Electromagnetic transients impinging on electromagnetic power devices - such as electric machines, transformers and reactors - can stress the design severely. Thus the magnitudes of the transients are often decisive for the design of the devices. Further, the operation of a device can be transient in itself. This is the case for the explosive magnetic flux compression generator (EMG) and a ferromagnetic actuator. Models are presented that are mainly intended for transients in the millisecond range and faster. Hence, eddy currents and the related skin and proximity effect become significant in windings, magnetic cores and in the armatures of the devices. These effects are important for, e.g., the damping of the transients. Further, the displacement current in the insulation of the winding is significant. It changes the response of the windings dramatically, as it manifests the finite velocity of propagation of the electromagnetic fields. Under such circumstances, reflections and excited resonances can make the transient voltage and current distribution highly irregular. Induced voltages are modelled with self and mutual inductances or reluctances combined with winding templates. The displacement currents are modelled with capacitances or coefficients of potential. Cauer circuits and their dual form are used to model eddy currents in laminated cores and in conductors. The Cauer circuit enables one to consider hysteresis and the non-linear response of a magnetic core. It is also used to model the eddy currents in the moving armature of an EMG. A set-up is presented that can be used to study the transient voltage and the current distribution along a coil. The transient response of coaxially insulated windings is analysed and modelled in detail. A lumped circuit model is developed for a coil, DryformerTM - the new high-voltage transformer - and PowerformerTM, the new high-voltage generator. An alternative model, a combined lumped circuit and FEM model, is presented for a coaxially insulated winding in two slot cores.

Multivariate pattern analysis (MVPA) of fMRI data has been growing in popularity due to its sensitivity to networks of brain activation. It is performed in a predictive modeling framework which is natural for implementing brain state prediction and real-time fMRI applications such as brain computer interfaces. Support vector machines (SVM) have been particularly popular for MVPA owing to their high prediction accuracy even with noisy datasets. Recent work has proposed the use of relevance vector machines (RVM) as an alternative to SVM. RVMs are particularly attractive in time sensitive applications such as real-time fMRI since they tend to perform classification faster than SVMs. Despite the use of both methods in fMRI research, little has been done to compare the performance of these two techniques. This study compares RVM to SVM in terms of time and accuracy to determine which is better suited to real-time applications.

En esta Tesis ha sido analizado el control de la màquina sincrónica de rotor bobinado actuando en isla. Para esta configuración, la velocidad mecànica determina la frecuencia, y la tensión de rotor se utiliza para fijar la amplitud de la tensión de estator. Debido a que la constante de tiempo eléctrica es mucho más ràpida comparada con la constante de tiempo mecánica, la velocidad mecánica fue considerada constante y externamente regulada y la investigación se enfocó en la regulación de la amplitud de la tensión de estator.Cuatro diferentes controladores basados en técnicas de modos deslizantes fueron diseñados en el marco de referencia dq. Las leyes de control obtenidas regulan la amplitud de la tensión de estator independientemte del valor de la carga. Adicionalmente, sólo las medidas de tensión y posición del rotor (para calcular la transformada dq) son necesarias. La estabilidad de los puntos de equilibrio obtenidos fueron probados al menos utilizando anàlisis de pequeña señal.Se realizó la validación por simulación y experimental de cada controlador en diferentes escenarios. Los resultados obtenidos validan los diseños y muestran las principales ventajas y desventajas de el sistema en lazo cerrado.El capítulo 2 cubre los problemas de modelado de la màquina sincrónica de rotor bobinado. Partiendo de las ecuaciones trifásicas generales, y utilizando la transformada de Park, se encontraron el modelo en dq del generador sincrónico de rotor bobinado (WRSG) en isla, alimentando tanto carga resistiva como inductiva. Los puntos de equilibrio del sistema obtenido fueron analizados y calculados, luego se definió el objetivo de control. Finalmente, se obtuvieron modelos lineales aproximados y sus respectivas funciones de transferencia.Los controladores PI son los más usados en la industria porque ofrecen buen desempeño y son sencillos de implementar. En el capítulo 3, se obtuvieron las reglas de sintonización para el controlador PI, y se analizaron estos