Análise posicional de jogadores brasileiros de futebol utilizando dados GPS
Ano de defesa: | 2018 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Federal de São Carlos
Câmpus Sorocaba |
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Ciência da Computação - PPGCC-So
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: | |
Palavras-chave em Inglês: | |
Área do conhecimento CNPq: | |
Link de acesso: | https://repositorio.ufscar.br/handle/ufscar/9748 |
Resumo: | The professional soccer is always changing and is constantly searching tools and data to help the decision-making, providing tatics and techniques to the team. In Brazil, this sport goes to same way and the investiments are considerables. The One Sports is a company that capture GPS data from professional soccer players of some brazilian teams. This set of data has a lot of features and the One Sports asked if was possible to predict the ideal position of a player. Then, was firmed a cooperation between a academic study and a comercial company. This work find to understand a propose methods and techniques to predict the ideal position of soccer player, using machine learning algorithms. The database has more of one million of tuples. It was submited to pre-processing step, what is fundamental, because generated new features, removed incomplete and noisy data, generated new balaced dataset and delete outliers, preparing the data to execution of the algorithms k-NN, decision trees, logistic regression, SVM and neural networks. With the purpose to understand the performance and accuracy, some scenarios was tested. There was poor results when executed multi-class problems. The best results come from binary problems. The models k-NN and SVM, specifically to this study, had the best accuracy. It is important to note that SVM spent more than six hours to finish your execution, and k-NN used less than one and half minute to end. |
id |
SCAR_89deab6263e3ffbef352cee983c7a971 |
---|---|
oai_identifier_str |
oai:repositorio.ufscar.br:ufscar/9748 |
network_acronym_str |
SCAR |
network_name_str |
Repositório Institucional da UFSCAR |
repository_id_str |
|
spelling |
Gasparini, RandalÁlvaro, Alexandrehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4735082P8http://buscatextual.cnpq.br/buscatextual/visualizacv.do?metodo=apresentar&id=K8162101J22018-04-13T14:37:50Z2018-04-13T14:37:50Z2018-02-26GASPARINI, Randal. Análise posicional de jogadores brasileiros de futebol utilizando dados GPS. 2018. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, Sorocaba, 2018. Disponível em: https://repositorio.ufscar.br/handle/ufscar/9748.https://repositorio.ufscar.br/handle/ufscar/9748The professional soccer is always changing and is constantly searching tools and data to help the decision-making, providing tatics and techniques to the team. In Brazil, this sport goes to same way and the investiments are considerables. The One Sports is a company that capture GPS data from professional soccer players of some brazilian teams. This set of data has a lot of features and the One Sports asked if was possible to predict the ideal position of a player. Then, was firmed a cooperation between a academic study and a comercial company. This work find to understand a propose methods and techniques to predict the ideal position of soccer player, using machine learning algorithms. The database has more of one million of tuples. It was submited to pre-processing step, what is fundamental, because generated new features, removed incomplete and noisy data, generated new balaced dataset and delete outliers, preparing the data to execution of the algorithms k-NN, decision trees, logistic regression, SVM and neural networks. With the purpose to understand the performance and accuracy, some scenarios was tested. There was poor results when executed multi-class problems. The best results come from binary problems. The models k-NN and SVM, specifically to this study, had the best accuracy. It is important to note that SVM spent more than six hours to finish your execution, and k-NN used less than one and half minute to end.O futebol profissional vem se transformando ao longo do tempo e busca constantemente ferramentas e dados que auxiliem a tomada de decisão, entregando informações táticas e técnicas para o time. Não diferente, a modalidade esportiva no Brasil segue a mesma tendência e os investimentos são cada vez mais consideráveis. A exemplo disso, a empresa One Sports é responsável pela captura de dados GPS de jogadores que atuam profissio- nalmente em determinados clubes nacionais. Uma vez que a coleta existe e a mesma é rica em atributos, esse estudo aborda a possibilidade de inferir a posição tática ideal de um jogador profissional de