Orientadores: Nancy Lopes Garcia, Ronaldo Dias / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-18T04:43:13Z (GMT). No. of bitstreams: 1 Ludwig_GuilhermeVieiraNunes_M.pdf: 4540322 bytes, checksum: c767b4a6c7cd883a70e9ebbc33fe04ec (MD5) Previous issue date: 2011 / Resumo: O objetivo desta dissertação é desenvolver estimadores não paramétricos para a função de covariância de dados funcionais agregados, que consistem em combinações lineares de dados funcionais que não podem ser observados separadamente. Estes métodos devem ser capazes de produzir estimativas que separem a covariância típica de cada uma das subpopulações que geram os dados, e que sejam funções não negativas definidas. Sob estas restrições, foi definida uma classe de funções de covariância não estacionarias, à qual resultados da teoria de estimação de covariância de processos estacionários podem ser estendidos. Os métodos desenvolvidos foram ilustrados com a aplicação em dois problemas reais: a estimação do perfil de consumidores de energia elétrica, em função do tempo, e a estimação da transmitância de substâncias puras em espectroscopia de infravermelho, através da inspeção de misturas, em função do espectro da luz / Abstract: The goal of this dissertation is to develop nonparametric estimators for the covariance function of aggregated functional data, which consists into linear combinations of functional data that cannot be sampled separately. Such methods must be able to produce estimates that not only separate the typical covariance of the subpopulations composing the data, but also be nonnegative definite functions. Under these restrictions, a class of nonstationary covariance functions was proposed, to which stationary processes' covariance function estimation results can be readily extended. The developed methods were illustrated with an application to two real problems: the estimation of electric energy consumers' profiles, as a function of the time of the day, and the estimation of the transmittance of pure substances in infrared spectroscopy, while inspecting mixtures of them, as a function of light spectrum / Mestrado / Estatistica Não Parametrica / Mestre em Estatística

Orientador: Ronaldo Dias / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica / Made available in DSpace on 2018-08-13T14:28:48Z (GMT). No. of bitstreams: 1 Gomes_JoseCleltoBarros_M.pdf: 1798618 bytes, checksum: db671b29b83f0321e8dbc03c5af42cde (MD5) Previous issue date: 2009 / Resumo: O desafio na modelagem de processos espaciais está na descrição da estrutura de covariância do fenômeno sob estudo. Um estimador não-paramétrico da função de covariância foi construído de forma a usar combinações lineares de funções B-splines. Estas bases são usadas com muita frequência na literatura graças ao seu suporte compacto e a computação tão rápida quanto a habilidade de criar aproximações suaves e apropriadas. Verificouse que a função de covariância estimada era definida positiva por meio do teorema de Bochner. Para a estimação da função de covariância foi implementado um algoritmo que fornece um procedimento completamente automático baseado no número de funções bases. Então foram realizados estudos numéricos que evidenciaram que assintoticamente o procedimento é consistente, enquanto que para pequenas amostras deve-se considerar as restrições das funções de covariância. As funções de covariâncias usadas na estimação foram as de exponencial potência, gaussiana, cúbica, esférica, quadrática racional, ondular e família de Matérn. Foram estimadas ainda covariâncias encaixadas. Simulações foram realizadas também a fim de verificar o comportamento da distribuição da afinidade. As estimativas apresentaram-se satisfatórias / Abstract: The challenge in modeling of spatials processes is in description of the framework of covariance of the phenomenon about study. The estimation of covariance functions was done using a nonparametric linear combinations of basis functions B-splines. These bases are used frequently in literature thanks to its compact support and fast computing as the ability to create smooth and appropriate approaches There was positive definiteness of the estimator proposed by the Bochner's theorem. For the estimation of the covariance functions was implemented an algorithm that provides a fully automated procedure based on the number of basis functions. Then numerical studies were performed that showed that the procedure is consistent assynthotically. While for small samples should consider the restrictions of the covariance functions, so the process of optimization was non-linear optimization with restrictions. The following covariance functions were used in estimating: powered exponential, Gaussian, cubic, spherical, rational quadratic and Matérn family. Nested covariance funtions still were estimated. Simulations were also performed to verify the behavior of affinity and affinity partial, which measures how good is the true function of the estimated function. Estimates showed satisfactory / Mestrado / Mestre em Estatística