resultados con el objetivo de proponer nuevos controladores que mejoraran el desempeño de la clásica aproximación PI.El esquema de control en modos deslizantes para la WRSG conectada a una carga resistiva fue diseñado en el capítulo 4. Éste, también incluye un completo análisis de estabilidad del sistema en lazo cerrado. El capítulo 5 presenta dos diseños basados en modos deslizantes para regular la amplitud de la tensión de estator para el WRSG actuando en isla. Ambos diseños usan la componente d de la tensión de estator en la función de conmutación. El primer caso es un control anidado, donde un lazo externo PI es añadido para proveer la referencia de la componente d de la tensión. En la segunda aproximación un término integral es añadido a la superficie de conmutación.El caso de alimentar una carga inductiva es estudiado en el capítulo 6. El controlador requiere una extensión dinámica debido a que la amplitud de la tensión de estator es una salida de grado relativo cero. Como resultado, un controlador robusto, que no depende de los parámetros de la máquina ni de los valores de carga es obtenido. En el capítulo 7 los resultados de simulación y experimentales para los controladores diseñados para el WRSG actuando en isla son presentados. En primer lugar, una descripción completa del banco es presentada. Esta incluye detalles de la etapa de adquisición de datos y de la DSP utilizada. En segundo lugar, se hace la descripción del procedimiento de simulación. Luego, las simulaciones y experimentos, que contienen diferentes escenarios, con cambios de referencia y variaciones de carga para cada controlador son presentados. / The control of the stand-alone the wound rotor synchronous generator has been analyzed in this dissertation. For this islanded configuration, the mechanical speed determines the frequency, and the rotor voltage is used to set the stator voltage amplitude. Due to the electrical time constant is so fast compared with the mechanical time constants, the mechanical speed was considered constant and externally regulated and the research was focused on the stator voltage amplitude regulation.Four different controllers based on sliding mode control techniques were designed in the dq reference frame. The obtained control laws regulate the stator voltage amplitude irrespectively of the load value. Furthermore, only voltage and rotor position measures (to compute the dq transformation), are required. The stability of the obtained equilibrium points was proved at least using small-signal analysis. Simulation and experimental validation of each controller containing several scenarios were carried out. The obtained results validate the designs and show the main advantages and disadvantages of each closed loop system. Chapter 2 covers the modeling issues of the wound rotor synchronous machine. From the general three-phase dynamical equations, and using the Park transformation, the dq-model of the stand-alone wound rotor synchronous generator feeding both a resistive and an inductive load are obtained. Equilibrium points of the obtained systems are analyzed and, after defining the control objective, the desired equilibrium points are computed.Finally, linear approximated models are obtained and their transfer functions are also presented.PI controllers are the most used in the industry because they offers good performance and are easily implementables. In Chapter 3 we obtain the tuning rule for the PI controller, and we analyze these results in order to propose new controllers which improve the classic PI approach.The sliding mode control scheme for the WRSG connected to a resistive load is designed in Chapter 4. It also includes a complete stability analysis of the closed loop system. Chapter 5 presents two sliding mode designs to regulate the stator voltage amplitude for a stand-alone wound rotor synchronous generator. Both use the stator voltage d-component error in the switching function. The first case is a nested controller, where an outer PI loop is added to provide the proper d-voltage component reference. In the second approach an integral term is added to the switching function. The case of feeding an inductive load is studied in Chapter 6. The controller introduces a dynamic extension because the stator voltage amplitude is a zero relative degree output. As result, a robust controller, which neither depends on the machine parameters nor on the load values, is obtained. In Chapter 7 the simulation and the experimental results of the designed controllers for the stand-alone wound rotor synchronous generator are presented. Firstly, a complete description of the bench is provided. It also includes details of the data acquisition stage and the used DSP card. Secondly, the description of the simulation procedure is commented. Then, the simulation and experiments which contains several scenarios, with reference change and load variations evaluated for each controller are presented.

