1000 resultados para Máquina de vetores de estado
Resumo:
A number of studies in the areas of Biomedical Engineering and Health Sciences have employed machine learning tools to develop methods capable of identifying patterns in different sets of data. Despite its extinction in many countries of the developed world, Hansen’s disease is still a disease that affects a huge part of the population in countries such as India and Brazil. In this context, this research proposes to develop a method that makes it possible to understand in the future how Hansen’s disease affects facial muscles. By using surface electromyography, a system was adapted so as to capture the signals from the largest possible number of facial muscles. We have first looked upon the literature to learn about the way researchers around the globe have been working with diseases that affect the peripheral neural system and how electromyography has acted to contribute to the understanding of these diseases. From these data, a protocol was proposed to collect facial surface electromyographic (sEMG) signals so that these signals presented a high signal to noise ratio. After collecting the signals, we looked for a method that would enable the visualization of this information in a way to make it possible to guarantee that the method used presented satisfactory results. After identifying the method's efficiency, we tried to understand which information could be extracted from the electromyographic signal representing the collected data. Once studies demonstrating which information could contribute to a better understanding of this pathology were not to be found in literature, parameters of amplitude, frequency and entropy were extracted from the signal and a feature selection was made in order to look for the features that better distinguish a healthy individual from a pathological one. After, we tried to identify the classifier that best discriminates distinct individuals from different groups, and also the set of parameters of this classifier that would bring the best outcome. It was identified that the protocol proposed in this study and the adaptation with disposable electrodes available in market proved their effectiveness and capability of being used in different studies whose intention is to collect data from facial electromyography. The feature selection algorithm also showed that not all of the features extracted from the signal are significant for data classification, with some more relevant than others. The classifier Support Vector Machine (SVM) proved itself efficient when the adequate Kernel function was used with the muscle from which information was to be extracted. Each investigated muscle presented different results when the classifier used linear, radial and polynomial kernel functions. Even though we have focused on Hansen’s disease, the method applied here can be used to study facial electromyography in other pathologies.
Resumo:
A number of studies in the areas of Biomedical Engineering and Health Sciences have employed machine learning tools to develop methods capable of identifying patterns in different sets of data. Despite its extinction in many countries of the developed world, Hansen’s disease is still a disease that affects a huge part of the population in countries such as India and Brazil. In this context, this research proposes to develop a method that makes it possible to understand in the future how Hansen’s disease affects facial muscles. By using surface electromyography, a system was adapted so as to capture the signals from the largest possible number of facial muscles. We have first looked upon the literature to learn about the way researchers around the globe have been working with diseases that affect the peripheral neural system and how electromyography has acted to contribute to the understanding of these diseases. From these data, a protocol was proposed to collect facial surface electromyographic (sEMG) signals so that these signals presented a high signal to noise ratio. After collecting the signals, we looked for a method that would enable the visualization of this information in a way to make it possible to guarantee that the method used presented satisfactory results. After identifying the method's efficiency, we tried to understand which information could be extracted from the electromyographic signal representing the collected data. Once studies demonstrating which information could contribute to a better understanding of this pathology were not to be found in literature, parameters of amplitude, frequency and entropy were extracted from the signal and a feature selection was made in order to look for the features that better distinguish a healthy individual from a pathological one. After, we tried to identify the classifier that best discriminates distinct individuals from different groups, and also the set of parameters of this classifier that would bring the best outcome. It was identified that the protocol proposed in this study and the adaptation with disposable electrodes available in market proved their effectiveness and capability of being used in different studies whose intention is to collect data from facial electromyography. The feature selection algorithm also showed that not all of the features extracted from the signal are significant for data classification, with some more relevant than others. The classifier Support Vector Machine (SVM) proved itself efficient when the adequate Kernel function was used with the muscle from which information was to be extracted. Each investigated muscle presented different results when the classifier used linear, radial and polynomial kernel functions. Even though we have focused on Hansen’s disease, the method applied here can be used to study facial electromyography in other pathologies.
Resumo:
The Support Vector Machines (SVM) has attracted increasing attention in machine learning area, particularly on classification and patterns recognition. However, in some cases it is not easy to determinate accurately the class which given pattern belongs. This thesis involves the construction of a intervalar pattern classifier using SVM in association with intervalar theory, in order to model the separation of a pattern set between distinct classes with precision, aiming to obtain an optimized separation capable to treat imprecisions contained in the initial data and generated during the computational processing. The SVM is a linear machine. In order to allow it to solve real-world problems (usually nonlinear problems), it is necessary to treat the pattern set, know as input set, transforming from nonlinear nature to linear problem. The kernel machines are responsible to do this mapping. To create the intervalar extension of SVM, both for linear and nonlinear problems, it was necessary define intervalar kernel and the Mercer s theorem (which caracterize a kernel function) to intervalar function
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Este artigo apresenta a experiência de implantação de um sistema de gestão em Saúde do Trabalhador implantado na Superintendencia de Controle de Endemias (SUCEN), no período de 1998 a 2002, que operava na atividade de controle químico de vetores no Estado de São Paulo. OBJETIVO: Descrever o sistema de gestão participativa, as ações desenvolvidas e os principais resultados alcançados. MÉTODO: Relato da experiência vivenciada pela equipe usando abordagem qualitativa, análise de documentos e apresentação de dados quantitativos. RESULTADOS: Foram eleitas 11 Comissões de Saúde e Trabalho (COMSAT's) que em conjunto com a equipe técnica iniciaram a identificação dos riscos e de propostas para prevenção e controle dos riscos no trabalho. O mapeamento de riscos resultou em 650 recomendações, 45,7% das quais foram executadas. Foram identificadas como doenças relacionadas ao trabalho: reações alérgicas aos pesticidas, lesões por esforços repetitivos, distúrbios auditivos e patologias de coluna vertebral. Participaram dos cursos básicos de saúde do trabalhador 1.003 servidores (76,3% do total de servidores), sendo que 90,8% dos participantes os consideraram ótimos ou bons. CONCLUSÕES: O sistema de gerenciamento participativo coloca em prática os princípios de gestão democrática do Sistema Único de Saúde (SUS); incorpora, por meio do mapeamento de riscos, o saber do trabalhador; inclui os trabalhadores como sujeitos do processo de negociação e mudanças; pratica o direito à informação. As COMSAT's revelaram-se espaços adequados para a negociação das melhorias nas condições de trabalho. A aprovação do sistema de gestão culminou na validação legal por meio de um acordo tripartite assinado em março de 2002.
Resumo:
A leishmaniose visceral é considerada atualmente uma doença emergente e reemergente, em zonas rurais e urbanas, tanto em área domiciliar quanto peridomiciliar. Este trabalho teve como objetivo verificar a distribuição espacial de Lutzomyia longipalpis e Lutzomyia cruzi no Estado de Mato Grosso. Os dados de 1996 a 2004 foram obtidos junto ao Laboratório de Entomologia, cujas capturas foram realizadas com armadilha de luz CDC. Foram pesquisados 68 dos 139 municípios do estado. Lutzomyia longipalpis e Lutzomyia cruzi ocorreram em 23 e 22 municípios, respectivamente. Os resultados demonstraram a grande ocorrência de Lutzomyia longipalpis nas áreas com bioma de floresta, de transição e de cerrado. Lutzomyia cruzi ocorreu principalmente em municípios com área de pantanal e cerrado. A verificação da distribuição da população de vetores no estado e os biomas preferenciais proporcionam indicar áreas vulneráveis e/ou receptivas para a transmissão da doença.
