Qu'il tente de prévenir la chute d'une personne âgée, de traduire la langue des signes ou de contrôler un humain virtuel, l'analyse de gestes est un vaste domaine de recherche qui s'attelle à reconnaître, classifier, segmenter, indexer ou encore évaluer différents types de mouvements. Cependant, peu de travaux se concentrent sur cette dernière approche d'évaluation. Ce travail de thèse propose de mettre en place un outil d’évaluation automatique et générique d’un geste sportif, reposant sur l’utilisation d’une base de données de gestes experts acquis via un système de capture de mouvements. Afin d’extraire un mouvement de référence, l’algorithme de déformation temporelle dynamique (DTW) est considéré pour aligner puis moyenner les gestes. Les méthodes d’alignements et de moyennage de séries temporelles se confrontant aux conséquences néfastes de chemins de déformation du DTW pathologiques, des contraintes locales sont ajoutées et donnent lieu à un nouvel algorithme appelé CDBA. La qualité d’un geste est estimée spatialement et temporellement à chaque instant et pour chaque membre par comparaison avec le geste de référence et pondérée par la dispersion des données expertes autour de ce geste moyen. Le processus ainsi mis en place est validé à partir de gestes de karaté et de tennis annotés par des entraîneurs. Un premier prototype d’outil d’entraînement en ligne est finalement proposé et laisse entrevoir les potentialités d’usage qui pourraient être menées à la suite de ce travail. / Either to reduce falling risks in elderly people, to translate the sign language or to control a virtual human being, gesture analysis is thriving research field that aims at recognizing, classifying, segmenting, indexing and evaluating different types of motions. As few studies tackle the evaluation process, this PhD focuses on the design of an autonomous system for the generic evaluation of sport-related gestures. The tool is trained on the basis of experts’ motions recorded with a motion capture system. Dynamic Time Warping (DTW) is deployed to obtain a reference gesture thanks to data alignment and averaging. Nevertheless, this standard method suffers from pathological paths issues that reduce its effectiveness. For this reason, local constraints are added to the new DTW-based algorithm, called CDBA (Constrained DTW Barycenter Averaging). At each time step and for each limb, the quality of a gesture is spatially and temporally assessed. Each new motion is compared to the reference gesture and weighted in terms of data dispersion around the reference.The process is validated on annotated karate and tennis databases. A first online training prototype is given in order to prompt further research on this subject.

In this doctoral thesis, we propose new iterative methods for solving a class of convex optimization problems. In general, we consider problems in which the objective function is composed of a finite sum of convex functions and the set of constraints is, at least, convex and closed. The iterative methods we propose are basically designed through the combination of incremental subgradient methods and string-averaging algorithms. Furthermore, in order to obtain methods able to solve optimization problems with many constraints (and possibly in high dimensions), generally given by convex functions, our analysis includes an operator that calculates approximate projections onto the feasible set, instead of the Euclidean projection. This feature is employed in the two methods we propose; one deterministic and the other stochastic. A convergence analysis is proposed for both methods and numerical experiments are performed in order to verify their applicability, especially in large scale problems. / Nesta tese de doutorado, propomos novos métodos iterativos para a solução de uma classe de problemas de otimização convexa. Em geral, consideramos problemas nos quais a função objetivo é composta por uma soma finita de funções convexas e o conjunto de restrições é, pelo menos, convexo e fechado. Os métodos iterativos que propomos são criados, basicamente, através da junção de métodos de subgradientes incrementais e do algoritmo de média das sequências. Além disso, visando obter métodos flexíveis para soluções de problemas de otimização com muitas restrições (e possivelmente em altas dimensões), dadas em geral por funções convexas, a nossa análise inclui um operador que calcula projeções aproximadas sobre o conjunto viável, no lugar da projeção Euclideana. Essa característica é empregada nos dois métodos que propomos; um determinístico e o outro estocástico. Uma análise de convergência é proposta para ambos os métodos e experimentos numéricos são realizados a fim de verificar a sua aplicabilidade, principalmente em problemas de grande escala.