[pt] Sentiment Analysis é um problema de categorização de texto no qual deseja-se identificar opiniões favoráveis e desfavoráveis com relação a um tópico. Um exemplo destes tópicos de interesse são organizações e seus produtos. Neste problema, documentos são classificados pelo sentimento, conotação, atitudes e opiniões ao invés de se restringir aos fatos descritos neste. O principal desafio em Sentiment Classification é identificar como sentimentos são expressados em textos e se tais sentimentos indicam uma opinião positiva (favorável) ou negativa (desfavorável) com relação a um tópico. Devido ao crescente volume de dados disponível na Web, onde todos tendem a ser geradores de conteúdo e expressarem opiniões sobre os mais variados assuntos, técnicas de Aprendizado de Máquina vem se tornando cada vez mais atraentes. Nesta dissertação investigamos métodos de Aprendizado de Máquina para Sentiment Analysis. Apresentamos alguns modelos de representação de documentos como saco de palavras e N-grama. Testamos os classificadores SVM (Máquina de Vetores Suporte) e Naive Bayes com diferentes modelos de representação textual e comparamos seus desempenhos. / [en] Sentiment Analysis is a text categorization problem in which we want to identify favorable and unfavorable opinions towards a given topic. Examples of such topics are organizations and its products. In this problem, docu- ments are classifed according to their sentiment, connotation, attitudes and opinions instead of being limited to the facts described in it. The main challenge in Sentiment Classification is identifying how sentiments are expressed in texts and whether they indicate a positive (favorable) or negative (unfavorable) opinion towards a topic. Due to the growing volume of information available online in an environment where we all tend to be content generators and express opinions on a variety of subjects, Machine Learning techniques have become more and more attractive. In this dissertation, we investigate Machine Learning methods applied to Sentiment Analysis. We present document representation models such as bag-of-words and N-grams.We compare the performance of the Naive Bayes and the Support Vector Machine classifiers for each proposed model

Cette thèse traite de la manipulation de l'énergie dans trois systèmes quantiques ouverts différents dans la limite de couplage faible système-environnement, et leurs dynamiques respectives sont décrites par une équation maîtresse quantique markovienne. Dans le premier chapitre, le calcul d'une telle équation est réalisé pour un système particulier, et diverses notions de thermodynamique quantique sont introduites. Pour le premier système physique, on analyse le transport d'énergie le long de chaînes atomiques (entre 2 et 7 atomes) soumises à un rayonnement de corps noir proche de la température ambiante. Il est montré que l'efficacité du transport peut atteindre des valeurs remarquables, surpassant 100% et atteignant jusqu'à 1400% dans certaines configurations. De plus, lorsque l'efficacité est amplifiée, la portée du transport est également considérablement augmentée. Le chapitre suivante traite aussi du transport d'énergie dans des chaînes atomiques. Le système quantique est placé à l'interface d'un isolant topologique photonique (ITP), qui supporte un plasmon polariton de surface (PPS) insensible à la réflexion. Le PPS se propage le long de la chaîne atomique et assiste le transport d'énergie. La comparaison est faite entre PPSs réciproque et unidirectionnel en termes d'efficacité du transport, et il est démontré que ce dernier produit une meilleure efficacité, de plus d'un ordre de grandeur. De surcroît, divers aspects pratiques dus aux propriétés des ITPs sont mis en avant, notamment la robustesse du transport d'énergie en présence de défauts sur le parcours du PPS. Enfin, un système quantique immergé dans un champ électromagnétique hors équilibre thermique est étudié. Il est composé d'un système à trois niveaux d'énergie, jouant le rôle de machine thermique quantique à absorption, ainsi que de N atomes à deux niveaux ("qubits") qui sont affectés par l'action de la machine. Il est montré que la machine est capable de délivrer des tâches thermiques d'intensité significative sur les qubits, y compris lorsque leur nombre augmente. De plus, il