A ascensão de um grande número de pessoas em países em desenvolvimento para a classe média, no inicio do século XXI, aliado ao movimento político para transferência de base energética para os biocombustíveis vêm aumentando a pressão sobre os preços das commodities agrícolas e apresentando novas oportunidades e cenários administrativos para os produtores agrícolas dessas commodities, em especial aquelas que podem se diversificar em muitos subprodutos para atender diferentes mercados, como o de alimentos, químico, têxtil e de energia. Nesse novo ambiente os produtores podem se beneficiar dividindo adequadamente a produção entre os diferentes subprodutos, definindo o melhor momento para a comercialização através de estoques, e ainda controlar sua exposição ao risco através de posições no mercado de derivativos. A literatura atual pouco aborda o tema da diversificação e seu impacto nas decisões de produção e comercialização agrícola e portanto essa tese tem o objetivo de propor um modelo de decisão fundado na teoria de seleção de portfólios capaz de decidir a divisão da produção entre diversos subprodutos, as proporções a serem estocadas e o momento mais adequado para a comercialização e por fim as posições em contratos futuros para fins de proteção ou hedge. Adicionalmente essa tese busca propor que esse modelo seja capaz de lidar com incerteza em parâmetros, em especial parâmetros que provocam alto impacto nos resultados, como é o caso dos retornos previstos no futuro. Como uma terceira contribuição, esse trabalho busca ainda propor um modelo de previsão de preços mais sofisticado que possa ser aplicado a commodities agrícolas, em especial um modelo híbrido ou hierárquico, composto de dois modelos, um primeiro modelo fundado sob a teoria de processos estocásticos e do Filtro de Kalman e um segundo modelo, para refinar os resultados do primeiro modelo de previsão, baseado na teoria de redes neurais, com a finalidade de considerar variáveis exógenas. O modelo híbrido de previsão de preços foi testado com dados reais do mercado sucroalcooleiro brasileiro e indiano, gerando resultados promissores, enquanto o modelo de decisão de parâmetros de produção, comercialização, estocagem e hedge se mostrou uma ferramenta útil para suporte a decisão após ser testado com dados reais do mercado sucroalcooleiro brasileiro e do mercado de milho, etanol e biodiesel norte-americano. / The rise of a large number of people in developing countries for the middle class at the beginning of the century, combined with the political movement to transfer the energy base for biofuels has been increasing pressure on prices of agricultural commodities and presenting new opportunities and administrative scenarios for agricultural producers of these commodities, especially those who may diversify into many products to meet different markets such as food, chemicals, textiles and energy. In this new environment producers can achieve benefits properly dividing production between different products, setting the best time to market through inventories, and still control their risk exposure through positions in the derivatives market. The literature poorly addresses the issue of diversification and its impact on agricultural production and commercialization decisions and therefore this thesis aims to propose a decision model based on the theory of portfolio selection able to decide the division of production between different products, the proportions to be stored and timing for marketing and finally the positions in futures contracts to hedge. Additionally this thesis attempts to propose that this model is capable of dealing with uncertainty in parameters, especially parameters that cause high impact on the results, as is the case of expected returns in the future. As a third contribution this paper seeks to also propose a model more sophisticated to forecast prices that can be applied to agricultural commodities, especially a hybrid or hierarchical model, composed of two models, a first one based on the theory of stochastic processes and Kalman filter and a second one to refine the results of the first prediction model, based on the theory of neural networks in order to consider the exogenous variables. The hybrid model for forecasting prices has been tested with real data from the Brazilian and Indian sugar ethanol market, generating promising results, while the decision model parameters of production, commercialization, storage and hedge proved a useful tool for decision support after being tested with real data from Brazilian sugar ethanol market and the corn, ethanol and biodiesel market in U.S.A.