Orientador: Nancy Lopes Garcia / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-22T12:21:05Z (GMT). No. of bitstreams: 1 Lenzi_Amanda_M.pdf: 1978923 bytes, checksum: 093900c4de8727a9c79d6afdfb0e3bd4 (MD5) Previous issue date: 2013 / Resumo: Neste trabalho tratamos de um problema de dados funcionais agregados, isto é, combinações lineares de curvas aleatórias que não podem ser observadas individualmente. A análise de curvas de carga de transformadores elétricos em linha de distribuição é uma situação onde tais dados são encontrados. O conjunto de dados consiste de diversas curvas agregadas; assumimos que cada curva individual é a realização de um processo Gaussiano com curva média que é modelada através da expansão em bases B-splines. Além disso, assumimos que os coeficientes também são desconhecidos e temos somente uma estimativa de tais números. Nosso objetivo é utilizar os valores aproximados desses coeficientes, além das curvas agregadas, para estimar o valor real dos coeficientes, a curva típica de cada subpopulação e parâmetros de variância. Para este fim, diferentemente de trabalhos anteriores sobre o tema, propomos a utilização de um modelo de efeitos aleatórios / Abstract: In this paper, we deal with a problem of aggregated functional data, i.e. linear combinations of random curves, which cannot be seen individually. The analysis of load curves of electrical transformers in the distribution line is a situation where those data are found. The data set consists of several aggregated curves; we assume that each individual curve is the realization of a Gaussian process with the mean curve modeled through the expansion in B-splines basis. Furthermore, we assume that the coefficients are also unknown and we have only an estimate of such numbers. Our goal is to use the approximate coefficients and the aggregated curve data to estimate the true coefficients, the typical curve of each subpopulation and variance parameters. For this purpose, unlike previous works on the subject, we propose using a random effects model / Mestrado / Estatistica / Mestra em Estatística

Orientadores: Anamaria Gomide, Jorge Stolfi / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-19T08:33:31Z (GMT). No. of bitstreams: 1 Rodrigues_ElisadeCassiaSilva_M.pdf: 2606848 bytes, checksum: 5290f0c06ecad44b5b23aa69a8920245 (MD5) Previous issue date: 2011 / Resumo: Métodos de deformação são importantes em áreas como modelagem geométrica e animação computacional. Na biologia, a modelagem de forma, crescimento, movimento e patologias de organismos microscópicos vivos ou células requerem deformações suaves, as quais são essencialmente 2D com poucas mudanças de profundidade. Nesta dissertação, apresentamos um método de deformação do espaço 2.5D suave. O modelo 3D do organismo é modificado deformando uma grade de controle formada por prismas que o envolve. A técnica de interpolação spline é usada para satisfazer o requisito de suavidade ('C POT. 1'). Implementamos esse método em um editor que torna possível definir e modificar a deformação de uma forma amigável usando o mouse. Os resultados experimentais mostram que o método é simples e efetivo / Abstract: Shape deformation methods are important in such fields as geometric modeling and computer animation. In biology, the modeling of shape, growth, movement and pathologies of living microscopic organisms or cells requires smooth deformations, which are essentially 2D with little change in depth. In this master thesis, we present a smooth 2.5D space deformation method. The 3D model of the organism is modified by deforming an enclosing control grid of prisms. Spline interpolation is used to satisfy the smoothness ('C POT. 1') requirement. We implemented this method in an editor which makes it possible to define and modify the deformation with the mouse in a user-friendly way. The experimental results show that the method is simple and effective / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