est mis en évidence qu'en raison d'interactions qubit-qubit, les tâches réalisées par la machine sont distribuées parmi l'ensemble du système des qubits en interaction, de sorte que dans certains cas, même les qubits complètement découplés de la machine subissent une modification de température considérable. Ce mécanisme de distribution des tâches est analysé à travers les corrélations entre différentes partitions du système quantique. Par ailleurs, le contrôle des tâches thermiques est également discuté. / This thesis deals with energy management in open quantum systems. Three different systems are under study in the limit of weak system-environment coupling, and their dynamics is described by Markovian quantum master equations. In the first chapter, the complete derivation of such equation is performed in a specific case, and several notions of quantum thermodynamics are introduced. In the first system, energy transport is investigated along atomic chains (between 2 and 7 atoms) embedded in blackbody radiation around room temperature. It is shown that the transport efficiency can reach remarkable values, exceeding 100% and reaching 1400% in some configurations. Moreover, when the efficiency is amplified, the transport range is also considerably increased. The following chapter also deals with energy transport in atomic chains. The quantum system is located at the interface of a photonic topological insulator (PTI), supporting a unidirectional surface-plasmon-polariton (SPP) immune to backscattering. The SPP propagates along the chain and assists energy transport. Comparison is made between reciprocal and unidirectional SPPs in terms of transport efficiency, and it is shown that the latter can yield an efficiency larger by one order of magnitude. In addition, several practical aspects stemming from PTIs are highlighted, including the robustness of energy transport in the presence of defects on the SPP path. In the last chapter, a quantum system embedded in an out-of-thermal-equilibrium electromagnetic field is investigated. It is composed of a three-level atom playing the role of an absorption quantum thermal machine, as well as N two-level atoms ('qubits'), with N=1,...,6, which are the target bodies. It is demonstrated that the machine is able to perform significant thermal tasks on the qubits, even when their number is increased. Moreover, it is pointed out that due to qubit-qubit interactions, the tasks delivered by the machine are distributed throughout the system of interacting qubits, such that in some cases the temperature of the qubits which are completely decoupled from the machine can still be considerably affected by it. This task-distribution mechanism is investigated by means of the correlations between different subparts of the system. In addition, the tuning of thermal tasks is discussed.

SOUZA, Fábio Henrique de. Desempenho energético de um trator agrícola 4x2 – TDA, em função da pressão de inflação dos pneus em pista de concreto e em solo mobilizado, conforme a norma OECD – código 2. 2013. 107 f. : Dissertação (mestrado) - Universidade Federal do Ceará, Centro de Ciências Agrárias, Departamento de Engenharia Agrícola, Programa de Pós-Graduação em Engenharia Agrícola, Fortaleza-CE, 2013. / Submitted by demia Maia (demiamlm@gmail.com) on 2016-06-28T13:26:48Z No. of bitstreams: 1 2013_dis_fhsouza.pdf: 2128349 bytes, checksum: 4b52bacc875b4c1ecff06ea1b54d30aa (MD5) / Approved for entry into archive by demia Maia (demiamlm@gmail.com) on 2016-06-28T13:27:24Z (GMT) No. of bitstreams: 1 2013_dis_fhsouza.pdf: 2128349 bytes, checksum: 4b52bacc875b4c1ecff06ea1b54d30aa (MD5) / Made available in DSpace on 2016-06-28T13:27:24Z (GMT). No. of bitstreams: 1 2013_dis_fhsouza.pdf: 2128349 bytes, checksum: 4b52bacc875b4c1ecff06ea1b54d30aa (MD5) Previous issue date: 2013 / Agricult tractor adequation aiming the use of appropriated tire inflation pressures for different surface conditions results in better overall performance with consequent increase in operational capacity and better quality of service. Thus this study aimed to assess the energy performance of a farm tractor 4x2 - TDA working with different forces in the drawbar, inflation pressure of tires on concrete surface and tilled soil, using as a testing standard OECD – “Code 2" (2012). The