Mapas fotogramétricos são de extrema importância para monitorar grandes áreas periodicamente. Alguns exemplos são: monitoramento de florestas, plantas invasivas, crescimento urbano, etc. Estes mapas são comumente construídos utilizando imagens de satélites ou aviões. Para se obter um mapa com proporções reais, uma operação de distorção destas imagens é realizada utilizando informações fornecidas por Pontos de Controle em Solo e triangulando features naturais das imagens ou utilizando um outro mapa conhecido a priori. A utilização de VANTs (Veículos Aéreos Não Tripulados) mostra-se uma solução mais segura quando comparada a um avião devido a não existência de tripulação. É uma solução mais flexível quando comparada a satélites, pois um VANT pode voar algumas horas ou mesmo minutos após um vôo anterior, enquanto um satélite estará disponível novamente após alguns dias na mesma área. Algumas partes do mapa podem não ser visíveis devido a nuvens e o VANT pode sobrevoar a área novamente para recuperar estas partes (sobrevoaria abaixo das nuvens caso necessário). Um método de fusão sensorial estocástico é proposto e combina técnicas de Visão Computacional, sensores inerciais e GPS a fim de estimar um mapa esparso tridimensional e a posição do VANT simultaneamente utilizando a técnica conhecida como SLAM (Simultaneous Localization and Mapping). O mapa completo é gerado projetando as imagens no mapa esparso. A principal vantagem deste método é que o mapa é construído sem conhecimento a priori do terreno. As principais contribuições deste trabalho são: a integração de técnicas de SLAM na área de Aerofotogrametria e o desenvolvimento de um método que realiza o mapeamento 3D sem o uso de conhecimento a priori do terreno. / Photogrammetric maps are of extreme importance in order to monitor large areas periodically. Some examples are: monitoring of forests, invasive plants, urban growth, etc. These maps are commonly built using images from satellites or planes. In order to obtain a map with real proportions, an operation of distortion of these images is realized using information provided by Ground Control Points and triangulating natural features in the scene or using another a priori known map. The utilization of an Unmanned Aerial Vehicle (UAV) provides a safer solution when compared to a plane mainly due to the non existence of a crew. It is also a more flexible solution when compared to satellites because an UAV can fly again some hours or even minutes after a previous flight, while a satellite will be available in some days for the same area. Some parts of the map might not be visible because of clouds and the UAV needs to fly again to recover these parts (flying below the clouds if necessary). A stochastic sensor fusion method is proposed that combines computational vision techniques, inertial sensors and GPS in order to estimate both the three dimensional sparse map and the UAV position using the technique known as SLAM (Simultaneous Localization and Mapping). The complete map is generated projecting the images into the sparse map. The main advantage of this method is that the map is constructed without the use of a priori knowledge of the terrain. The main contributions of this work are: the integration of SLAM techniques into the Aerophotogrammetry field and the development of a method that can realize a 3D mapping without the use of a priori knowledge of the terrain.

This thesis introduces novel ideas in subsurface reservoir model calibration known as History Matching in the reservoir engineering community. The target of history matching is to mimic historical pressure and production data from the producing wells with the output from the reservoir simulator for the sole purpose of reducing uncertainty from such models and improving confidence in production forecast. Ensemble based methods such as the Ensemble Kalman Filter (EnKF) and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) as been proposed for history matching in literature. EnKF/ES-MDA is a Monte Carlo ensemble nature filter where the representation of the covariance is located at the mean of the ensemble of the distribution instead of the uncertain true model. In EnKF/ES-MDA calculation of the gradients is not required, and the mean of the ensemble of the realisations provides the best estimates with the ensemble on its own estimating the probability density. However, because of the inherent assumptions of linearity and Gaussianity of petrophysical properties distribution, EnKF/ES-MDA does not provide an acceptable history-match and characterisation of uncertainty when tasked with calibrating reservoir models with channel like structures. One of the novel methods introduced in this thesis combines a successive parameter and shape reconstruction using level set functions (EnKF/ES-MDA-level set) where the spatial permeability fields' indicator functions are transformed into signed distances. These signed distances functions (better suited to the Gaussian requirement of EnKF/ES-MDA) are then updated during the EnKF/ES-MDA inversion. The method outperforms standard EnKF/ES-MDA in retaining geological realism of channels during and after history matching and also yielded lower Root-Mean-Square function (RMS) as compared to the standard EnKF/ES-MDA. To improve on the petrophysical reconstruction attained with the EnKF/ES-MDA-level set technique, a novel parametrisation incorporating an unsupervised machine learning method for the recovery of the permeability and porosity field is developed. The permeability and porosity fields are posed as a sparse field recovery problem and a novel SELE (Sparsity-Ensemble optimization-Level-set Ensemble optimisation) approach is proposed for the history matching. In SELE some realisations are learned using the K-means clustering Singular Value Decomposition (K-SVD) to generate an overcomplete codebook or dictionary. This dictionary is combined with Orthogonal Matching Pursuit (OMP) to ease the ill-posed nature of the production data inversion, converting our permeability/porosity field into a sparse domain. SELE enforces prior structural information on the model during the history matching and reduces the computational complexity of the Kalman gain matrix, leading to faster attainment of the minimum of the cost function value. From the results shown in the thesis; SELE outperforms conventional EnKF/ES-MDA in matching the historical production data, evident in the lower RMS value and a high geological realism/similarity to the true reservoir model.