Avec l’arrivée de l’Analyse IsoGéométrique (IGA), le calcul de coque est devenu possible en utilisant la géométrie exacte pour des maillages grossiers. Pour cela, les polynômes de Lagrange sont remplacés pour l’interpolation par des fonctions NURBS (technologie la plus courante en conception assistée par ordinateur). De plus, ces fonctions possèdent une continuité supérieure ce qui offre une meilleure précision qu’un calcul éléments finis à nombre de degrés de liberté égal. L’IGA a déjà été développée pour les formulations coques. Elle n’a été cependant que très peu étudiée pour les modèles massifs coque. Pourtant, cette deuxième approche est très utilisée par l’ingénieur car elle permet de calculer des structures minces à l’aide d’éléments continus 3D, c’est-à-dire en faisant intervenir uniquement des inconnues en déplacements. La difficulté en calcul de coque est de faire face au verrouillage qui conduit à une forte dégradation de la convergence de la solution. Le cadre NURBS ne permet pas lui-même de résoudre ce problème. La meilleure efficacité de l’approximation NURBS ne peut donc être atteinte sans le développement de techniques particulières pour supprimer le verrouillage. C’est le but de cette thèse dans le cadre des éléments massifs coque. Le premier travail a consisté, sur un problème de poutre courbe, à étendre les méthodes sans verrouillage habituelles au contexte NURBS. Deux nouvelles stratégies ont alors été développées pour les NURBS : la première est basée sur une technique d’intégration réduite tandis que la seconde fait appel à une projection B-bar. Le formalisme général des méthodes B-bar semblant plus adapté, c’est celui-ci que nous avons développé ensuite pour les éléments massifs coque. Plus précisément, nous avons mis en place une formulation mixte de laquelle nous avons pu dériver la projection B-bar équivalente. Cette démarche constitue d’un point de vue théorique le résultat principal du travail : une méthode systématique pour construire une projection B-bar consistante est de passer par une formulation mixte. D’un point de vue mise en œuvre, l’idée principale pour traiter le verrouillage des éléments massifs coque a été de modifier l’interpolation de la moyenne dans l’épaisseur de la coque des composantes du tenseur des contraintes. Un contrôle de hourglass a aussi été ajouté pour stabiliser l’élément dans certaines situations. L’élément obtenu est de bonne qualité pour une interpolation de bas degrés et des maillages grossiers : la version quadratique semble plus précise que des éléments standards NURBS de degré 4. La méthode proposée conduit à une matrice de rigidité globale de petite taille mais pleine. Ce problème est inhérent aux NURBS. Il a pu être limité ici en utilisant une procédure de type moindres carrés locaux pour approcher la projection B-bar. Finalement, l’élément mixte a été étendu avec succès en non linéaire géométrique ce qui témoigne du potentiel de la méthode pour mener des simulations complexes. / With the introduction of IsoGeometric Analysis (IGA), the calculation of shell has become possible using the exact geometry for coarse meshes. In order to that, Lagrange polynomials are replaced by NURBS functions, the most commonly used technology in Computer-Aided Design, to perform the analysis. In addition, NURBS functions have a higher order of continuity, which leads to higher per-degree-of-freedom accuracy of the shell solution than with classical Finite Elements Analysis (FEA). IGA has now been widely applied in shell formulations. Nevertheless, it has still rarely been studied in the context of solid-shell models. This second shell approach is, however, very useful for engineers, since it enables to calculate thin structures using 3D solid elements, i.e. involving only displacements as degrees of freedom. The difficulty in shell analysis is to deal with locking which highly deteriorates the convergence of the solution. The NURBS framework does not enable to solve the problem directly. Then, to really benefit from NURBS in shells, specific strategies need to be implemented to answer the locking issue. This is the goal of the thesis in the context of solid-shell elements. The first work has consisted, on a curved beam problem, in extending the locking-free methods usually encountered in FEA to the NURBS context. The study resulted in the development of two new strategies for NURBS: the first one is based on a selective reduced integration technique and the second one makes use of a B-bar projection. The global formalism offered by the B-bar method appearing more suitable for NURBS, it has then been investigated for solid-shell elements. More precisely, a mixed formulation has first been elaborated from which, it has been possible to derive the equivalent B-bar projection. From a theoretical point of view, this strategy constitutes the most important result of this work: a systematic method to construct a consistent B-bar projection is to write a mixed formulation. With regards to the implementation, the main idea to treat locking of the solid-shell elements has been to modify the average of the strain and stress components across the thickness of the shell. Hourglass control has also been added to stabilize the element in particular situations. The resulting element is of good quality for low order approximations and coarse meshes: the quadratic version seems to be more accurate than basic NURBS elements of order 4. The proposed method leads to a global stiffness matrix of small size but full. This problem is inherent to NURBS functions. It has been limited here by using a local least squares procedure to approach the B-bar projection. Finally, the mixed element has been successfully extended to geometric non-linearity which reflects the ability of the methodology to be used in complex simulations.