tests were conducted at the Center for Testing Machines and Tires Agroforestry - NEMPA, a randomized 2x3x2 factorial and tracks with five repetitions, two tire inflation pressures Tractor 165.4 kPa (24 psi) in rear axles and 220.6 kPa (32 psi) front axles on the tractor, corresponding to maximum inflation pressure recommended by the tire manufacturer and 110.3 kPa (16 psi) in rear axles and 110.3 kPa (16 psi) in front wheelsets Tractor, corresponding to minimal inflation pressure recommended by the tire manufacturer, three forces applied to the drawbar 100%, 75% and 50% of the maximum force of traction at maximum power and rated speed of the engine and two types of bearing surfaces . These factors were arranged to allow evaluation of the effects of performance variables individually or in groups, with all data presented normality were subjected to analysis of variance, using the DMS test at 5% significance for the comparison of means, the data not normally distributed were arranged for statistical analysis by Exponentially Weighted Moving Average - MMEP. The tractor test was evaluated in the 7040 New Holland TM engine with maximum power specified by the manufacturer of 132 kW at 2200 rpm, pulling the Mobile Unit Testing in Drawbar - UMEB generated. In field trials showed that the minimum tire inflation pressure recommended by the tire manufacturer has improved the energy performance of the tractor, reducing specific consumption of fuel and increasing the yield on the tractor drawbar. In concrete surface the tractor got maximum tensile strength 32.6% higher than the maximum tensile strength obtained in surface soil mobilized. The test criteria employed the standard OECD - "Code 2" provided a standardized test in facilitating the comparison between the factors evaluated. / A adequação de um trator agrícola, visando utilização de pressões de inflação dos pneus adequadas, para diferentes condições superficiais de solo, resulta em melhor desempenho geral, com consequente aumento da capacidade operacional e melhor qualidade de operação. Assim este trabalho teve como objetivo avaliar o desempenho energético de um trator agrícola 4x2 - TDA trabalhando com diferentes forças na barra de tração, pressão de inflação dos pneus em superfície de concreto e em solo mobilizado, utilizando como norma de ensaio a OECD – “Código 2” (2012). Os ensaios foram realizados, no Núcleo de Ensaios de Máquinas e Pneus Agroflorestais – NEMPA, com delineamento experimental em faixas e esquema fatorial 2x3x2 com cinco repetições, sendo duas pressões de inflação dos pneus do trator 165,4 kPa (24 psi) nos rodados traseiro e 220,6 kPa (32 psi) nos rodados dianteiro do trator, correspondente a máxima pressão de inflação recomendada pelo fabricante dos pneus e 110,3 kPa (16 psi) nos rodados traseiro e 110,3 kPa (16 psi) nos rodados dianteiro do trator, correspondente a mínima pressão de inflação recomendada pelo fabricante dos pneus, três forças aplicadas na barra de tração 100%, 75% e 50% da força máxima de tração na potência máxima e velocidade nominal do motor e dois tipos de superfícies de rolamento. Esses fatores foram arranjados para permitir a avaliação dos efeitos das variáveis de desempenho individualmente ou em grupos, sendo todos os dados que apresentaram normalidade foram submetidos à análise de variância, aplicando o teste DMS a 5% de significância, para a comparação das médias, os dados que não apresentaram distribuição normal foram arranjados para analise estatística através da Média Móvel Exponencialmente Ponderada - MMEP. O trator avaliado no ensaio foi o New Holland TM 7040 com potência máxima no motor indicada pelo fabricante de 132 kW a 2200 rpm, tracionando a Unidade Móvel de Ensaio na Barra de Tração - UMEB. Nos ensaios de campo observou-se que a mínima pressão de inflação dos pneus recomendada pelo fabricante dos pneus melhorou o desempenho energético do trator, reduzindo o consumo especifico de combustível e aumentando o rendimento na barra de tração do trator. Em superfície de concreto o trator obteve força máxima de tração 32,6% superior à força máxima de tração obtida em superfície de solo mobilizado. Os critérios de ensaio empregados da norma OECD - “Código 2” proporcionaram uma padronização no ensaio facilitando a comparação entre os fatores avaliados.

