Les études théoriques en épidémiologie utilisent principalement des équations différentielles pour étudier (voire tenter de prévoir) les processus infectieux liés aux maladies contagieuses, souvent sous des hypothèses peu réalistes (ex: des populations spatialement homogènes). Cependant ces modèles ne sont pas bien adaptés pour étudier les processus épidémiologiques à différentes échelles et ils ne sont pas efficaces pour prédire correctement les épidémies. De tels modèles devraient notamment être liés à la structure sociale et spatiale des populations. Dans cette thèse, nous proposons un ensemble de nouveaux modèles dans lesquels différents niveaux de spatialité (par exemple la structure locale de la population, en particulier la dynamique de groupe, la distribution spatiale des individus dans l'environnement, le rôle des personnes résistantes, etc.) sont pris en compte pour expliquer et prédire la façon dont des maladies transmissibles se développent et se répandent à différentes échelles, même à l'échelle de grandes populations. La manière dont les modèles que nous avons développé sont paramétrés leur permet en outre d'être reliés entre eux pour bien décrire en même temps le processus épidémiologique à grande échelle (population d'une grande ville, pays ...) mais avec précision dans des zones de surface limitée (immeubles de bureaux, des écoles). Nous sommes d'abord parvenus à inclure la notion de groupes dans des systèmes d'équations différentielles de modèles SIR (susceptibles, infectés, résistants) par une réécriture des dynamiques de population s'inspirant des réactions enzymatiques avec inhibition non compétitive : les groupes (une forme de complexe) se forment avec des compositions différentes en individus S, I et R, et les individus R se comportent ici comme des inhibiteurs non compétitifs. Nous avons ensuite couplé de tels modèles SIR avec la dynamique globale des groupes simulée par des algorithmes stochastiques dans un espace homogène, ou avec les dynamiques de groupe émergentes obtenues dans des systèmes multi-agents. Comme nos modèles fournissent de l'information bien détaillée à différentes échelles (c'est-à-dire une résolution microscopique en temps, en espace et en population), nous pouvons proposer une analyse de criticité des processus épidémiologiques. Nous pensons en effet que les maladies dans un environnement social et spatial donné présentent des signatures caractéristiques et que de telles mesures pourraient permettre l'identification des facteurs qui modifient leur dynamique.Nous visons ainsi à extraire l'essence des systèmes épidémiologiques réels en utilisant différents modèles mathématique et numériques. Comme nos modèles peuvent prendre en compte les comportements individuels et les dynamiques de population, ils sont en mesure d'utiliser des informations provenant du BigData, collectée par les technologies des réseaux mobiles et sociaux. Un objectif à long terme de ce travail est d'utiliser de tels modèles comme de nouveaux outils pour réduire les épidémies en guidant les rythmes et organisation humaines, par exemple en proposant de nouvelles architectures et en changeant les comportements pour limiter les propagations épidémiques. / Theoretical studies in epidemiology mainly use differential equations, often under unrealistic assumptions (e.g. spatially homogeneous populations), to study the development and spreading of contagious diseases. Such models are not, however, well adapted understanding epidemiological processes at different scales, nor are they efficient for correctly predicting epidemics. Yet, such models should be closely related to the social and spatial structure of populations. In the present thesis, we propose a series of new models in which different levels of spatiality (e.g. local structure of population, in particular group dynamics, spatial distribution of individuals in the environment, role of resistant people, etc) are taken into account, to explain and predict how communicable diseases develop and spread at different scales, even at the scale of large populations. Furthermore, the manner in which our models are parametrised allow them to be connected together so as to describe the epidemiological process at a large scale (population of a big town, country ...) and with accuracy in limited areas (office buildings, schools) at the same time.We first succeed in including the notion of groups in SIR (Susceptible, Infected, Recovered) differential equation systems by a rewriting of the SIR dynamics in the form of an enzymatic reaction in which group-complexes of different composition in S, I and R individuals form and where R people behave as non-competitive inhibitors. Then, global group dynamics simulated by stochastic algorithms in a homogeneous space, as well emerging ones obtained in multi-agent systems, are coupled to such SIR epidemic models. As our group-based models provide fine-grain information (i.e. microscopical resolution of time, space and population) we propose an analysis of criticality of epidemiological processes. We think that diseases in a given social and spatial environment present characteristic signatures and that such measurements could allow the identification of the factors that modify their dynamics.We aim here to extract the essence of real epidemiological systems by using various methods based on different computer-oriented approaches. As our models can take into account individual behaviours and group dynamics, they are able to use big-data information yielded from smart-phone technologies and social networks. As a long term objective derived from the present work, one can expect good predictions in the development of epidemics, but also a tool to reduce epidemics by guiding new environmental architectures and by changing human health-related behaviours.

This study focuses on the development of a stochastic simulation methodology to study the effects of cure kinetics uncertainty, in plane fibre misalignment and boundary conditions uncertainty on the cure process of composite materials. Differential Scanning Calorimetry was used to characterise cure kinetics variability of a commercial epoxy resin used in aerospace applications. It was found that cure kinetics uncertainty is associated with variations in the initial degree of cure, activation energy and reaction order. Image analysis was employed to characterise in plane fibre misalignment in a carbon fibre ±45º non-crimp fabric. The experimental results showed that variability in tow orientation was significant with a standard deviation of about 1.2º. A set of experiments using an infusion set-up was carried out to quantify boundary conditions uncertainty related to tool temperature, ambient temperature and surface heat transfer coefficient using thermocouples (tool/ambient temperature) and heat flux sensors (surface heat transfer coefficient). It was concluded that boundary conditions uncertainty can show considerable short term and long term variability. Conventional Monte Carlo and Probabilistic Collocation Method were integrated with a thermo-mechanical cure simulation model in order to investigate the effect of cure kinetics, fibre misalignment and boundary conditions variability on process outcome. The cure model was developed and implemented using a finite element model incorporating appropriate material sub-models of cure kinetics, specific heat capacity, thermal conductivity, moduli, thermal expansion and cure shrinkage. The effect of cure kinetics uncertainty on the temperature overshoot of a thick carbon fibre epoxy flat panel was investigated using the two stochastic simulation schemes. The stochastic simulation results showed that variability in cure kinetics can introduce a significant scatter in temperature overshoot, presenting a coefficient of variation of about 30%. Furthermore, it was shown that the collocation method can offer an efficient solution with significantly lower computational cost compared to Monte Carlo at comparable accuracy. Stochastic simulation of the cure of an angle shaped carbon fibre-epoxy component within the Monte Carlo scheme showed that fibre misalignment can cause considerable variability in the process outcome. The coefficient of variation of maximum residual stress can reach up to approximately 2% (standard deviation of 1 MPa) whilst qualitative and quantitative variations in final distortion of the cured part occur with the standard deviation in twist and corner angle reaching values of 0.4 º and 0.05º respectively. Simulation of the cure of a thin carbon fibre-epoxy panel within the Monte Carlo scheme indicated that surface heat transfer and tool temperature variability dominate variability in cure time, resulting in a coefficient of variation of about 22%. In addition to Monte Carlo, the effect of surface heat transfer coefficient and tool temperature variations on cure time was addressed using the collocation method. It was found that probabilistic collocation is capable of capturing variability propagation with good accuracy while offering tremendous benefits in terms of computational costs.

