Tesis sobre el tema "Statistique – Environnement"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Statistique – Environnement".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Tomasini, Linda. "Apprentissage d'une représentation statistique et topologique d'un environnement". Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0024.
Texto completoGuerineau, Lise. "Analyse statistique de modèles de fiabilité en environnement dynamique". Lorient, 2013. http://www.theses.fr/2013LORIS297.
Texto completoWe propose models which integrate time varying stresses for assessing reliability of the electrical network. Our approach is based on the network observation and consists of statistical and probabilistic modelling of failure occurrence. The great flexibility allowed by the piecewise exponential distribution makes it appropriate to model time-to-failure of a component under varying environmental conditions. We study properties of this distribution and make statistical inference for different observation schemes. Models relating components reliability with environmental constraints, and relying on the piecewise exponential distribution, are proposed. The maximum likelihood is assessed on both simulated and real data sets. Then, we consider a multi-component system whose evolution is linked with the corrective maintenance performed. Reliability of this system can be described using stochastic processes. We present inference methods according to the nature of the observation. Discrete observation can be formulated in terms of missing data; the EM algorithm is used to reach estimates in this situation. Stochastic versions of this algorithm have been considered to overcome a possible combinatorial explosion preventing from the EM algorithm implementation. Numerical examples are presented for the proposed algorithms
Zahalca, Cristina-Anca. "Fiabilité de systèmes en environnement aléatoire stressant". Grenoble INPG, 1999. http://www.theses.fr/1999INPG0140.
Texto completoChevenet, François. "Un environnement coopératif de résolution de problèmes pour l'analyse statistique en écologie". Lyon 1, 1994. http://www.theses.fr/1994LYO10074.
Texto completoZombré, Wendlamita. "Durabilité des matériaux composites dans un environnement Génie Civil : expérimentation multi-échelle et analyse statistique". Thesis, Lyon, 2019. http://www.theses.fr/2019LYSE1106/document.
Texto completoOur thesis is part of this MICRO project "Innovative Composite Materials for the Repair of Structures: Reliability approach of the dimensioning for their requalification and the prediction of their durability". Final objective of the thesis is to understand the problem of sustainability through a multi-scale phenomenological experimental approach and to propose probabilistic life-time models. So, we defined the methodology of our study, as well as the methods, materials and analysis techniques. The study material is a non-equilibrium (70% / 30%) unbalanced bidirectional carbon / epoxy that is crosslinked at room temperature and made by hand layup process. Six hygrothermal aging obtained by crossing between temperatures (20°C, 40°C and 60°C) and humidities (50%, 75% and immersion) at various times were carried out during the study. After identifying the various indicators, we carried out physicochemical analyzes (absorption-desorption, DSC, TMA, Infrared, DMA and Tomography) as well as a follow-up of the mechanical characteristics (tensile, interlaminar shear, pull-out and double shear). These indicators were analyzed statistically to more rigorously validate the trends that were observed. The monitoring of mechanical performance indicators by accelerated aging was carried out and then compared to 1 year of natural aging. The antagonism of the various mechanisms of damage has been demonstrated in the case of simple traction and interlaminar shear. It appears that plasticization is the mechanism that most affects the performance of carbon / epoxy composites. For high temperatures, it appears that post-cure by densifying the network has improved interfacial cohesion, which has inhibited the impact of thermal degradation on mechanical performance. Comparing with natural aging, it was noted that aging in an aqueous condition was more generally degrading and aqueous conditions accelerated well the degradation in a natural environment. In particular, the trends observed do not follow evolutions that permit to write simplified prediction models. The quality of the composite / concrete adhesion was evaluated by pull-out tests. The strong disparities between the results make the analysis delicate. But it has been shown that the post-cure seems to improve the cohesion whereas the plasticization is very harmful for the stability of the bonded joints accelerating excessively the degradation in comparison to the natural aging. This instability has also been proven by the double shear tests where the delamination was observed from the first maturities of aging. The anchor length is reduced and a time-sensitive model has been proposed for the selected aging condition (60°C-immersion). On the other hand, this plasticization softens the failure due to the increased deformability of the joint. In this environmental condition, the monitoring of the elastic limit stress seems to be a relevant indicator for the monitoring of the durability because it simulates the natural aging with reasonable differences. The last part of our work consisted in the proposal of a statistical treatment of the data in order to validate firstly the trends observed experimentally, to bring more information and to discuss on the choice of the models of prediction. Although, physical model is very appreciated by the community, it is not systematically applicable. Indeed, it assumes degenerative performance, which in practice is not the case. A physical approach has been proposed on the refined database in order to respect the writing conditions of the model (degenerative trends). The model chosen to predict the ultimate tensile strength is conservative but applicable for reliability studies. Bayesian enrichment can be used to demonstrate the advantage it can confer in reliability studies
Vatsiou, Alexandra. "Analyse de génétique statistique en utilisant des données pangénomiques". Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAS002/document.