Submitted by Daniel Felipe Silva Santos null (danielfssantos@yahoo.com.br) on 2017-08-29T19:56:20Z No. of bitstreams: 1 ReconhecedorDeVeiculos2D-DBM.pdf: 3800862 bytes, checksum: 46f12ff55f4e0680833b9b1b184ad505 (MD5) / Approved for entry into archive by Luiz Galeffi (luizgaleffi@gmail.com) on 2017-08-29T20:19:13Z (GMT) No. of bitstreams: 1 santos_dfs_me_sjrp.pdf: 3800862 bytes, checksum: 46f12ff55f4e0680833b9b1b184ad505 (MD5) / Made available in DSpace on 2017-08-29T20:19:13Z (GMT). No. of bitstreams: 1 santos_dfs_me_sjrp.pdf: 3800862 bytes, checksum: 46f12ff55f4e0680833b9b1b184ad505 (MD5) Previous issue date: 2017-08-14 / Neste trabalho é proposto um método para reconhecer veículos em imagens coloridas baseado em uma rede neural Perceptron Multicamadas pré-treinada por meio de técnicas de aprendizado em profundidade, sendo uma das técnicas composta por Máquinas de Boltzmann Profundas e projeção bilinear e a outra composta por Máquinas de Boltzmann Profundas Multinomiais e projeção bilinear. A proposição deste método justifica-se pela demanda cada vez maior da área de Sistemas de Transporte Inteligentes. Para se obter um reconhecedor de veículos robusto, a proposta é utilizar o método de treinamento inferencial não-supervisionado Divergência por Contraste em conjunto com o método inferencial Campos Intermediários, para treinar múltiplas instâncias das redes profundas. Na fase de pré-treinamento local do método proposto são utilizadas projeções bilineares para reduzir o número de nós nas camadas da rede. A junção das estruturas em redes profundas treinadas separadamente forma a arquitetura final da rede neural, que passa por uma etapa de pré- treinamento global por Campos Intermediários. Na última etapa de treinamentos a rede neural Perceptron Multicamadas (MLP) é inicializada com os parâmetros pré-treinados globalmente e a partir deste ponto, inicia-se um processo de treinamento supervisionado utilizando gradiente conjugado de segunda ordem. O método proposto foi avaliado sobre a base BIT-Vehicle de imagens frontais de veículos coletadas de um ambiente de tráfego real. Os melhores resultados obtidos pelo método proposto utilizando rede profunda multinomial foram de 81, 83% de acurácia média na versão aumentada da base original e 91, 10% na versão aumentada da base combinada (Carros, Caminhões e Ônibus). Para a abordagem de redes profundas não multinomiais os melhores resultados foram de 81, 42% na versão aumentada da base original e 91, 13% na versão aumentada da base combinada. Com a aplicação da projeção bilinear, houve um decréscimo considerável nos tempos de treinamento das redes profundas multinomial e não multinomial, sendo que no melhor caso o tempo de execução do método proposto foi 5, 5 vezes menor em comparação com os tempos das redes profundas sem aplicação de projeção bilinear. / In this work it is proposed a vehicle recognition method for color images based on a Multilayer Perceptron neural network pre-trained through deep learning techniques (one technique composed by Deep Boltzmann Machines and bilinear projections and the other composed by Multinomial Deep Boltzmann Machines and bilinear projections). This proposition is justified by the increasing demand in Traffic Engineering area for the class of Intelligent Transportation Systems. In order to create a robust vehicle recognizer, the proposal is to use the inferential unsupervised training method of Contrastive Divergence together with the Mean Field inferential method, for training multiple instances of deep models. In the local pre-training phase of the proposed method, bilinear projections are used to reduce the number of nodes of the neural network. The combination of the separated trained deep models constitutes the final recognizer’s architecture, that yet will be global pre-trained through Mean Field. In the last phase of training the Multilayer Perceptron neural network is initialized with globally pre-trained parameters and from this point, a process of supervised training starts using second order conjugate gradient. The proposed method was evaluated over the BIT-Vehicle database of frontal images of vehicles collected from a real road traffic environment. The best results obtained by the proposed method that used multinomial deep models were 81.83% of mean accuracy in the augmented original database version and 91.10% in the augmented combined database version (Cars, Trucks and Buses). For the non-multinomial deep models approach, the best results were 81.42% in the augmented version of the original database and 91.13% in the augmented version of the combined database. It was also observed a significant decreasing in the training times of the multinomial deep models and non-multinomial deep models with bilinear projection application, where in the best case scenario the execution time of the proposed method was 5.5 times lower than the deep models that did not use bilinear projection.