Neste trabalho, nós consideramos o seguinte problema de valor inicial para uma equação diferencial funcional retardada com impulsos { \'x PONTO\' = \'varepsilon\' f (t, \'x IND.t\'), t \' DIFERENTE\' \'t IND. k\', \'DELTA\' x(\'t IND. k\') = \'varepsilon\' \' I IND. k\' (x ( \'t IND.k\')), k = 0, 1, 2, ... \'x IND. t IND.0\' = \' phi\', onde f está definida em um aberto \' OMEGA\' de R x \' G POT. -\' ([- r, 0], \' R POT. n\') e assume valores em \'R POT. n\', \' \'varepsilon\' \'G POT. - ([ - r, 0], \'R POT.n\'), r .0, onde \' G POT -\' ([ - r, 0], \' R POT. n\') denota o espaço das funções de [ - r, 0] em \' R POT. n\' que estão regradas e contínuas à esquerda. Além disso, \' t IND.0 < \' t IND. 1\'< ... \'t IND. k\' < ... são momentos pré determinados de impulsos tais que \'lim SOBRE k SETA + \' INFINITO\' \'t IND. k = + \' INFINITO\' e \'DELTA\'x (\' t IND.k\') = x ( \'t POT. + IND > k) - x (\'t IND. k). Os operadores de impulso \' I IND. k\', k = 0, 1, ... são funções contínuas de \'R POT. n\' em \' R POT. n\'. Consideramos, também, que para cada x \'varepsilon\' \' G POT. -\' ([- r, \' INFINITO\'), \'R POT. n\'), t \'SETA\' f (t, \'x IND. t\') é uma função localmente Lebesgue integrável e sua integral indefinida satisfaz uma condição do tipo Carathéodory. Além disso, f é Lipschitziana na segunda variável. Definimos \' f IND. 0\' ( \'phi\') = \' lim SOBRE T \' SETA\' \' INFINITO\' \'1 SUP. T \' INT. SUP. T INF. \' T IND.0\' f (t, \' PSI\') dt e \' I IND. 0(x) = \' lim SOBRE T \'SETA\' \' INFINITO\' \' 1 SUP. T\' \' SIGMA\' IND. 0 < ou = \' t IND. i\' < T onde \' psi\' \'varepsilon\' \' G POT. -\' ([ - r, 0], \' R POT. n\', e consideremos a seguinte equação diferencial funcioonal autônoma \" média\" y PONTO = \' varepsilon\' [ \' f IND. 0\' (\' y IND. t\' + \' I IND> 0\' (y (t))], \'y IND. t IND. 0 = \' phi\'. Então provamos que, sob certas condições, a solução x(t) de (1) se aproxima da solução y(t) de (2) em tempo assintoticamente grande / In this present work, we condider the following initial value problem for a retarded functional differential equation with impulses { \'x POINT\' = \'varepsilon\' f (t, \'x IND.t\'), t \' DIFFERENT\' \'t IND. k\', \'DELTA\' x(\'t IND. k\') = \'varepsilon\' \' I IND. k\' (x ( \'t IND.k\')), k = 0, 1, 2, ... \'x IND. t IND.0\' = \' phi\', where f está defined in a open set \' OMEGA\' de R x \' G POT. -\' ([- r, 0], \' R POT. n\'), r >0, and takes values in \'R POT. n\', \' \'varepsilon\' \'G POT. - ([ - r, 0], \'R POT.n\'), r .0, where \' G POT -\' ([ - r, 0], \' R POT. n\') denotes the space of regulated functions from [ - r, 0] to \' R POT. n\' which are left continuous. Furthermore, \' t IND.0 < \' t IND. 1\'< ... \'t IND. k\' < ... are pre-assigned moments of impulse effects such that \'lim ON k ARROW + \' THE INFINITE\' \'t IND. k = + \' THE INFINITE\' e \'DELTA\'x (\' t IND.k\') = x ( \'t POT. + IND>k) - x (\'t IND. k). The impulse operators \' I IND. k\', k = 0, 1, ... are continuous mappings from \'R POT. n\' to \' R POT. n\'. For each x \'varepsilon\' \' G POT. -\' ([- r, \' THE INFINITE\'), \'R POT. n\'), t \'ARROW\' f (t, \'x IND. t\') is locally Lebesgue integrable and its indefinite integral satisfies a Carathéodory. Moreover, f é Lipschitzian with respect to the second variable. We define \' f IND. 0\' ( \'phi\') = \' lim ON T \' ARROW\' \' THE INFINITE\' \'1 SUP. T \' INT. SUP. T INF. \' T IND.0\' f (t, \' PSI\') dt and \' I IND. 0(x) = \' lim ON T \'ARROW\' \' THE INFINITE\' \' 1 SUP. T\' \' SIGMA\' IND. 0 < or = \' t IND. i\' < T where \' psi\' \'varepsilon\' \' G POT. -\' ([ - r, 0], \' R POT. n\', and consider the \"averaged\" autonomous functional differential equation \'y PONTO = \' varepsilon\' [ \' f IND. 0\' (\' y IND. t\' + \' I IND> 0\' (y (t))], \'y IND. t IND. 0 = \' phi\'. Then we prove that, under certain conditions, the solution x(t) of (1) in aproximates the solution y(t) de (2) in an asymptotically large time interval