futebol. Desse modo, promovendo uma parceria entre uma empresa comercial e um estudo acadêmico, esse trabalho busca entender e propor métodos e técnicas para inferir o posicionamento ideal dos jogadores de futebol, adotando algoritmos de aprendizado de máquina. A base de dados contém mais de um milhão de tuplas e passou pela etapa de pré-processamento, a qual demonstrou ser fundamental e de extrema importância, uma vez que gerou novos atributos, eliminou dados incompletos e ruidosos, realizou o balanceamento das classes e removeu outliers, preparando assim a base para a execução dos algoritmos k-NN, árvores de decisão, regressão logística, SVM e redes neurais. Com o objetivo de ampliar o entendimento sobre o desempenho e as taxas de acerto, diferentes cenários foram considerados e testados. Houve baixa taxa de acerto quando os algoritmos trabalharam com um problema multi-classe. Os melhores resultados foram obtidos ao utilizar apenas duas classes. Os modelos k-NN e SVM, especificamente para esse estudo, foram aqueles que obtiveram as melhores taxas de acerto. É importante salientar que o SVM consumiu mais de seis horas para finalizar a sua execução, enquanto o k-NN utilizou menos de um minuto para a entrega dos resultados.Não recebi financiamentoporUniversidade Federal de São CarlosCâmpus SorocabaPrograma de Pós-Graduação em Ciência da Computação - PPGCC-SoUFSCarAprendizado de MáquinaFutebolClassificaçãoGPSClassificationMachine LearningSoccerAprendizaje de máquinaFútbolClasificaciónCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAOAnálise posicional de jogadores brasileiros de futebol utilizando dados GPSPositional analysis of brazilian soccer players using GPS datainfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisOnlineinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFSCARinstname:Universidade Federal de São Carlos (UFSCAR)instacron:UFSCARORIGINALdefesa.pdfdefesa.pdfDissertaçãoapplication/pdf3691474https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/3/defesa.pdff35783e188bf8cff226a15f82024f7d4MD53Termo de encaminhamento da versão definitiva.pdfTermo de encaminhamento da versão definitiva.pdfcarta comprovante - Termo de encaminhamentoapplication/pdf211383https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/4/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf002b346604f55ec1b0265c8d95b79db1MD54LICENSElicense.txtlicense.txttext/plain; charset=utf-81957https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/5/license.txtae0398b6f8b235e40ad82cba6c50031dMD55TEXTdefesa.pdf.txtdefesa.pdf.txtExtracted texttext/plain160917https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/6/defesa.pdf.txtdfbf95e6d0d69cfc05878756aba960d6MD56Termo de encaminhamento da versão definitiva.pdf.txtTermo de encaminhamento da versão definitiva.pdf.txtExtracted texttext/plain1365https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/7/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf.txt82f8c9e6df3dfd755b490df21d6b563dMD57THUMBNAILdefesa.pdf.jpgdefesa.pdf.jpgIM Thumbnailimage/jpeg5511https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/8/defesa.pdf.jpgfb1cc853a82f3df0785384c65e8efa48MD58Termo de encaminhamento da versão definitiva.pdf.jpgTermo de encaminhamento da versão definitiva.pdf.jpgIM Thumbnailimage/jpeg5235https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/9/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf.jpg5f17c08345661c619a188ed5f466dc2eMD59ufscar/97482019-11-21 14:37:45.861oai:repositorio.ufscar.br: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Repositório InstitucionalPUBhttps://repositorio.ufscar.br/oai/requestopendoar:43222023-05-25T12:55:43.843387Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)false |
dc.title.por.fl_str_mv |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
dc.title.alternative.eng.fl_str_mv |
Positional analysis of brazilian soccer players using GPS data |
title |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
spellingShingle |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS Gasparini, Randal Aprendizado de Máquina Futebol Classificação GPS Classification Machine Learning Soccer Aprendizaje de máquina Fútbol Clasificación CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
title_short |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
title_full |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
title_fullStr |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
title_full_unstemmed |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
title_sort |
Análise posicional de jogadores brasileiros de futebol utilizando dados GPS |
author |
Gasparini, Randal |
author_facet |
Gasparini, Randal |
author_role |
author |