Les réseaux de fractures et les karsts constituent des discontinuités au sein de la roche qui affectent considérablement les écoulements de fluides, ce qui engendre des problèmes spécifiques dans divers domaines des géosciences. La problématique générale consiste à déterminer les caractéristiques géométriques et hydrauliques des réseaux de fractures ou de karsts. La caractérisation et la modélisation de ces structures se heurtent cependant à leur complexité géométrique et à leur distribution spatiale hétérogène. De plus, les observations et données directes concernant aussi bien les fractures et karsts que leur encaissant rocheux restent largement insuffisantes pour décrire avec certitudes leurs caractéristiques. Pour ces raisons, la modélisation de réseaux de fractures ou de karsts est le plus souvent réalisée dans un cadre probabiliste. Des simulations stochastiques de type objet ou pixel sont généralement mise en œuvre pour générer des modèles 3D de fractures ou karsts. Cependant les mécanismes sur lesquels repose ce type d'approche ne permet pas de reproduire toutes la complexité de ces objets naturels et fournit des modèles manquant de réalisme géologique.Dans ces travaux de thèse, nous proposons d'aborder la problématique de la modélisation des fractures et des karsts suivant une approche pseudo-génétique. Il s'agit de contraindre le processus de simulation stochastique de fractures et karsts par des règles géométriques et heuristiques qui imitent les processus physiques gouvernant leur formation. Deux méthodes poursuivant cet objectif ont été développées, l'une adressant la simulation des fractures et la seconde celle des karsts. Les modèles ainsi générés exposent des caractéristiques similaires à celles des réseaux de fractures et karsts naturels. / Fractures and karstic networks are known to significantly affect flow paths and therefore raise specific issues in a wide variety of geoscience fields. The common question beyond these problems isto determine whether there is a network of fractures and/or karstic conduits and if yes what are itsgeometrical and hydraulic characteristics. Characterization and modeling of these features is a challenge for it usually displays complex geometries and heterogeneous spatial distribution. Moreover, in most cases, neither fracture and karst nor their host environment can be observed or described with certainty at all scales and location of relevance. For these reasons, fractures and karstic networks are usually integrated into 3D geological model through a probabilistic framework. Stochastic object- or pixel-based simulations are commonly performed to generate 3D models of fractures and karst but failed to reproduce the whole complexity of these natural objects and 3D models often lack geological realism.To address the issues related to fracture and karst modeling, we present two genetic-like approaches. The motivation of this work is to constrain the stochastic simulation of fractures and karsts by geometrical and heuristic rules which mimic the physical processes governing their formation. The resulting fracture and karst models display similar characteristics as those of natural pattern.

[pt] O principal objetivo dessa dissertação é elaborar um modelo estocástico e implementar um simulador para a fluxo de caixa de ativos e passivos para uma simplificação de um plano de previdência privada de um único indivíduo. / [en] The main objective of this work is to propose a sthocastic model and to implement a simulator for the cash flow considering the assets and liabilities of a single person retirement plain.

Les réseaux karstiques s'organisent de manière hiérarchique et se comportent comme des drains pour l'écoulement des fluides souterrains. Cependant seule une partie limitée de ces réseaux karstiques est généralement humainement observable, et la connaissance globale d'un système reste limitée. Les simulations géostatistiques représentent un moyen d’étudier les différentes configurations des réseaux karstiques tridimensionnels (3D) probables et ainsi de déterminer les incertitudes sur le comportement du réservoir. Établir une telle démarche nécessite de comprendre les étapes de structuration d'un karst donné à partir de déterminations karstologiques permettant d'identifier la morphogenèse des formes exo- et endokarstique et de reconstituer l'évolution spéléogénétique d'un massif (spéléogenèse épigène ou hypogène, évolution du niveau de base, etc.). Cela a permis de définir une zonation de l'occurrence de l'organisation des structures karstiques (zone vadose, épiphréatique ou phréatique). En parallèle, l'analyse quantitative de géométries et de topologies de données 3D de cavités analogues a permis de comparer les différentes structures de réseaux karstiques et de fournir une base de données quantitative de caractéristiques morphologiques de cavités en fonction de processus spéléogénétiques. Deux approches géostatistiques ont été testées pour la simulation stochastique de réseaux karstiques. Elles reposent sur l'utilisation de méthodes classiques de géostatistiques basées-pixel : la simulation séquentielle d’indicatrice (SIS) et les simulations multipoints (MPS). / Karst networks are hierarchically organized and behave as drains for underground fluid flows. However, the humanly observed karst conduits represent only a limited part of the complete karst conduit system, and overall knowledge remains limited. Geostatistical stochastic simulations represent an interesting tool to study the different three-dimensional (3D) probable configurations of karst networks and then, to determine the uncertainties on the reservoir behaviors. This approach first requires understanding the successive stages of karst structuring of a reservoir and then to numerically reconstruct the 3D organization of karst structures. From karstological determinations, it is possible to identify the morphogenesis of the exo- and endokarst forms and to reconstitute the speleogenetic evolution of a massif (epigenic or hypogenic speleogenesis, evolution of the basic level, etc.). The speleogenetic reconstitutions then make it possible to identify the successive phases of the karst system structuration (epigenic or hypogenic speleogenesis, evolution of base level, etc.). In parallel, a quantitative analysis of the geometries and the topologies performed on 3D cave surveys permits to compare the different organizations of the karst network patterns, related to speleogenetic processes. This morphometric analysis provides a quantitative database of morphological characteristics according to their speleogenetic processes. Finally, two geostatistical approaches were tested to generate karst networks. They correspond to two classical pixel-based geostatistical methods: the sequential indicator simulation (SIS) and the multipoint simulations (MPS).

Ao longo dos anos, pesquisadores têm liderado estudos com o objetivo de investigar o perfil de consumo de água em edifícios, os quais contribuem para o conhecimento no que tange ao correto dimensionamento dos sistemas prediais. No contexto dos métodos para a caracterização das solicitações, as rotinas comumente empregadas para a obtenção das vazões de projeto foram, em sua maioria, propostas na metade do século XX. Estes modelos precisam ser revisados e readequados para a realidade de conservação existente atualmente. Nos últimos anos, alguns estudos propuseram modelos de simulação com foco de aplicação em sistemas prediais de distribuição de água, devido ao comportamento aleatório e temporal das solicitações neste tipo de sistema. Neste trabalho foi proposto um modelo de simulação estocástica da demanda de água em edifícios residenciais, que contemplou a modelagem comportamental dos usuários e a interação destes com o sistema, a fim de aperfeiçoar o processo de dimensionamento dos sistemas prediais de distribuição de água. Para isto, foram revisadas as bases teóricas de modelos propostos anteriormente com interesse de identificar aspectos significativos e construir um novo modelo, que mesclou a modelagem comportamental dos usuários e do sistema hidráulico. Para a obtenção dos valores das variáveis intervenientes, foi feita uma consulta em trabalhos dentro do contexto nacional e uma coleta de dados em campo. Os resultados da pesquisa em campo mostraram a correlação entre a rotina dos usuários e o volume de água consumida e um aumento médio de 192% do valor da vazão de projeto obtida pelo Método dos Pesos Relativos quando comparada com as vazões obtidas no medidor dos apartamentos monitorados. Em posse de todos os dados de entrada, foram feitas diferentes simulações que variaram o tipo do chuveiro instalado nos apartamentos. Quando comparadas as vazões obtidas pela simulação e pelo Método dos Pesos Relativos, em todos os componentes do sistema, a redução da vazão de projeto variou entre 4% e 61%. Em termos de consumo de material, a redução ficou entre 25% a 63%. / Over the years, researchers have been conducting studies to investigate the water consumption profile in buildings, which contribute to the knowledge regarding the correct sizing of the building hydraulic systems. In context of the methods for characterization of requests, the routines commonly used to obtain the project flows were mostly proposed in mid-20th-century. These models need to be revised and adapted to nowadays water conservation reality. In recent years, some studies have proposed simulation models with application focus in water distribution systems, due to the random and temporal behavior of the requests in this type of system. In this study, a stochastic simulation model of water demand in residential buildings has been proposed, which contemplated the behavioral modeling of users and their interaction with the system, in order to improve the design process of water distribution systems. For such, the theoretical bases of previously- proposed models for the identification of significant aspects for the construction of a new model were revised, which merged the behavioral modeling of users and the hydraulic system. In order to obtain the values of intervening variables, fieldworks and a review was conducted in papers which treated about the Brazilian context. The results of the data collected on the fieldworks show a correlation between the routine of users and the volume of water consumed. Besides, there was an average increase of 192% in the value of the project flow rate obtained by the Brazilian Standard Method when compared with the flows obtained in the monitored apartments. Considering the input data in the model, different simulations - with several different types of showers installed in the apartments - were made. When comparing the flows obtained by the simulation and the Brazilian Standard Method, in all components of the system, the reduction of the project flow varied between 4% and 61%. In terms of material consumption, the reduction was between 25% and 63%.

Desenvolve-se, neste trabalho, um modelo de simulação estocástica para o sistema de transporte por táxi com viagens exclusivas. Basicamente, o modelo simula a geração da demanda pelo serviço e as formas alternativas de oferta: ponto privativo, ponto livre e rádio táxi. A validação do modelo é realizada através da comparação entre o sistema de táxi observado na cidade de Bauru (SP) e o sistema simulado através da aplicação do modelo. A comparação é feita para a alternativa de oferta com pontos privativos, a única existente na cidade. Os resultados indicam que o modelo de simulação proposto reproduz bem a demanda e a oferta de viagens por táxi em cidades de porte médio. Apresenta-se, além disso, uma análise comparativa das simulações realizadas para as duas outras alternativas fictícias de operação na cidade de Bauru (SP); os resultados destas, quando comparados aos da situação existente, mostram uma significativa economia nos custos variáveis. Conclui-se que o modelo pode constituir-se num instrumento de análise e avaliação das diferentes políticas de operação de táxi e apontar a mais adequada para uma determinada cidade de porte médio. / In this work, a stochastic simulation model for the exclusive-ride taxi system is developed. The model simulates the demand generation for taxi service and the alternative forms of service supply: private pickup point, free pickup point, and radiotaxi. The model validation is carried out by comparing the taxi system observed in Bauru (SP) with that simulated using data set collected in it. The comparison is concerning to the operation with private pickup point because in Bauru there is only this type of operation. The results indicate that the proposed simulation model reproduces adequately the taxi demand and supply in medium sized cities. It is also presented a comparative analysis between existent system and other operation systems simulated. The analysis shows that a significative cost saving is obtained if the operation system is changed in Bauru. It is concluded that the proposed model may constitute an important tool to analyze and evaluate the different operational policy and indicate the most adequate one for the medium sized cities.

Se manipulado de forma eficiente, o crescimento compensatório pode ser uma alternativa para reduzir o custo com a alimentação. No presente trabalho objetivou-se analisar o efeito bioeconômico do crescimento compensatório sobre sistemas intensivos de recria e terminação de bovinos de corte. Por meio de simulação, em um Sistema de Apoio a Decisão, a produtividade (Pr) e a resposta econômica foram avaliadas em quatro sistemas. Caracterizados por diferentes períodos de restrição alimentar (sem restrição, CONT; 90 dias de restrição, COMP90; 120 dias de restrição, COMP120 e 150 dias de restrição, COMP150) no período pós-desmama. Além disso, foram realizadas análises de risco e de sensibilidade, por meio de simulação de Monte Carlo. Os sistemas com regime alimentar restrito necessitaram de maior período de engorda (14, 21 e 35 dias para COMP90, COMP120 e COMP150, respectivamente) que CONT. O sistema COMP90 teve Pr (434,2 kg/ha/ano) similar ao CONT (434,0 kg/ha/ano) e ambos maiores que COMP120 (395,0 kg/ha/ano) e COMP150 (394,0 kg/ha/ano). A margem bruta/ha foi de 608,98; 493,5; 366,96 e 304,23 R$/ha/ano para os sistemas COMP90, CONT, COMP120 e COMP150, respectivamente. Entretanto, na análise de risco o sistema menos estável economicamente foi o CONT e o com menor risco foi COMP90. A análise de sensibilidade demonstrou que as variáveis com maior efeito sobre a margem bruta foram o preço do boi gordo, do bezerro e do milho usado no confinamento. O uso do crescimento compensatório pode ser uma ferramenta para redução de custos com a alimentação em sistemas de recria e engorda de bovinos de corte, mas a sua eficácia é influenciada pelo período de restrição. / When used efficiently the compensatory growth can be an option to reduce feeding cost. The aim was to analyze the bioeconomic effect of compensatory growth on intensive growing and fattening beef cattle systems. By simulation using a Decision Support System the productivity and the economic return were evaluated in four different systems, characterized by different periods of feeding restriction (no restriction, CONT; 90 days restriction, COMP90; 120 days restriction, COMP120 and 150 days restriction, COMP150). Besides, the risk analysis and sensitivity analysis were performed using Monte Carlo simulation. The systems with restriction of feeding required longer fattening periods (14, 21 e 35 days for COMP90, COMP120 e COMP150 respectively) than the CONT system. The COM90 obtained higher productivity (434,2 kg/ha/year) close of CONT system (434kg/ ha/ year) and both were higher than COMP120 (395 kg/ha/year) and COMP150 (394 kg/ha/year). The highest gross margin/ha was obtained in COMP90 (608,98 R$/ha/year) that was more than CONT (493,5 R$/ha/year), COMP120 (366,96 R$/ha/year) and COMP150 (304,23 R$/ha/ year). However, the risk analysis resulted in a highest risk using CONT system and lowest risk with COMP90. The sensitivity analysis demonstrated that the variables with the most effect on gross margin are beef, calf and corn prices. The use of compensatory growth can be a tool to reduce feeding costs in beef cattle systems however its effectiveness is influenced by the restriction period.