Texto completoThe complex phenotypes observed nowadays in human populations are determined by genetic as well as environmental factors. For example, nutrition and lifestyle play important roles in the development of multifactorial diseases such as obesity and diabetes. Adaptation on such complex phenotypic traits may occur via allele frequency shifts at multiple loci, a phenomenon known as polygenic selection. Recent advances in statistical approaches and the emergence of high throughput Next Generation Sequencing data has enabled the detection of such signals. Here we aim to understand the extent to which environmental changes lead to shifts in selective pressures as well as the impact of those on disease susceptibility. To achieve that, we propose a gene set enrichment analysis using SNP selection scores that are simply scores that quantify the selection pressure on SNPs and they could be derived from genome-scan methods. Initially we carry out a sensitivity analysis to investigate which of the recent genome-scan methods identify accurately the selected region. A simulation approach was used to assess their performance under a wide range of complex demographic structures under both hard and soft selective sweeps. Then, we develop SEL-GSEA, a tool to identify pathways enriched for evolutionary pressures, which is based on SNP data. Finally, to examine the effect of potential environmental changes that could represent changes in selection pressures, we apply SEL-GSEA as well as Gowinda, an available online tool, on a population-based study. We analyzed three populations (Africans, Europeans and Asians) from the HapMap database. To acquire the SNP selection scores that are the basis for SEL-GSEA, we used a combination of two genome scan methods (iHS and XPCLR) that performed the best in our sensitivity analysis. The results of our analysis show extensive selection pressures on immune related pathways mainly in Africa population as well as on the glycolysis and gluconeogenesis pathway in Europeans, which is related to metabolism and diabetes
De, moura braga Elayne. "Enseignement apprentissage de la statistique, TICE et environnement numérique de travail : étude des effets de supports didactiques numériques, médiateurs dans la conceptualisation en statistique". Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20021/document.
Texto completoDefining the Information and Communication Technologies for Education (TICE) as mediators in learning process, we carry out a research of the didactic support virtual “Quantitative Methods FORSE”, available to scholars students in Sciences of Education - Distance Learning (CNED) in order to propose complements to TICE in the way it becomes good mediators. Distance learning through TICE requires a new reading of education, practices and roles of the implied subjects (learning, contents, support, teacher). We show which are its roles, its advantages and its constraints, according to ergonomic analyses, observations of use, design questionnaires for gathering information from students and also analyses of their productions. Variables as attribution of causality, motivation and affective representations, sound suggested like essential points to complete the pedagogical-didactic triangle. These cognitive and emotional aspects are argued in this PhD thesis like rules of action for the learning of statistics concepts. Our hypothesis here is that a didactic support virtual can become a good mediator of conceptualization only if it holds the mentioned rules of action.According to our results, we observe that affective representations, attribution of causality and motivation influence significantly the learning of abstract concepts. By consequence, we propose that didactic support virtual can infer the affective state of users toward their performances and so, to be able to act in the direction to promote positive affective representations, which will bring back better conceptualizations from students
Hermant, Marie. "Variation des traits le long des gradients environnementaux : rôle de l’intégration phénotypique et de la variabilité au sein des clades". Rennes 1, 2011. https://tel.archives-ouvertes.fr/tel-00588294.