Cette thèse présente un algorithme automatique pour la construction d’un modèle NURBS volumique à partir d’un modèle représenté par ses bords (maillages ou splines). Ce type de modèle est indispensable dans le cadre de l’analyse isogéométrique utilisant les NURBS comme fonctions de forme. Le point d’entrée de l’algorithme est une triangulation du bord du modèle. Après deux étapes de décomposition, le modèle est approché par un polycube. Ensuite un paramétrage surfacique entre le bord du modèle et celui du polycube est établi en calculant un paramétrage global aligné à un champ de direction interpolant les directions de courbure principales du modèle. Finalement, le paramétrage volumique est obtenu en se basant sur ce paramétrage surfacique. Dans le contexte des études paramétriques basées sur des paramètres de formes géométriques, cette méthode peut être appliquée aux techniques de réduction de modèles pour obtenir la même représentation pour des objets ayant différentes géométries mais la même topologie. / This thesis presents an effective method to automatically construct trivariate tensor-product spline models of complicated geometry and arbitrary topology. Our method takes as input a solid model defined by its triangulated boundary. Using cuboid decomposition, an initial polycube approximating the input boundary mesh is built. This polycube serves as the parametric domain of the tensor-product spline representation required for isogeometric analysis. The polycube's nodes and arcs decompose the input model locally into quadrangular patches, and globally into hexahedral domains. Using aligned global parameterization, the nodes are re-positioned and the arcs are re-routed across the surface in a way to achieve low overall patch distortion, and alignment to principal curvature directions and sharp features. The optimization process is based on one of the main contributions of this thesis: a novel way to design cross fields with topological (i.e., imposed singularities) and geometrical (i.e., imposed directions) constraints by solving only sparse linear systems. Based on the optimized polycube and parameterization, compatible B-spline boundary surfaces are reconstructed. Finally, the interior volumetric parameterization is computed using Coon's interpolation and the B-spline surfaces as boundary conditions. This method can be applied to reduced order modeling for parametric studies based on geometrical parameters. For models with the same topology but different geometries, this method allows to have the same representation: i.e., meshes (or parameterizations) with the same topology.

In this thesis the main object of our concern is a Pythagorean hodograph B- spline curve. We recall notions of both Pythagorean hodograph (PH) curves and B-spline functions separately first. Then we put these fields together to generalize PH curves to their B-spline instances. We encapsulate these curves in various spaces under one algebraic structure using the formalism of Clifford algebras. We consider both Euclidean and Minkowski spaces of lower dimensions which give room for real applications and use of these curves. We support our results by giving numerous examples. 1

Molts sistemes mecànics existents tenen un comportament vibratori funcionalment perceptible, que es posa de manifest enfront d'excitacions transitòries. Normalment, les vibracions generades segueixen presents després del transitori (vibracions residuals), i poden provocar efectes negatius en la funció de disseny del mecanisme.El mètode que es proposa en aquesta tesi té com a objectiu principal la síntesi de lleis de moviment per reduir les vibracions residuals. Addicionalment, els senyals generats permeten complir dues condicions definides per l'usuari (anomenats requeriments funcionals). El mètode es fonamenta en la relació existent entre el contingut freqüencial d'un senyal transitori, i la vibració residual generada, segons sigui l'esmorteïment del sistema. Basat en aquesta relació, i aprofitant les propietats de la transformada de Fourier, es proposa la generació de lleis de moviment per convolució temporal de polsos. Aquestes resulten formades per trams concatenats de polinomis algebraics, cosa que facilita la seva implementació en entorns numèrics per mitjà de corbes B-spline. / Many mechanical systems have a vibratory behavior, functionally noticeable, which can be raised when transient excitations happen. Usually, such generated vibrations remain in the system after this transient (residual vibrations), and may imply negative effects in the mechanism's intended function.The method proposed in this thesis has as main objective, the synthesis of excitation signals for mechanical systems in order to reduce residual vibrations. In addition, generated signals are able to achieve two conditions defined by the user related to function of the mechanism (called functional requirements). This method is based on the relationship between the frequency contents of the transient signal and the residual vibration generated, depending on the system damping. From this relation, and taking advantage of the Fourier transform properties, motion laws are generated through the pulses' time convolution. Resultant laws are made up of algebraic polynomial pieces linked together, which makes them very suitable for implementation with numerical calculus through B-spline curves.