The aim of this thesis is to show that news analytics data can be utilised to improve the predictive ability of existing models that have useful roles in a variety of financial applications. The modified models are computationally efficient and perform far better than the existing ones. The new modified models offer a reasonable compromise between increased model complexity and prediction accuracy. I have investigated the impact of news sentiment on volatility of stock returns. The GARCH model is one of the most common models used for predicting asset price volatility from the return time series. In this research, I have considered quantified news sentiment as a second source of information and its impact on the movement of asset prices, which is used together with the asset time series data to predict the volatility of asset price returns. Comprehensive numerical experiments demonstrate that the new proposed volatility models provide superior prediction than the "plain vanilla" GARCH, TGARCH and EGARCH models. This research presents evidence that including news sentiment term as an exogenous variable in the GARCH framework improves the prediction power of the model. The analysis of this study suggested that the use of an exponential decay function is good when the news flow is frequent, whereas the Hill decay function is good only when there are scheduled announcements. The numerical results vindicate some recent findings regarding the utility of news sentiment as a predictor of volatility, and also vindicate the utility of the new models combining the proxies for past news sentiments and the past asset price returns. The empirical analysis suggested that news augmented GARCH models can be very useful in estimating VaR and implementing risk management strategies. Another direction of my research is introducing a new approach to construct a commodity futures pricing model. This study proposed a new method of incorporating macroeconomic news into a predictive model for forecasting prices of crude oil futures contracts. Since these futures contracts are iii iv more liquid than the underlying commodity itself, accurate forecasting of their prices is of great value to multiple categories of market participants. The Kalman filtering framework for forecasting arbitrage-free (futures) prices was utilized, and it is assumed that the volatility of oil (futures) price is influenced by macroeconomic news. The impact of quantified news sentiment on the price volatility is modelled through a parametrized, nonlinear functional map. This approach is motivated by the successful use of a similar model structure in my earlier work, for predicting individual stock volatility using stock-specific news. Numerical experiments with real data illustrate that this new model performs better than the one factor model in terms of accuracy of predictive power as well as goodness of fit to the data. The proposed model structure for incorporating macroeconomic news together with historical (market) data is novel and improves the accuracy of price prediction quite significantly.

Esta Tese explora o Processo de Cox quando sua intensidade pertence a uma família de difusões afim. A forma da funçâo densidade de Probabilidade do Processo de Cox é obtida quando a intensidade é descrita por uma difusão fim d-dimensional arbitrária. Analisa-se também o acoplamento e convergência para o Processo de Cox com intensidade afim. Para ilustrar assume-se que a intensidade do Processo é governada por uma difusão de Feller e resultados mais detalhados são obtidos. Adicionalmente, os parâmetros da intensidade do Processo são estimados por meio do Filtro de Kalman conjugado com o estimador de Quase-Máxima Verossimilhança. / This Thesis deals with the Cox Process when its intensity belongs to a family of affine diffusions. The form of the probability density function of the Cox process is obtained when the density is described by an arbitrary d-dimensional affine diffusion. Coupling and convergence results are also addressed for a general Cox process with affine intensity. We adopted the Feller diffusion for driving the underlying intensity of the Cox Process to illustrate our results. Additionally the parameters of the underlying intensity processes are estimated by means of the Kalman Filter in conjunction with Quasi-Maximum Likelihood estimation.

The thesis focuses on the yield curve modeling using the dynamic Nelson-Siegel approach. We propose two models of the yield curve and apply them on four currency areas - USD, EUR, GBP and CZK. At first, we distill the entire yield curve into the time-varying level, slope and curvature factors and estimate the parameters for individual currencies. Subsequently, we build a novel model investigating to what extent unobservable factors of the dynamic Nelson-Siegel model are determined by macroeconomic drivers. The main contribution of this thesis resides in the innovative approach to yield curve modeling with the application of advanced technical tools. Our primary objective was to increase the accuracy and the estimation power of the model. Moreover, we applied both models across different currency areas, which enabled us to compare the dynamics of the yield curves as well as the influence of the macroeconomic drivers. Interestingly, the results proved that both models we developed not only demonstrate strong validity, but also produce powerful estimates across all examined currencies. In addition, the incorporated macroeconomic factors contributed to reach higher precision of the modeling. JEL Classification: C51, C53, G17 Keywords: Nelson-Siegel, Kalman filter, Kalman smoother, Stace space formulation...

Title: Methods of dynamical analysis of portfolio composition Author: Ivana Meňhartová Department: Department of Probability and Mathematical Statistics Supervisor: Mgr. Tomáš Hanzák, KPMS, MFF UK Abstract: In the presented thesis we study methods used for dynamic analysis of portfolio based on it's revenues. The thesis focuses on Kalman filter and local- ly weighted regression as two basic methods for dynamic analysis. It describes in detail theory for these methods as well as their utilization and it discusses their proper settings. Practical applications of both methods on artificial data and real data from Prague stock-exchange are presented. Using artificial data we demonstrate practical importance of Kalman filter's assumptions. Afterwards we introduce term multicolinearity as a possible complication to real data applicati- ons. At the end of the thesis we compare results and usage of both methods and we introduce possibility of enhancing Kalman filter by projection of estimations or by CUSUM tests (change detection tests). Keywords: Kalman filter, locally weighted regression, multicollinearity, CUSUM test

A Tomografia por Impedância Elétrica (TIE) aplica-se no monitoramento contínuo e detecção de alterações pulmonares sérias. Principalmente no ambiente das unidades de terapia intensiva (UTI) para a avaliação das condições do paciente em estado crítico submetido à ventilação artificial sem que seja necessário retirar o paciente da UTI e dos diferentes instrumentos de assistência à vida. A técnica permite estimar alterações de impedância nos pulmões. O objetivo deste trabalho é diminuir o erro numérico num algoritmo desenvolvido para TIE, utilizando o Filtro Estendido de Kalman. Especificamente, esse algoritmo aplica-se na a obtenção de imagens dos pulmões do corpo humano. Para realizar tal objetivo foram projetados phantoms compostos por um recipiente circular com solução salina, dentro do qual é colado um objeto cilíndrico de vidro e 32 eletrodos localizados no contorno do recipiente. Foi desenvolvido um algoritmo em linguagem C, utilizando a técnica de Filtro Estendido de Kalman para estimação de parâmetros de um modelo de elementos finitos. Foram implementados o procedimento de renumeração da malha de elementos finitos, com o objetivo de obter uma matriz de condutividade de banda, e o procedimento de melhoramento iterativo da solução para diminuir o erro numérico de soluções de sistemas lineares. Foram comparados dois algoritmos, um utilizando matriz de condutividade esparsa Alg Esparsa e outro com matriz de condutividade de banda limitada, obtida por renumeração da malha, e aplicando refinamento iterativo na solução de sistemas lineares, Alg RRI. Obtiveram-se melhores estimativas de impedância e uma melhor estabilidade do algoritmo do Filtro de Kalman com o algoritmo Alg RRI. O erro numérico na inversa da matriz de condutividade e o erro numérico na matriz de sensibilidade são significativamente menores quando se utiliza renumeração da malha e refinamento iterativo da solução de sistemas lineares. A redução de erro numérico nestas matrizes leva a melhores imagens. / The Electrical Impedance Tomography (EIT) is applied for the continuing monitoring and detection of serious pulmonar change. It may be used in intensive care units for the evaluation of patient condition in critical state submitted to artificial ventilation. It is not necessary to leave the intensive care unit and disconnect life assist devices. This technique allow estimation of impedance distribution on a cross section of the thorax. The main of this work is the reduction of numerical error in the Kalman Filter for EIT image estimation. Specifically, this algorithm may be applied for estimating lunge impedance distribution. To obtain this objective a phantom was developed. It is constituted by a cilindrical container with saline solution, a glass object is glued to the container, and 32 electrodes attached to the container wall. An algorithm in C language, using the Extended Kalman Filter technique was developed, it is a parameter estimation procedure. Mesh renumbering, to obtain a band limited conductivity matrix and the iterative improvement of the solution of linear systems were implemented. The estimation of impedance distribution was performed. Two different algorithms were considered. One algorithm uses a sparse conductivity matrix, Alg sparse. Another algorithm uses a band limited conductivity matrix and iterative refinement of the solution of linear systems, Alg RRI. Better impedance estimation and better stability of Kalman Filter algorithm was obtained using Alg RRI. The numerical error on the inverse of the conductivity matrix and the numerical error on the sensitivity matrix were smaller on algorithm Alg RRI. The numerical error reduction on the conductivity matrix and on the sensitivity matrix produced better images.