Texto completoLa réponse des traits à l'environnement a été étudiée essentiellement à travers la moyenne des attributs de trait des espèces et des lignées et a récemment été étendue à la variabilité intraspécifique. Cependant, les traits peuvent également répondre aux contraintes de l’environnement par (i) une forte détermination mutuelle des traits au sein des individus ou des populations, i. E. Une forte intégration phénotypique, et (ii) une faible variation des traits au sein de lignées phylogénétiques entières. Nous avons testé : (i) les effets de l’environnement abiotique et biotique sur l'intégration phénotypique chez des espèces végétales subantarctiques et les conséquences écologiques et biogéographiques d'une forte intégration phénotypique, et (ii) les effets de l’environnement abiotique et biotique sur la variabilité phénotypique réalisée au sein des genres d’Angiospermes de l'Europe Centrale. Pour le premier aspect, nous avons constaté que l'intégration phénotypique est plus forte en conditions abiotiques stressantes. Le renforcement de l'intégration phénotypique se produit sur de petites échelles spatiales et peut limiter la flexibilité à grande échelle des stratégies de croissance et de reproduction. Nous avons également montré que la forte intégration phénotypique et environnementale peut contribuer à l'endémisme de certaines espèces subantarctiques, probablement par une spécialisation sur le long terme de ces espèces à leur habitat. Pour le second aspect, nous avons observé que la variabilité phénotypique réalisée au sein des genres de l'Europe Centrale est plus élevée dans des conditions abiotiques intermédiaires, ce qui reflète une plus grande indépendance des traits. .
Jay, Emmanuelle. "Détection en Environnement non Gaussien". Phd thesis, Université de Cergy Pontoise, 2002. http://tel.archives-ouvertes.fr/tel-00174276.
Texto completoAvec l'évolution technologique des systèmes radar, la nature réelle du fouillis s'est révélée ne plus être Gaussienne. Bien que l'optimalité du filtre adapté soit mise en défaut dans pareils cas, des techniques TFAC (Taux de Fausses Alarmes Constant) ont été proposées pour ce détecteur, dans le but d'adapter la valeur du seuil de détection aux multiples variations locales du fouillis. Malgré leur diversité, ces techniques se sont avérées n'être ni robustes ni optimales dans ces situations.
A partir de la modélisation du fouillis par des processus complexes non-Gaussiens, tels les SIRP (Spherically Invariant Random Process), des structures optimales de détection cohérente ont pu être déterminées. Ces modèles englobent de nombreuses lois non-Gaussiennes, comme la K-distribution ou la loi de Weibull, et sont reconnus dans la littérature pour modéliser de manière pertinente de nombreuses situations expérimentales. Dans le but d'identifier la loi de leur composante caractéristique qu'est la texture, sans a priori statistique sur le modèle, nous proposons, dans cette thèse, d'aborder le problème par une approche bayésienne.
Deux nouvelles méthodes d'estimation de la loi de la texture en découlent : la première est une méthode paramétrique, basée sur une approximation de Padé de la fonction génératrice de moments, et la seconde résulte d'une estimation Monte Carlo. Ces estimations sont réalisées sur des données de fouillis de référence et donnent lieu à deux nouvelles stratégies de détection optimales, respectivement nommées PEOD (Padé Estimated Optimum Detector) et BORD (Bayesian Optimum Radar Detector). L'expression asymptotique du BORD (convergence en loi), appelée le "BORD Asymptotique", est établie ainsi que sa loi. Ce dernier résultat permet d'accéder aux performances théoriques optimales du BORD Asymptotique qui s'appliquent également au BORD dans le cas où la matrice de corrélation des données est non singulière.
Les performances de détection du BORD et du BORD Asymptotique sont évaluées sur des données expérimentales de fouillis de sol. Les résultats obtenus valident aussi bien la pertinence du modèle SIRP pour le fouillis que l'optimalité et la capacité d'adaptation du BORD à tout type d'environnement.
Capderou, Sami. "Estimation statistique non paramétrique appliquée à la surveillance des eaux côtières". Thesis, Bordeaux, 2018. http://www.theses.fr/2018BORD0128/document.
Texto completoThe protection of the environment, in particular aquatic systems, should be tackled as one of the top priorities of our society. The use of biological sensors to continuously test water quality is a possible way of monitoring aquatic environments. This approach has been successfully implemented on bivalve molluscs equipped with light electrodes that respect their natural behaviour, we then speak of valvometry. The purpose of this thesis is to automatically calculate and process the velocity of movement of bivalve mollusc valves in various aquatic environments. Years of recordings already acquired will allow us, from our models, to detect if there are variations in the speed of movement of the valves related to temperature variations. In particular, we studied the derivatives of different non parametric estimators of the regression function : the recursive Nadaraya-Watson estimator, the Johnston estimator, the Wand-Jones estimator and the Révész estimator. We also considered the deterministic version of the Nadaraya-Watson estimator. For each of the estimators we conducted a study on the asymptotic behaviour especially on the almost sure convergence and th asymptotic normality. We digitally illustrated these properties and applied these new estimation methods to real data to validate, or not, the environmental assumptions made by biologists
Démery, Vincent. "Interactions induites par un environnement fluctuant". Phd thesis, Université Paul Sabatier - Toulouse III, 2012. http://tel.archives-ouvertes.fr/tel-00713393.
Texto completoKazma, Rémi. "Les interactions gène-environnement dans les études génétiques des maladies complexes". Phd thesis, Université Paris Sud - Paris XI, 2010. http://tel.archives-ouvertes.fr/tel-00502881.
Texto completoDeloux, Estelle. "Politiques de maintenance conditionnelle pour un système à dégradation continue soumis à un environnement stressant". Nantes, 2008. http://archive.bu.univ-nantes.fr/pollux/show.action?id=866ed1e3-a4f9-4612-917d-8c5e8db2204d.
Texto completoOne of the challenges of maintenance optimisation is the development of decision-making models combining performance at the strategic level and at the operational level. A classic hypothesis is to consider that the degradation level of the system can be modelled by a stochastic process characterized in stationary state without taking into account the effects of the operating environment on the system. This hypothesis can be seen as one of the factors leading to gaps between expected performance and measured performance of maintenance policies. However, many works have been developed in the reliability field for the integration of the impact of these environmental conditions. The main objective of this manuscript is to develop maintenance decision tools for gradually deteriorating systems evolving in a stressful environment. First, we propose different ways to model the environment and its impact since it can directly influence the system failure or the degradation process. We express mutual relationships between environment and the degradation processes. Next, we propose and compare different adaptive maintenance policies which are based not only on the degradation level, but also on the stressful environment level. In addition, the proposed policies can be based either on an a priori knowledge of the system, or integrate the available online information on the environment. We will try throughout this manuscript to propose new maintenance approaches which combine theoretical expected performance on one side and operational reality and pragmatism on the other
Kazma, Rémi. "Les interactions gène-environnement dans les études génétiques des maladies complexes". Phd thesis, Paris 11, 2010. http://www.theses.fr/2010PA11T016.
Texto completoHakim, Vincent. "La morphologie des amas et la mécanique quantique dans un environnement dissipatif : deux illustrations des méthodes de la physique des phénomèmes critiques". Paris 11, 1985. http://www.theses.fr/1985PA112082.
Texto completoWe use several methods developed in the field of critical phenomena in order to study other problems. We obtain the number of directed 2D-animals growing from an arbitrary root and we compute two related exponents, ν and θ, by taking some inspiration from the solutions of exactly solved models of statistical Mechanics. Then, we define and solve two models of irreversible growth (DLA and the Eden model) on the Bethe lattice. After that, we study quantum Mechanics in a dissipative environment, à la Caldeira-Leggett. We begin by the completely soluble motion of a free particle coupled to a thermal bath. Then, we study, with renormalization group methods, a transition occurring for the two-level system, at a critical value of the friction coefficient. We also relate this model to other well-known hamiltonians of solid state Physics, by using the relations between fermions and bosons in one dimension. Finally, we study the damped motion of a particle in a periodic potential and find a similar transition between diffusive
Lajoie, Gilles. "Analyse de l'environnement urbain : exploitation du carroyage pour la statistique spatiale". Rouen, 1989. http://www.theses.fr/1989ROUEL093.