Este trabalho aborda o problema da inversão do vetor momento magnético, com ampla aplicação na Ressonância Nuclear Magnética (RNM). Em vez de uma sequência de impulsos e de abordarmos somente o problema de conduzir o vetor de -e3 para +e3, escolhemos uma lei de controle limitada e analisamos o processo de várias iterações (voltas completas). Através do método da medianização, obtemos uma solução explícita aproximada para o sistema e, através dela e de alguns teoremas auxiliares sobre rotações, discutimos a propagação do erro em módulo e fase cometido após a realização dessas iterações. / This dissertation considers the problem of inversion of the magnetic moment vector, with wide application in Nuclear Magnetic Resonance (NMR). Instead of a pulse sequence and only approach the problem of driving the vector from -e3 to +e3, we choose limited controls and we analyze several iterations of the process (laps). By the averaging method, we obtain an approximate explicit solution for the system and through this method, together with some auxiliary theorems on rotations, we discuss the propagation of error in magnitude and phase committed after performing these iterations.

Neste trabalho foi proposta uma estratégia de modelagem hidrológica para a transformação chuva vazão da Bacia do Ribeirão da Onça (B.R.O) utilizando-se técnicas de auto calibração com análise de incertezas e de ponderação de modelos. Foi utilizado o modelo hidrológico Soil and Water Assessment Tool (SWAT), por ser um modelo que possui uma descrição física e de maneira distribuída dos processos hidrológicos da bacia. Foram propostas cinco diferentes séries de precipitação e esquemas de interpolação espacial a serem utilizados como dados de entrada para o modelo SWAT. Em seguida, utilizou-se o método semiautomático Sequential Uncertainty Fitting ver.-2 (SUFI-2) para a auto calibração e análise de incertezas dos parâmetros do modelo e produção de respostas com intervalos de incerteza para cada uma das séries de precipitação utilizadas. Por fim, foi utilizado o método de ponderação bayesiana de modelos (BMA) para o pós-processamento estocástico das respostas. Os resultados da análise de incerteza dos parâmetros do modelo SWAT indicam uma não adequação do método Soil Conservation Service (SCS) para simulação da geração do escoamento superficial, juntamente com uma necessidade de maior investigação das propriedades físicas do solo da bacia. A análise da precisão e acurácia dos resultados das séries de precipitação em comparação com a resposta combinada pelo método BMA sugerem a última como a mais adequada para a simulação chuva-vazão na B.R.O. / This study proposed an approach to the hydrological modeling of the Ribeirão da Onças Basin (B.R.O) based on automatic calibration and uncertainty analysis methods, together with model averaging. The Soil and Water Assessment Tool (SWAT) was used due to its distributed nature and physical description of hydrologic processes. An ensemble, composed by five different precipitation schemes, based on different sources and spatial interpolation methods was used. The Sequential Uncertainty Fitting ver-2 (SUFI-2) procedure was used for automatic calibration and uncertainty analysis of the SWAT model parameters, together with generation of streamflow simulations with uncertainty intervals. Following, the Bayesian Model Averaging (BMA) was used to merge the different responses into a single probabilistic forecast. The results of the uncertainty analysis for the SWAT parameters show that the Soil Conservation Service (SCS) model for surface runoff prediction may not be suitable for the B.R.O, and that more investigations about the soil physical properties at the Basin are recommended. An analysis of the accuracy and precision of the simulations produced by the precipitation ensemble members against the BMA simulation supports the use of the latter as a suitable framework for streamflow simulations at the B.R.O.