Rastreamento visual em sequências de imagens tem sido muito estudado nos últimos 30 anos devido às inúmeras aplicações que possui em sistemas de visão computacional em tempo real; entretanto, poucos são os algoritmos disponíveis para que tal tarefa seja realizada com sucesso. Esta dissertação apresenta um método e uma arquitetura eficazes e eficientes para rastrear jogadores em jogos de futebol. A entrada do sistema consiste de vídeos capturados por câmeras estáticas instaladas em estádios de futebol. A saída é a trajetória descrita pelo jogador durante uma partida de futebol, dada no plano de imagem. O sistema possui dois estágios de processamento: inicialização e rastreamento. A inicialização do sistema é crítica no desempenho do rastreador e seu objetivo consiste em produzir uma estimativa aproximada da configuração e características de cada alvo, a qual é usada como uma estimativa inicial do estado pelo rastreador. O sistema de rastreamento utiliza Filtros de Kalman para modelar o contorno, posição e velocidade dos jogadores. Resultados são apresentados usando dados reais. Avaliações quantitativas são fornecidas e o sistema proposto é comparado com outro sistema correlato. Os experimentos mostram que o sistema proposto apresenta resultados bastante promissores. / Visual tracking in image sequences has been extensively studied in the last 30 years because of the many applications it has in real-time computer vision systems; however, there are few algorithms available for this task so that it is performed successfully. This work presents an effective and efficient system architecture and method to track players in soccer games. The system input consists of videos captured by static cameras installed in soccer stadiums. The output is the trajectory described by the player during a soccer match, given in the image plane. The system comprises two processing stages: initialization and tracking. The system startup is critical in the tracking performance and its goal is to produce a rough estimate of the configuration and characteristics of each target, which is used as an initial estimate of the state by the visual tracker. The tracking system uses Kalman filters to model the shape, position and speed of the players. Results are presented using real data. Quantitative assessments are provided and the proposed system is compared with related systems. The experiments show that our system can achieve very promising results.

O presente trabalho trata do desenvolvimento de um sistema de sensoriamento de orientação utilizando sensores inerciais de baixo custo, de tecnologia MicroElectroMechanical Systems, MEMS, que apresentam altas taxas de ruído. Assim, é realizada a filtragem e fusão dos dados dos sensores para obtenção de uma estimativa confiável, com a aplicação do filtro de Kalman estendido. O sistema é utilizado para a navegação e controle em um veículo aquático de superfície autônomo. No desenvolvimento do trabalho são investigados os princípios da navegação inercial, da representação da orientação e os sistemas de coordenadas envolvidos, apresentando o método por ângulos de Euler, quatérnios e DCM e o procedimento de atualização conforme a variação da orientação. O sistema desenvolvido foi testado em bancada e em um barco com formato de trimarã construído no Laboratório de Controle e Eletrônica de Potência, na Escola de Engenharia de São Carlos, mostrando os resultados dos testes realizados navegando em uma represa, obtendo resultados satisfatórios para essa aplicação. É mostrado também o comportamento dinâmico dos veículos aquáticos de superfície através do estudo da dinâmica de corpos rígidos. / This work describes the development of an orientation sensing system composed of low cost inertial sensors with MicroElectroMechanical Systems (MEMS) technology, which presents high noise levels. Thus, filtering and sensor\'s measurements fusion is done in order to achieve a reliable estimation, trough an extended Kalman filter. The system is used for navigation and control of an autonomous aquatic surface vehicle. In this work, the principles of inertial navigation, orientation representation as well as the coordinate frames involved are investigated, presenting the methods trough Euler angles, quaternions and DCM, and the update proceeding according to the orientation changes. The developed system was tested in the lab and on a trimaran shaped vessel navigating on a dam, wich was developed in the Control and Power Electronics Laboratory at the São Carlos School of Engineering, achieving satisfactory results for this application. It is also shown the dynamic behavior of the surface aquatic vehicles, using rigid-body dynamics.