A classificação de imagens de satélite é muito utilizada para elaborar mapas de cobertura do solo. O objetivo principal deste trabalho consistiu no mapeamento automático da cobertura do solo no entorno da Usina de Lajeado (TO) utilizando-se o classificador SVM. Buscou-se avaliar a dimensão de áreas antropizadas presentes na represa e a acurácia da classificação gerada pelo algoritmo, que foi comparada com a acurácia da classificação obtida pelo tradicional classificador MAXVER. Esta dissertação apresentou sugestões de calibração do algoritmo SVM para a otimização do seu resultado. Verificou-se uma alta acurácia na classificação SVM, que mostrou o entorno da represa hidrelétrica em uma situação ambientalmente favorável. Os resultados obtidos pela classificação SVM foram similares aos obtidos pelo MAXVER, porém este último contextualizou espacialmente as classes de cobertura do solo com uma acurácia considerada um pouco menor. Apesar do bom estado de preservação ambiental apresentado, a represa deve ter seu entorno devidamente monitorado, pois foi diagnosticada uma grande quantidade de incêndios gerados pela população local, sendo que as ferramentas discutidas nesta dissertação auxiliam esta atividade de monitoramento. / Satellite Image Classification are very useful for building land cover maps. The aim of this study consists on an automatic land cover mapping in the domain area of Lajeados dam, at Tocantins state, using the SVM classifier. The aim of this work was to evaluate anthropic dimension areas near the dam and also to verify the algorithms classification accuracy, which was compared to the results of the standard ML (Maximum Likelihood) classifier. This work presents calibration suggestions to the SVM algorithm for optimizing its results. SVM classification presented high accuracy, suggesting a good environmental situation along Lajeados dam region. Classification results comparison between SVM and ML were quite similar, but SVMs spatial contextual mapping areas were slightly better. Although environmental situation of the study area was considered good, monitoring ecosystem is important because a significant quantity of burnt areas was noticed due to local communities activities. This fact emphasized the importance of the tools discussed in this work, which helps environmental monitoring.

Neste trabalho, foram utilizadas as vantagens da ferramenta matemática de análise temporal e espectral, a transformada wavelet discreta (DWT), além dos coeficientes de predição linear (LPC) e do algoritmo de inteligência artificial, Least Squares Support Vector Machines (LS-SVM), para aplicações em análise de sinais de voz e classificação de vozes patológicas. Inúmeros trabalhos na literatura têm demonstrado o grande interesse existente por ferramentas auxiliares ao diagnóstico de patologias da laringe. Os componentes da DWT forneceram parâmetros de medida para a análise e classificação das vozes patológicas, principalmente aquelas provenientes de pacientes com edema de Reinke e nódulo nas pregas vocais. O banco de dados com as vozes patológicas foi obtido do Departamento de Otorrinolaringologia e Cirurgia de Cabeça e Pescoço do Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto (FMRP-USP). Utilizando-se o algoritmo de reconhecimento de padrões, LS-SVM, mostrou-se que a combinação dos componentes da DWT de Daubechies com o filtro LP inverso levou a um classificador de bom desempenho alcançando mais de 90% de acerto na classificação das vozes patológicas. / The main objective of this work was to use the advantages of the time-frequency analysis mathematical tool, discrete wavelet transform (DWT), besides the linear prediction coefficients (LPC) and the artificial intelligence algorithm, Least Squares Support Vector Machines (LS-SVM), for applications in voice signal analysis and classification of pathological voices. A large number of works in the literature has been shown that there is a great interest for auxiliary tools to the diagnosis of laryngeal pathologies. DWT components gave measure parameters for the analysis and classification of pathological voices, mainly that ones from patients with Reinke\'s edema and nodule in the vocal folds. It was used a data bank with pathological voices from the Otolaryngology and the Head and Neck Surgery sector of the Clinical Hospital of the Faculty of Medicine at Ribeirão Preto, University of Sao Paulo (FMRP-USP), Brazil. Using the automatic learning algorithm applied in pattern recognition problems, LS-SVM, results have showed that the combination of Daubechies\' DWT components and inverse LP filter leads to a classifier with good performance reaching more than 90% of accuracy in the classification of the pathological voices.

O grande crescimento da Internet ocorreu a partir da década de 1990 com o surgimento dos provedores comerciais de serviços, e resulta principalmente da boa aceitação e vasta disseminação do uso da Web. O grande problema que afeta a escalabilidade e o uso de tal serviço refere-se à organização e à classificação de seu conteúdo. Os engenhos de busca atuais possibilitam a localização de páginas na Web pela comparação léxica de conjuntos de palavras perante os conteúdos dos hipertextos. Tal mecanismo mostra-se ineficaz quando da necessidade pela localização de conteúdos que expressem conceitos ou objetos, a exemplo de produtos à venda oferecidos em sites de comércio eletrônico. A criação da Web Semântica foi anunciada no ano de 2000 para esse propósito, visando o estabelecimento de novos padrões para a representação formal de conteúdos nas páginas Web. Com sua implantação, cujo prazo inicialmente previsto foi de dez anos, será possível a expressão de conceitos nos conteúdos dos hipertextos, que representarão objetos classificados por uma ontologia, viabilizando assim o uso de sistemas, baseados em conhecimento, implementados por agentes inteligentes de software. O projeto DEEPSIA foi concebido como uma solução centrada no comprador, ao contrário dos atuais Market Places, para resolver o problema da localização de páginas Web com a descrição de produtos à venda, fazendo uso de métodos de classificação de textos, apoiados pelos algoritmos k-NN e C4.5, no suporte ao processo decisório realizado por um agente previsto em sua arquitetura, o Crawler Agent. Os testes com o sistema em sites brasileiros denotaram a necessidade pela sua adaptação em diversos aspectos, incluindo-se o processo decisório envolvido, que foi abordado pelo presente trabalho. A solução para o problema envolveu a aplicação e a avaliação do método Support Vector Machines, e é descrita em detalhes. / The huge growth of the Internet has been occurring since 90s with the arrival of the internet service providers. One important reason is the good acceptance and wide dissemination of the Web. The main problem that affects its scalability and usage is the organization and classification of its content. The current search engines make possible the localization of pages in the Web by means of a lexical comparison among sets of words and the hypertexts contents. In order to find contents that express concepts or object, such as products for sale in electronic commerce sites such mechanisms are inefficient. The proposition of the Semantic Web was announced in 2000 for this purpose, envisioning the establishment of new standards for formal contents representation in the Web pages. With its implementation, whose deadline was initially stated for ten years, it will be possible to express concepts in hypertexts contents, that will fully represent objects classified into an ontology, making possible the use of knowledge based systems implemented by intelligent softwares agents. The DEEPSIA project was conceived as a solution centered in the purchaser, instead of current Market Places, in order to solve the problem of finding Web pages with products for sale description, making use of methods of text classification, with k-NN and C4.5 algorithms, to support the decision problem to be solved by an specific agent designed, the Crawler Agent. The tests of the system in Brazilian sites have denoted the necessity for its adaptation in many aspects, including the involved decision process, which was focused in present work. The solution for the problem includes the application and evaluation of the Support Vector Machines method, and it is described in detail.