| spelling |
Frederico Gadelha Guimarãeshttp://lattes.cnpq.br/2472681535872194Carlos Alberto Severiano JúniorTiago Garcia de Senna CarneiroWalmir Matos CaminhasPedro Paulo Balbi de Oliveirahttp://lattes.cnpq.br/7293782719912115Lucas Malacarne Astore2023-04-13T17:51:24Z2023-04-13T17:51:24Z2022-12-16http://hdl.handle.net/1843/51934There have been several applications of computer simulations in studies of spatio-temporal dynamic systems, including epidemiological models. Among the strategies capable of reproducing and predicting future states and behaviors over time, Cellular Automata (CAs) are often applied in geospatial environmental modeling. The core concept of a typical and well-defined CAs model is the development of local rules set that describe the future cell states considering the neighboring cells. The process of building this set demands technical knowledge and years of scientific research. Machine learning-based techniques can be applied in order to automate it, although hyper-parameter optimization algorithms are required. Therefore, this work presents a data-driven approach for CA transitional rules set definition, based exclusively on historical data of a given spatio-temporal phenomenon. The local rules of the automaton are learned and represented using a Multivariate Fuzzy Time Series (MVFTS) method. The MVFTS model is then integrated into the CA simulation, working similarly to a traditional set of CA rules. The proposed methodology was tested using two study cases: Spatial Spread of Chagas Disease and Land Cover/Use Change in Delhi, India. In both sets of data, there was great potential for using the FTS model as a state transition strategy in CA.Há atualmente diversas aplicações de simulações computacionais em estudos de sistemas dinâmicos espaço-temporais, incluindo, por exemplo, em modelos epidemiológicos. Dentre as estratégias capazes de reproduzir e predizer o futuro dos estados e comportamentos dinâmicos, os autômatos celulares (em inglês, cellular automata - CAs) são frequentemente aplicados na modelagem espaço-temporal. O conceito central de um típicoe bem definido modelo CAs é o desenvolvimento de um conjunto de regras locais que descrevem os estados futuros das células considerando as células vizinhas. O processo de construção deste conjunto exige conhecimento técnico e anos de pesquisa científica. Técnicas baseadas em aprendizado de máquina podem ser aplicadas para automatizá-lo, embora sejam necessários algoritmos de otimização de hiperparâmetros. Nesse contexto, este trabalho apresenta uma abordagem orientada a dados para definição de conjuntos de regras de transição de CA, baseada exclusivamente em dados históricos de um determinado fenômeno espaço-temporal. As regras locais do autômato são aprendidas e representadas usando o método Multivariado Fuzzy Time Series (MFTS). O modelo MFTS é então integrado à simulação do CA, funcionando de forma semelhante a um conjunto tradicional de regras. A metodologia proposta foi testada em dois casos de estudo: Espalhamento Espacial da Doença de Chagas e Dinâmica da Mudança do Uso e Cobertura do Solo em Delhi, na Índia. Em ambos conjuntos de dados, verificou-se grande potencial no uso do modelo FTS como estratégia de transição de estados em CA.CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorengUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Engenharia ElétricaUFMGBrasilENG - DEPARTAMENTO DE ENGENHARIA ELÉTRICAEngenharia elétricaAprendizado do computadorModelagemFuzzy times seriesCellular automataSpatio-temporal modelingLand cover land usageDynamics modelingData-driven spatio-temporal modeling with cellular automata and fuzzy time series methodsModelagem espaço-temporal baseada em dados com autômatos celulares e métodos fuzzy time seriesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALDissertação-LucasAstore-vfinal.pdfDissertação-LucasAstore-vfinal.pdfapplication/pdf9117685https://repositorio.ufmg.br/bitstream/1843/51934/3/Disserta%c3%a7%c3%a3o-LucasAstore-vfinal.pdff307cde0dd1c45148aa6a4734674e58dMD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/51934/4/license.txtcda590c95a0b51b4d15f60c9642ca272MD541843/519342023-04-13 14:51:24.532oai:repositorio.ufmg.br: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ório InstitucionalPUBhttps://repositorio.ufmg.br/oaiopendoar:2023-04-13T17:51:24Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false
|