisor1Nóbrega, Rafael Antunes
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/9217577296048418pt_BR
dc.contributor.referee1Cerqueira, Augusto Santiago
dc.contributor.referee1Latteshttp://lattes.cnpq.br/pt_BR
dc.contributor.referee2Lima JĆŗnior, Herman Pessoa
dc.contributor.referee2Latteshttp://lattes.cnpq.brpt_BR
dc.creatorLopes, Guilherme Sebastião Pinheiro
dc.creator.Latteshttp://lattes.cnpq.br/7216200223124240pt_BR
dc.date.accessioned2022-07-14T13:53:42Z
dc.date.available2022-07-14
dc.date.available2022-07-14T13:53:42Z
dc.date.issued2022-03-18
dc.description.abstractThis work proposes to study the impact of classic digital filters and a convolutional neural network in the detection process of pixels with the presence of a signal formed from the release of energy produced by particles that interact inside a TPC detector which makes use of an optical readout based on high-resolution image sensors. For this analysis, an evaluation methodology based on the use of simulation data obtained within the scope of the CYGNO Experiment is also proposed. Finally, real data are analyzed as a way to validate the results. Some classical filtering techniques were selected for comparative purposes, together with a convolutional neural network trained to perform the selection of pixels of interest, with the objective of verifying the advantages of using such techniques in a pre-processing stage of the data, especially regarding energy estimation and processing time. The results obtained showed that a convolutional network has the potential to improve the performance of the processing stage of the images generated by the detector and that a classical non-linear filtering can reproduce a result similar to the algorithm used by the experiment in a time four times shorter.pt_BR
dc.description.resumoEste trabalho visa avaliar o impacto da utilizaĀøc˜ao de filtros digitais no processo de detecĀøc˜ao de pixels em um detector de particulas do tipo TPC, com leitura Ā“otica baseada em sensores de imagem de alta resoluĀøc˜ao. Para esta anĀ“alise, uma metodologia de avaliaĀøc˜ao baseada no uso de dados de simulaĀøc˜ao obtidos no ˆambito do Experimento CYGNO tambĀ“em Ā“e proposta. Por fim, dados reais s˜ao analisados como forma de validar os resultados. Para fins comparativos, algumas tĀ“ecnicas clĀ“assicas de filtragem foram selecionadas, juntamente com a proposta de utilizar uma rede neural convolucional para realizar a seleĀøc˜ao de pixels de interesse, com o objetivo de verificar as vantagens de se utilizar tais tĀ“ecnicas em uma etapa de prĀ“e-processamento dos dados, principalmente no que tange a estimaĀøc˜ao de energia e tempo de processamento. Os resultados obtidos demonstraram que uma rede convolucional tem potencial para melhorar o desempenho da etapa de processamento das imagens geradas pelo detector e que uma filtragem n˜ao-linear clĀ“assica consegue reproduzir um resultado similar ao do algoritmo utilizado pelo experimento em um tempo quatro vezes menor.pt_BR
dc.identifier.doihttps://doi.org/10.34019/ufjf/te/2022/00032
dc.identifier.urihttps://repositorio.ufjf.br/handle/ufjf/14262
dc.languageengpt_BR
dc.publisherUniversidade Federal de Juiz de Fora (UFJF)pt_BR
dc.publisher.countryBrasilpt_BR
dc.publisher.departmentFaculdade de Engenhariapt_BR
dc.publisher.initialsUFJFpt_BR
dc.publisher.programPrograma de Pós-graduação em Engenharia Elétricapt_BR
dc.rightsAcesso Abertopt_BR
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Brazil*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/br/*
dc.subjectFiltragempt_BR
dc.subjectCYGNOpt_BR
dc.subjectRedes neurais convolucionaispt_BR
dc.subjectFilteringpt_BR
dc.subjectConvolution neural networkpt_BR
dc.subject.cnpqCNPQ::ENGENHARIAS::ENGENHARIA ELETRICApt_BR
dc.titleImpact of filtering on CYGNO experimentpt_BR
dc.typeTesept_BR

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
guilhermesebastiaopinheirolopes.pdf
Size:
9.48 MB
Format:
Adobe Portable Document Format
Description:
PDF/A

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: