1000 resultados para Máquinas de vetores de suporte
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
In this project the Pattern Recognition Problem is approached with the Support Vector Machines (SVM) technique, a binary method of classification that provides the best solution separating the data in the better way with a hiperplan and an extension of the input space dimension, as a Machine Learning solution. The system aims to classify two classes of pixels chosen by the user in the interface in the interest selection phase and in the background selection phase, generating all the data to be used in the LibSVM library, a library that implements the SVM, illustrating the library operation in a casual way. The data provided by the interface is organized in three types, RGB (Red, Green and Blue color system), texture (calculated) or RGB + texture. At last the project showed successful results, where the classification of the image pixels was showed as been from one of the two classes, from the interest selection area or from the background selection area. The simplest user view of results classification is the RGB type of data arrange, because it’s the most concrete way of data acquisition
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
The human voice is an important communication tool and any disorder of the voice can have profound implications for social and professional life of an individual. Techniques of digital signal processing have been used by acoustic analysis of vocal disorders caused by pathologies in the larynx, due to its simplicity and noninvasive nature. This work deals with the acoustic analysis of voice signals affected by pathologies in the larynx, specifically, edema, and nodules on the vocal folds. The purpose of this work is to develop a classification system of voices to help pre-diagnosis of pathologies in the larynx, as well as monitoring pharmacological treatments and after surgery. Linear Prediction Coefficients (LPC), Mel Frequency cepstral coefficients (MFCC) and the coefficients obtained through the Wavelet Packet Transform (WPT) are applied to extract relevant characteristics of the voice signal. For the classification task is used the Support Vector Machine (SVM), which aims to build optimal hyperplanes that maximize the margin of separation between the classes involved. The hyperplane generated is determined by the support vectors, which are subsets of points in these classes. According to the database used in this work, the results showed a good performance, with a hit rate of 98.46% for classification of normal and pathological voices in general, and 98.75% in the classification of diseases together: edema and nodules
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
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:
Dissertação de mestrado integrado em Engenharia Civil
Resumo:
Esta tese resume os trabalhos desenvolvidos na área de processamento automático de fala com o objetivo de incrementar a quantidade de recursos linguísticos disponíveis para o português europeu. O estágio de desenvolvimento e a aplicação das tecnologias de fala para uma língua estão relacionados com a quantidade e a qualidade de recursos disponíveis para esta língua. Poucas línguas apresentam, no domínio público e livre, todos os recursos necessários para desenvolver as tecnologias de fala. A língua portuguesa, como muitas outras, tem escassez de recursos públicos e livres, o que pode dificultar o desenvolvimento e a aplicação de tecnologias de fala que incorporam esta língua. Os trabalhos descritos nesta tese apresentam uma abordagem para criar bases de dados de fala, recorrendo apenas aos recursos do domínio público e livres, partindo de sinais multimédia sem transcrições ortográficas ou fonéticas. É apresentada uma solução para aproveitar a grande disponibilidade de material multimédia existente no domínio público (podcasts por exemplo) e selecionar segmentos de fala adequados para treinar modelos acústicos. Para isso, foram desenvolvidos vários sistemas para segmentar e classificar automaticamente os noticiários. Estes sistemas podem ser combinados para criar bases de dados de fala com transcrição fonética sem a intervenção humana. Foi desenvolvido um sistema de conversão automático de grafemas para fonemas que se apoia em regras fonológicas e modelos estatísticos. Esta abordagem híbrida é justificada pelos desenvolvimentos de algoritmos de aprendizagem automática aplicados a conversão de grafemas para fonemas e pelo fato do português apresentar uma razoável regularidade fonética e fonológica bem como uma ortografia de base fonológica. Com auxílio deste sistema, foi criado um dicionário de pronunciação com cerca de 40 mil entradas, que foram verificadas manualmente. Foram implementados sistemas de segmentação e de diarização de locutor para segmentar sinais de áudio. Estes sistemas utilizam várias técnicas como a impressão digital acústica, modelos com misturas de gaussianas e critério de informação bayesiana que normalmente são aplicadas noutras tarefas de processamento de fala. Para selecionar os segmentos adequados ou descartar os segmentos com fala não preparada que podem prejudicar o treino de modelos acústicos, foi desenvolvido um sistema de deteção de estilos de fala. A deteção de estilos de fala baseia-se na combinação de parâmetros acústicos e parâmetros prosódicos, na segmentação automática e em classificadores de máquinas de vetores de suporte. Ainda neste âmbito, fez-se um estudo com o intuito de caracterizar os eventos de hesitações presentes nos noticiários em português. A transcrição fonética da base de dados de fala é indispensável no processo de treino de modelos acústicos. É frequente recorrer a sistemas de reconhecimento de fala de grande vocabulário para fazer transcrição automática quando a base de dados não apresenta nenhuma transcrição. Nesta tese, é proposto um sistema de word-spotting para fazer a transcrição fonética dos segmentos de fala. Fez-se uma implementação preliminar de um sistema de word-spotting baseado em modelos de fonemas. Foi proposta uma estratégia para diminuir o tempo de resposta do sistema, criando, a priori, uma espécie de “assinatura acústica” para cada sinal de áudio com os valores de todos os cálculos que não dependem da palavra a pesquisar, como a verosimilhanças de todos os estados dos modelos de fonemas. A deteção de uma palavra utiliza medidas de similaridade entre as verosimilhanças do modelo da palavra e do modelo de enchimento, um detetor de picos e um limiar definido por forma a minimizar os erros de deteção. Foram publicados vários recursos para a língua portuguesa que resultaram da aplicação dos vários sistemas desenvolvidos ao longo da execução desta tese com especial destaque para o sistema de conversão de grafemas para fonemas a partir do qual se publicaram vários dicionários de pronunciação, dicionários com as palavras homógrafas heterofónicas, dicionário com estrangeirismos, modelos estatísticos para a conversão de grafemas para fonemas, o código fonte de todo sistema de treino e conversão e um demonstrador online.
Resumo:
One of the most important goals of bioinformatics is the ability to identify genes in uncharacterized DNA sequences on world wide database. Gene expression on prokaryotes initiates when the RNA-polymerase enzyme interacts with DNA regions called promoters. In these regions are located the main regulatory elements of the transcription process. Despite the improvement of in vitro techniques for molecular biology analysis, characterizing and identifying a great number of promoters on a genome is a complex task. Nevertheless, the main drawback is the absence of a large set of promoters to identify conserved patterns among the species. Hence, a in silico method to predict them on any species is a challenge. Improved promoter prediction methods can be one step towards developing more reliable ab initio gene prediction methods. In this work, we present an empirical comparison of Machine Learning (ML) techniques such as Na¨ýve Bayes, Decision Trees, Support Vector Machines and Neural Networks, Voted Perceptron, PART, k-NN and and ensemble approaches (Bagging and Boosting) to the task of predicting Bacillus subtilis. In order to do so, we first built two data set of promoter and nonpromoter sequences for B. subtilis and a hybrid one. In order to evaluate of ML methods a cross-validation procedure is applied. Good results were obtained with methods of ML like SVM and Naïve Bayes using B. subtilis. However, we have not reached good results on hybrid database
Resumo:
As condições meteorológicas são determinantes para a produção agrícola; a precipitação, em particular, pode ser citada como a mais influente por sua relação direta com o balanço hídrico. Neste sentido, modelos agrometeorológicos, os quais se baseiam nas respostas das culturas às condições meteorológicas, vêm sendo cada vez mais utilizados para a estimativa de rendimentos agrícolas. Devido às dificuldades de obtenção de dados para abastecer tais modelos, métodos de estimativa de precipitação utilizando imagens dos canais espectrais dos satélites meteorológicos têm sido empregados para esta finalidade. O presente trabalho tem por objetivo utilizar o classificador de padrões floresta de caminhos ótimos para correlacionar informações disponíveis no canal espectral infravermelho do satélite meteorológico GOES-12 com a refletividade obtida pelo radar do IPMET/UNESP localizado no município de Bauru, visando o desenvolvimento de um modelo para a detecção de ocorrência de precipitação. Nos experimentos foram comparados quatro algoritmos de classificação: redes neurais artificiais (ANN), k-vizinhos mais próximos (k-NN), máquinas de vetores de suporte (SVM) e floresta de caminhos ótimos (OPF). Este último obteve melhor resultado, tanto em eficiência quanto em precisão.
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)