La segmentation d'image par modèles déformables est une méthode permettant de localiser les frontières d'un objet. Dans le cas d'images difficiles à segmenter en raison de la présence de bruit ou d'un manque d'information, l'introduction de connaissance a priori dans le modèle déformable améliore la segmentation. Ces cas difficiles sont fréquents dans l'imagerie du vivant, où les applications peuvent concerner le traitement d'une grande quantité de donnée. Il est alors nécessaire d'utiliser une méthode de traitement robuste et rapide. Cette problématique nous a amené à proposer une régularisation locale du modèle déformable. Pour ce faire, nous reprenons le concept du contour actif en proposant un nouveau schéma de régularisation. Celle-ci est désormais effectuée via un filtrage RII des déplacements à chaque itération. Le filtre est basé sur un noyau de spline lissante dont le but, à l'origine, était d'approcher un ensemble de points par une fonction continue plutôt que d'interpoler exactement ces points. Nous mettons en avant, dans cette méthode de régularisation, la concision du paramètre de régularisation : il s'agit d'une valeur ?, réelle et positive, qui influe sur la fréquence de coupure du filtre passe-bas. Une relation analytique existant entre ?, la fréquence de coupure et la fréquence d'échantillonnage, il est possible de donner un sens métrique à la fréquence de coupure. De plus, nous pouvons affecter une valeur ? différente en chaque point du contour par une variation des coefficients du filtre et ainsi permettre une régularisation locale du contour actif. La généralisation de cette nouvelle méthode de régularisation pour des modèles déformables surfaciques est proposée. La difficulté principale concerne la connectivité du maillage, contrainte à une valence 4 partout par le filtrage bidimensionnel. Des résultats de segmentation sont donnés pour de tels maillages ainsi que pour des maillages sphériques où un traitement particulier des pôles est mis en oeuvre.

Afin d'étudier les processus biogéochimiques de l'Océan Austral, des balises posées sur des éléphants de mer ont permis de récolter en 2009-2010 des profils de variables océanographiques (Chlorophylle a (Chl a), température, salinité, lumière) dans une zone s'étalant du sud des îles Kerguelen jusqu'au continent Antarctique. Cette thèse se penche en particulier sur les données de Chl a, car celle-ci est contenue dans les organismes photosynthétiques qui jouent un rôle essentiel de pompe à carbone. Mais les profils verticaux de Chl a, récoltés peu fréquemment, ne permettent pas d'obtenir une cartographie de cette variable dans cette zone de l'océan. Cependant, nous disposons de profils de lumière, échantillonnés plus souvent. L'objectif était alors de développer une méthodologie permettant de reconstruire de manière indirecte les profils de Chl a à partir des profils de lumière, et qui prenne en compte les caractéristiques de ce type de données qui se présentent naturellement comme des données fonctionnelles. Pour cela, nous avons abordé la décomposition des profils à reconstruire ou explicatifs sur une base de splines, ainsi que les questions d'ajustement associées. Un modèle linéaire fonctionnel a été utilisé, permettant de prédire des profils de Chl a à partir des dérivées des profils de lumière. Il est montré que l'utilisation d'un tel modèle permet d'obtenir une bonne qualité de reconstruction pour accéder aux variations hautes fréquences des profils de Chl a à fine échelle. Enfin, une interpolation par krigeage fonctionnel permet de prédire la concentration en Chl a de nuit, car les mesures de lumière acquises à ce moment-là ne peuvent pas être exploitées. / To study biogeochemical processes in the Southern Ocean, tags placed on elephant seals allowed to collect during 2009-2010 oceanographic variables profiles (Chlorophyll a (Chl a), temperature, salinity, light) in an area ranging from southern Kerguelen until the Antarctic continent. This thesis focuses on Chl a data as it is contained in photosynthetic organisms and these ones play an essential role in the oceanic carbon cycle. The infrequently collected vertical Chl a profiles don't provide a mapping of this variable in this area of the ocean. However, we have light profiles sampled more often. The aim of this thesis was then to develop a methodology for reconstructing indirectly Chl a profiles from light profiles, and that takes into account characteristics of this kind of data that naturally occur as functional data. For this, we adressed the profiles decomposition to rebuild or explanations on splines basis, as well as issues related adjustment. A functional linear model was used to predict Chl a profiles from light profiles derivatives. It was shown that the use of such a model provides a good quality of reconstruction to access high frequency variations of Chl a profiles at fine scale. Finally, a functional kriging interpolation predicted the Chl a concentration during night, as light measurements acquired at that time can't be exploited. In the future, the methodology aims to be applied to any type of functional data.