dc.contributor.authorlattes.por.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?metodo=apresentar&id=K8162101J2 |
dc.contributor.author.fl_str_mv |
Gasparini, Randal |
dc.contributor.advisor1.fl_str_mv |
Álvaro, Alexandre |
dc.contributor.advisor1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4735082P8 |
contributor_str_mv |
Álvaro, Alexandre |
dc.subject.por.fl_str_mv |
Aprendizado de Máquina Futebol Classificação GPS Classification |
topic |
Aprendizado de Máquina Futebol Classificação GPS Classification Machine Learning Soccer Aprendizaje de máquina Fútbol Clasificación CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
dc.subject.eng.fl_str_mv |
Machine Learning Soccer |
dc.subject.esp.fl_str_mv |
Aprendizaje de máquina Fútbol Clasificación |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
description |
The professional soccer is always changing and is constantly searching tools and data to help the decision-making, providing tatics and techniques to the team. In Brazil, this sport goes to same way and the investiments are considerables. The One Sports is a company that capture GPS data from professional soccer players of some brazilian teams. This set of data has a lot of features and the One Sports asked if was possible to predict the ideal position of a player. Then, was firmed a cooperation between a academic study and a comercial company. This work find to understand a propose methods and techniques to predict the ideal position of soccer player, using machine learning algorithms. The database has more of one million of tuples. It was submited to pre-processing step, what is fundamental, because generated new features, removed incomplete and noisy data, generated new balaced dataset and delete outliers, preparing the data to execution of the algorithms k-NN, decision trees, logistic regression, SVM and neural networks. With the purpose to understand the performance and accuracy, some scenarios was tested. There was poor results when executed multi-class problems. The best results come from binary problems. The models k-NN and SVM, specifically to this study, had the best accuracy. It is important to note that SVM spent more than six hours to finish your execution, and k-NN used less than one and half minute to end. |
publishDate |
2018 |
dc.date.accessioned.fl_str_mv |
2018-04-13T14:37:50Z |
dc.date.available.fl_str_mv |
2018-04-13T14:37:50Z |
dc.date.issued.fl_str_mv |
2018-02-26 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
GASPARINI, Randal. Análise posicional de jogadores brasileiros de futebol utilizando dados GPS. 2018. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, Sorocaba, 2018. Disponível em: https://repositorio.ufscar.br/handle/ufscar/9748. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufscar.br/handle/ufscar/9748 |
identifier_str_mv |
GASPARINI, Randal. Análise posicional de jogadores brasileiros de futebol utilizando dados GPS. 2018. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de São Carlos, Sorocaba, 2018. Disponível em: https://repositorio.ufscar.br/handle/ufscar/9748. |
url |
https://repositorio.ufscar.br/handle/ufscar/9748 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus Sorocaba |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação - PPGCC-So |
dc.publisher.initials.fl_str_mv |
UFSCar |
publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus Sorocaba |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFSCAR instname:Universidade Federal de São Carlos (UFSCAR) instacron:UFSCAR |
instname_str |
Universidade Federal de São Carlos (UFSCAR) |
instacron_str |
UFSCAR |
institution |
UFSCAR |
reponame_str |
Repositório Institucional da UFSCAR |
collection |
Repositório Institucional da UFSCAR |
bitstream.url.fl_str_mv |
https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/3/defesa.pdf https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/4/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/5/license.txt https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/6/defesa.pdf.txt https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/7/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf.txt https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/8/defesa.pdf.jpg https://{{ getenv "DSPACE_HOST" "repositorio.ufscar.br" }}/bitstream/ufscar/9748/9/Termo%20de%20encaminhamento%20da%20versa%cc%83o%20definitiva.pdf.jpg |
bitstream.checksum.fl_str_mv |
f35783e188bf8cff226a15f82024f7d4 002b346604f55ec1b0265c8d95b79db1 ae0398b6f8b235e40ad82cba6c50031d dfbf95e6d0d69cfc05878756aba960d6 82f8c9e6df3dfd755b490df21d6b563d fb1cc853a82f3df0785384c65e8efa48 5f17c08345661c619a188ed5f466dc2e |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR) |
repository.mail.fl_str_mv |
|
_version_ |
1767351133243703296 |