Cette thèse étudie la problématique du fonctionnement sans capteur et à basse vitesse des moteurs synchrones à aimant permanent par l'injection des signaux. Nous nous focalisons sur les effets de la saturation magnétique car leur compensation est primordiale pour résoudre cette problématique. Nous proposons une méthode originale pour modéliser la saturation magnétique en utilisant une approche énergétique (les formulations Lagrangienne et Hamiltonienne), où les symétries physiques sont exploitées pour simplifier l'expression de l'énergie magnétique. Les données expérimentales montrent qu'un polynôme de degré 4 est suffisant pour décrire avec précision les effets de la saturation. Ensuite, nous proposons une analyse claire et originale basée sur la moyennisation de second ordre et qui explique comment obtenir l'information de position à partir de l'injection des signaux (en utilisant le modèle proposé). Nous donnons une relation explicite entre les oscillations des courants statoriques et la position du rotor; cette relation est utilisée en temps réel. Ce modèle de saturation magnétique ainsi que la procédure d'estimation de position ont été testés et validés sur deux types de moteurs : avec des aimants permanents à l'intérieur ou sur la surface du rotor. Les résultats expérimentaux obtenus sur un banc de test montrent que les erreurs d'estimation de la position du rotor n'excèdent pas quelques degrés électriques dans la zone d'opération à basse vitesse. / This thesis addresses the problematic of sensorless low speed operation of permanent magnet synchronous motors (PMSM) by signal injection. We focus on the effects of magnetic and cross saturations because their compensation is paramount to solve this problematic. We propose an original way of modeling magnetic saturation using an energy approach (Lagrangian and Hamiltonian formulations), where the physical symmetries are exploited to simplify the expression of the magnetic energy. Experimental data show that a simple polynomial of degree 4 is sufficient to describe accurately magnetic saturation effects. Then we propose a clear and original analysis based on second-order averaging of how to recover the position information from signal injection (using the proposed model). We give an explicit relation between stator current ripples and rotor position; this relation is used in real time operation. Such magnetic saturation model and the resulting position estimates were tested and validated on two types of motors: with interior and surface permanent magnets (IPM and SPM). Experimental results obtained on a test bench show that estimation errors of the rotor position do not exceed few electrical degrees in the low speed operating domain.

L’utilisation des matériaux à faibles impacts environnementaux devient essentielle dans le secteur du bâtiment à cause de sa forte consommation d’énergie et de ressources naturelles. Cette thèse porte sur les isolants bio-sourcés et spécialement les laines de chanvres possédant des propriétés thermiques et hydriques intéressantes. La laine de chanvre, étant composée essentiellement de fibres végétales, constitue un matériau fibreux anisotrope et fortement poreux, et possède à l’échelle microscopique une structure complexe et aléatoire. D’où l’intérêt de décrire précisément la morphologie de ce type de laine et de caractériser sa structure par analyse d’images tomographiques à rayons X et des images MEB. Puis nous avons mis en place un modèle macroscopique couplé de transfert de chaleur et de masse, permettant de comprendre le comportement thermohydrique de ces laines en utilisant la méthode de changement d’échelle par prise de moyenne. Pour prendre en compte la complexité géométrique de la microstructure nous avons eu recours à un double changement d’échelle. / The use of low environmental impact materials becomes essential in the construction industry due to its high consumption of energy and natural resources. In this thesis it was focused on the bio-based and especially wool hemp insulation with interesting thermal and water properties. Hemp wool, being composed substantially of plant fibers, is an anisotropic, fibrous and highly porous material. At the microscopic level it possesses a complex and random structure, hence the interest of an accurate description to the morphology of this type of wool and to characterize its structure analysis by X-ray tomographic images and SEM images. Then a macroscopic model of coupled heat transfer and mass transport is set up to understand the behavior of these wools using the scaling method average gain. To take into account the geometric complexity of the microstructure a double change of scale was used.