Resumo:
Pós-graduação em Agronomia (Energia na Agricultura) - FCA
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
OBJETIVO: Analisar dados de reações sorológicas realizadas em dois períodos, entre fins da década de 1960 e o ano de 1983, quando a sorologia passou a complementar a informação sobre triatomíneos vetores do Estado de São Paulo e, de 1984 até 1999, caracterizando o panorama atual da endemia nessa região. MÉTODOS: Foram realizadas análises soroepidemiológicas de reações, obtidas em inquéritos escolares (fins da década de 1960 e entre 1973 e 1983), em inquéritos populacionais em Cananéia, Iguape e Peruíbe (entre 1980 e 1982) e em moradores de unidades domiciliares. Os resultados da análise foram associados a informações obtidas sobre os vetores encontrados. RESULTADOS: Manteve-se a sororreatividade entre escolares em patamares baixos, porém constantes, ao longo dos anos 1973 a 1982, tornando-se nulos em 1983. A curva de freqüência de distribuição de títulos demonstrou um padrão típico de área negativa no município de Cananéia e de baixa endemicidade nos demais. A investigação de casos revelou predominância de importados e, quando autóctones, sugestivos de transmissão oral. Foram observadas 1.261 unidades domiciliares com relato de presença de triatomíneos vetores (principais espécies: Panstrongylus megistus e Triatoma tibiamaculata), com um total de 5.338 amostras de sangue colhidas e 40 sororreagentes (0,75%). Exemplares adultos predominaram no intradomicílio e cerca da metade deles sem ingesta de sangue humano. Não foi observada diferença entre resultados de sorologia em moradores de casas com triatomíneos infectados e não infectados por Trypanosoma cruzi. CONCLUSÕES: Os resultados mostram ser necessário desenvolver um trabalho integrado entre instituições, que permita o isolamento e estudos de cepas e de isolados de tripanosomatídeos presentes em vetores, reservatórios (domésticos ou não) e humanos, com o objetivo de observar a interação dos pontos de vista evolutivo, de patogenia e de ecologia, de eventuais diferentes linhagens.
Resumo:
The use of mobile robots in the agriculture turns out to be interesting in tasks of cultivation and application of pesticides in minute quantities to reduce environmental pollution. In this paper we present the development of a system to control an autonomous mobile robot navigation through tracks in plantations. Track images are used to control robot direction by preprocessing them to extract image features, and then submitting such characteristic features to a support vector machine to find out the most appropriate route. As the overall goal of the project to which this work is connected is the robot control in real time, the system will be embedded onto a hardware platform. However, in this paper we report the software implementation of a support vector machine, which so far presented around 93% accuracy in predicting the appropriate route.
Resumo:
Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes.
Resumo:
Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.
Resumo:
Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.
Resumo:
Depois de acentuar que a tripanossomose americana é uma zoonose do tipo anfixenose, bem enquadrável no conceito de PAVLOVSKY de infecção com focos naturais, o Autor analisa o problema da multiplicidade e diversidade dêstes focos que são devidas ao grande número de hospedeiros e vetores naturais com hábitos variados. Descreve, em seguida, alguns focos naturais mais freqüentes e importantes, observados na região nordeste do Estado de São Paulo e áreas limítrofes do Estado de Minas Gerais, focos êstes constituídos por buracos e cavidades no solo, ocos e anfractuosidades em troncos de árvores, tufos de vegetação herbácea, touceiras de piteira e copa de palmeiras, onde triatomíneos e mamíferos convivem.
Resumo:
São apresentadas as principais informações de ordem geográfica do Estado, que é dividido em 23 micro-regiões e 141 municípios. Desses, em 129 foram encontrados triatomíneos, de acordo com informações obtidas em diversos organismos de pesquisa, de 1957 a 1974. A espécie principal no Estado é o Triatoma brasiliensis, semi-doméstico, encontrado nas casas de 91,5% dos municípios (129), suas taxas de infecção variam de 1,0 a 40,4% (média de 8,2%), o P. megistus é a terceira espécie e é encontrado em 61,7% dos municípios (87), com uma taxa de infecção muito variável, com média de 3,9% e máxima de 25,9%. Em áreas restritas como a do Cariri essa taxa subirá para 24,5%. A segunda espécie, menos doméstica que as duas primeiras é o T. pseudomaculata, encontrado em 68,8% dos municípios e taxas de infecção variando de 0,3% a 7,1% e uma média de 4,2%. A quarta espécie é o Rhodnius nasutus, encontrado em 17,7% dos municípios e infectado em 1,0%. Penetrando na casa (não foram encontradas ninfas) há uma quinta espécie, o Panstrongylus lutzi capturado em algumas casas de 26 municípios (18,4%) e com elevadas taxas de infecção: 17,9%. Com taxas globais de triatomíneos infectados por T. cruzi acima de 10% estão 12 municípios, dos quais mais da metade constitui as 4 micro-regiões centrais do Estado: Sertão de Quixeramobim, Sertão de Senador Pompeu, Sertão dos Inhamuns e Médio Jaguaribe.