Desenvolve-se, neste trabalho, um modelo de simulação estocástica para o sistema de transporte por táxi com viagens exclusivas. Basicamente, o modelo simula a geração da demanda pelo serviço e as formas alternativas de oferta: ponto privativo, ponto livre e rádio táxi. A validação do modelo é realizada através da comparação entre o sistema de táxi observado na cidade de Bauru (SP) e o sistema simulado através da aplicação do modelo. A comparação é feita para a alternativa de oferta com pontos privativos, a única existente na cidade. Os resultados indicam que o modelo de simulação proposto reproduz bem a demanda e a oferta de viagens por táxi em cidades de porte médio. Apresenta-se, além disso, uma análise comparativa das simulações realizadas para as duas outras alternativas fictícias de operação na cidade de Bauru (SP); os resultados destas, quando comparados aos da situação existente, mostram uma significativa economia nos custos variáveis. Conclui-se que o modelo pode constituir-se num instrumento de análise e avaliação das diferentes políticas de operação de táxi e apontar a mais adequada para uma determinada cidade de porte médio. / In this work, a stochastic simulation model for the exclusive-ride taxi system is developed. The model simulates the demand generation for taxi service and the alternative forms of service supply: private pickup point, free pickup point, and radiotaxi. The model validation is carried out by comparing the taxi system observed in Bauru (SP) with that simulated using data set collected in it. The comparison is concerning to the operation with private pickup point because in Bauru there is only this type of operation. The results indicate that the proposed simulation model reproduces adequately the taxi demand and supply in medium sized cities. It is also presented a comparative analysis between existent system and other operation systems simulated. The analysis shows that a significative cost saving is obtained if the operation system is changed in Bauru. It is concluded that the proposed model may constitute an important tool to analyze and evaluate the different operational policy and indicate the most adequate one for the medium sized cities.