This thesis aims to identify main driving market risk factors of different strategies implemented by hedge funds by looking at correlation coefficients, implementing Principal Component Analysis and analyzing "loadings" for first three principal components, which explain the largest portion of the variation of hedge funds' returns. In the next step, a stepwise regression through iteration process includes and excludes market risk factors for each strategy, searching for the combination of risk factors which will offer a model with the best "fit", based on The Akaike Information Criterion - AIC and Bayesian Information Criterion - BIC. Lastly, to avoid counterfeit results and overcome model uncertainty issues a Bayesian Model Average - BMA approach was taken. Key words: Hedge Funds, hedge funds' strategies, market risk, principal component analysis, stepwise regression, Akaike Information Criterion, Bayesian Information Criterion, Bayesian Model Averaging Author's e-mail: aleksaradosavcevic@gmail.com Supervisor's e-mail: mp.princ@seznam.cz

The Iterative Closest Point (ICP) algorithm has been an extremely popular method for 3D points or surface registration. Given two point sets, it simultaneously solves for correspondences and estimates the motion between these two point sets. However, by only registering two such views at a time, ICP fails to exploit the redundant information available in multiple views that have overlapping regions. In this thesis, a multiview extension of the ICP algorithm is provided that simultaneously averages the redundant information available in the views with overlapping regions. Variants of this method that carry out such simultaneous registration in a causal manner and that utilize the transitivity property of point correspondences are also provided. The improved accuracy in registration of these motion averaged approaches in comparison with the conventional ICP method is established through extensive experiments. In addition, the motion averaged approaches are compared with the existing multiview techniques of Bergevin et. al. and Benjemaa et. al. The results of the methods applied to the Happy Buddha and the Stanford Bunny datasets of 3D Stanford repository and to the Pooh and the Bunny datasets of the Ohio (MSU/WSU) Range Image database are also presented.

Les protocoles de consensus ont gagné beaucoup d’intérêt ces dernières années. Dans cette thèse, nous étudions les problèmes d’optimisation, de contrôle, et de théorie de jeu qui se posent dans ces protocoles. Tout d’abord, nous étudions les techniques d’optimisation pour des problèmes de sélection de poids permettant ainsi d’augmenter la vitesse de convergence de protocoles de consensus dans les réseaux. Nous proposons de sélectionner les poids en appliquant un algorithme d’approximation: minimisation de la norme p de Schatten de la matrice de poids. Nous caractérisons l’erreur induite par cette approximation et nous montrons que l’algorithme proposé a l’avantage qu’il peut être soit résolu de façon distribuée. Ensuite, nous proposons un cadre conceptuel d’analyse des jeux d’adversaire qui peut ajouter du bruit aux poids utilisés par l’algorithme de consensus de moyenne afin d’éloigner le système de consensus. Nous analysons également la performance des algorithmes de consensus de moyenne où les informations échangées entre les agents voisins sont soumises à la quantification uniforme déterministe (les valeurs réelles envoyées par les nœuds de leurs voisins sont tronquées). Le problème de la terminaison des protocoles de consensus s’avère difficile dans le cadre distribué. Nous proposons un algorithme distribué pour la terminaison des protocoles de consensus. L’algorithme réduit la charge de communication tout en garantissant la convergence vers un consensus. Enfin, nous proposons une mesure de similarité qui évalue la qualité d’un regroupement (clustering) des nœuds dans un réseau. Un algorithme local de clustering basé sur cette métrique est donné. / Consensus protocols have gained a lot of interest in the recent years. In this thesis, we study optimization, control, and game theoretical problems arising in consensus protocols. First, we study optimization techniques for weight selection problems to increase the speed of convergence of discrete-time consensus protocols on networks. We propose to select the weights by applying an approximation algorithm: minimizing the Schatten p-norm of the weight matrix. We characterize the approximation error and we show that the proposed algorithm has the advantage that it can be solved in a totally distributed way. Then we propose a game theoretical framework for an adversary that can add noise to the weights used by averaging protocols to drive the system away from consensus. We give the optimal strategies for the game players (the adversary and the network designer) and we show that a saddle-point equilibrium exists in mixed strategies. We also analyze the performance of distributed averaging algorithms where the information exchanged between neighboring agents is subject to deterministic uniform quantization (e.g., when real values sent by nodes to their neighbors are truncated). Consensus algorithms require that nodes exchange messages persistently to reach asymptotically consensus. We propose a distributed algorithm that reduces the communication overhead while still guaranteeing convergence to consensus. Finally, we propose a score metric that evaluates the quality of clusters such that the faster the random walk mixes in the cluster and the slower it escapes, the higher is the score. A local clustering algorithm based on this metric is proposed.