[pt] Em muitas aplicações reais de processamento de sinais, as observações do fenômeno em estudo chegam seqüencialmente no tempo. Consequentemente, a tarefa de análise destes dados envolve estimar quantidades desconhecidas em cada observação concebida do fenômeno. Na maioria destas aplicações, entretanto, algum conhecimento prévio sobre o fenômeno a ser modelado está disponível. Este conhecimento prévio permite formular modelos Bayesianos, isto é, uma distribuição a priori sobre as quantidades desconhecidas e uma função de verossimilhança relacionando estas quantidades com as observações do fenômeno. Dentro desta configuração, a inferência Bayesiana das quantidades desconhecidas é baseada na distribuição a posteriori, que é obtida através do teorema de Bayes. Infelizmente, nem sempre é possível obter uma solução analítica exata para esta distribuição a posteriori. Graças ao advento de um formidável poder computacional a baixo custo, em conjunto com os recentes desenvolvimentos na área de simulações estocásticas, este problema tem sido superado, uma vez que esta distribuição a posteriori pode ser aproximada numericamente através de uma distribuição discreta, formada por um conjunto de amostras. Neste contexto, este trabalho aborda o campo de simulações estocásticas sob a ótica da genética Mendeliana e do princípio evolucionário da sobrevivência dos mais aptos. Neste enfoque, o conjunto de amostras que aproxima a distribuição a posteriori pode ser visto como uma população de indivíduos que tentam sobreviver num ambiente Darwiniano, sendo o indivíduo mais forte, aquele que possui maior probabilidade. Com base nesta analogia, introduziu-se na área de simulações estocásticas (a) novas definições de núcleos de transição inspirados nos operadores genéticos de cruzamento e mutação e (b) novas definições para a probabilidade de aceitação, inspirados no esquema de seleção, presente nos Algoritmos Genéticos. Como contribuição deste trabalho está o estabelecimento de uma equivalência entre o teorema de Bayes e o princípio evolucionário, permitindo, assim, o desenvolvimento de um novo mecanismo de busca da solução ótima das quantidades desconhecidas, denominado de inferência evolucionária. Destacamse também: (a) o desenvolvimento do Filtro de Partículas Genéticas, que é um algoritmo de aprendizado online e (b) o Filtro Evolutivo, que é um algoritmo de aprendizado batch. Além disso, mostra-se que o Filtro Evolutivo, é em essência um Algoritmo Genético pois, além da sua capacidade de convergência a distribuições de probabilidade, o Filtro Evolutivo converge também a sua moda global. Em conseqüência, a fundamentação teórica do Filtro Evolutivo demonstra, analiticamente, a convergência dos Algoritmos Genéticos em espaços contínuos. Com base na análise teórica de convergência dos algoritmos de aprendizado baseados na inferência evolucionária e nos resultados dos experimentos numéricos, comprova-se que esta abordagem se aplica a problemas reais de processamento de sinais, uma vez que permite analisar sinais complexos caracterizados por comportamentos não-lineares, não- gaussianos e nãoestacionários. / [en] In many real-world signal processing applications, the phenomenon s observations arrive sequentially in time; consequently, the signal data analysis task involves estimating unknown quantities for each phenomenon observation. However, in most of these applications, prior knowledge about the phenomenon being modeled is available. This prior knowledge allows us to formulate a Bayesian model, which is a prior distribution for the unknown quantities and the likelihood functions relating these quantities to the observations. Within these settings, the Bayesian inference on the unknown quantities is based on the posterior distributions obtained from the Bayes theorem. Unfortunately, it is not always possible to obtain a closed-form analytical solution for this posterior distribution. By the advent of a cheap and formidable computational power, in conjunction with some recent developments in stochastic simulations, this problem has been overcome, since this posterior distribution can be obtained by numerical approximation. Within this context, this work studies the stochastic simulation field from the Mendelian genetic view, as well as the evolutionary principle of the survival of the fittest perspective. In this approach, the set of samples that approximate the posteriori distribution can be seen as a population of individuals which are trying to survival in a Darwinian environment, where the strongest individual is the one with the highest probability. Based in this analogy, we introduce into the stochastic simulation field: (a) new definitions for the transition kernel, inspired in the genetic operators of crossover and mutation and (b) new definitions for the acceptation probability, inspired in the selection scheme used in the Genetic Algorithms. The contribution of this work is the establishment of a relation between the Bayes theorem and the evolutionary principle, allowing the development of a new optimal solution search engine for the unknown quantities, called evolutionary inference. Other contributions: (a) the development of the Genetic Particle Filter, which is an evolutionary online learning algorithm and (b) the Evolution Filter, which is an evolutionary batch learning algorithm. Moreover, we show that the Evolution Filter is a Genetic algorithm, since, besides its capacity of convergence to probability distributions, it also converges to its global modal distribution. As a consequence, the theoretical foundation of the Evolution Filter demonstrates the convergence of Genetic Algorithms in continuous search space. Through the theoretical convergence analysis of the learning algorithms based on the evolutionary inference, as well as the numerical experiments results, we verify that this approach can be applied to real problems of signal processing, since it allows us to analyze complex signals characterized by non-linear, nongaussian and non-stationary behaviors.