Texto completoAfter having specified the notion of "grid square", we first point out the advantages of this method for the geographical an analysis and its adjustment for the spatial information use; in the same time we evaluate the qualitative and quantitative informations loss. Among the examples of cartography based on grid squares, the British National Grid System remains so far the only national case. Then, we present the example of Rouen from the first steps at a pace of 750m to 500m, to the actual configuration. We precise the modications made on the algorithm of data transfer from the geographical partition to the grid square thanks to the application of a inhabited areas bit map. This is realised with the ventilation of social-demographic INSEE data from the last three censuses. The extend to data base by grid square is the logical result of the experience of rouen: a collaboration beetween different organisms allows the environmental and social variables gathering in order to draw a better frame of urban environment. Finally, we approach the contribution of remote sensing to the bosom of the data base by grid square as a parallel source of data. In conclusion, we present some tools for the analysis of the data base by grid squares. We validate this new geographical information by applying usual data process (ACP. CAH), then we expose specific tools (analysis of contiguous areas, variograms). Finally, we test this geographical data base through to the modelization of intra-urban dynamics with the P. Allen's model applied to the Greater Rouen, which confirm the great advantages of this data structure
Populaire, Sébastien. "Modèles probabiliste et crédibiliste du raisonnement incertain : Aspects méthodologiques et application dans le domaine du traitement des eaux usées". Compiègne, 2003. http://www.theses.fr/2003COMP1438.
Texto completoLn this thesis, we propose a methodology for combining expert knowledge with information extracted from statistical data, for estimating pollution solubility in wastewater. The method is based on: 1. A case-based approach allowing to predict a quantity of interest from past cases in the form of a belief function; 2. Bayesian networks for modeling expert knowledge 3. A tuning mechanism allowing to mix information sources, so as to minimize a performance criterion. The use of this method for this environmental problem is motivated by the fact that knowledge in this domain is very partial and ill structured. The belief functions theory allows to handle the induced uncertainty and imprecision. The approach is expected to be useful in situations where both small databases and partial expert knowledge are available
Johannet, Anne y Anne Johannet. "Modélisation par apprentissage statistique des systèmes naturels, ou en interaction avec un environnement naturel. Applications aux karsts, crues éclair et en robotique". Habilitation à diriger des recherches, Université Pierre et Marie Curie - Paris VI, 2011. http://tel.archives-ouvertes.fr/tel-00745131.
Texto completoSiohan, Olivier. "Reconnaissance automatique de la parole continue en environnement bruité : Application à des modèles stochastiques de trajectoires". Nancy 1, 1995. http://docnum.univ-lorraine.fr/public/SCD_T_1995_0290_SIOHAN.pdf.
Texto completoNjomgue, Sado Wilfried. "Indexation des documents dans un référentiel métier avec approche ontologique : Le système MAID au sein de l'Intranet de Suez-Environnement". Compiègne, 2005. http://www.theses.fr/2005COMP1572.
Texto completoThis work presents an automatic method of indexing documents based on semantic, linguistic and finally statistics approaches. System MAID, Multi-Approach for the Indexing of Documents applies successively these approaches: a semantic analysis of water domain' s ontology that annotates the document, a linguistic analysis that extracts significant terms, a statistical analysis by the decomposition in singular values of words composing the document. Here, weighting terms are set to take advantages of both their position compared to other terms (co-occurrence) and their local and global context. We will also highlight the contribution of semantics compared to the linguistic-statistic approach. MAID was developed in order to suggest assignments topics of documents to a referential. Finally, we will present experiments results (with or without semantic treatment) and evaluation carried out on documents of Suez-Environnement
Nguyen, Van Quan. "Cartographie d'un environnement sonore par un robot mobile". Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0172/document.
Texto completoRobot audition provides hearing capability for robots and helps them explore and understand their sound environment. In this thesis, we focus on the task of sound source localization for a single or multiple, intermittent, possibly moving sources using a mobile robot and exploiting robot motion to improve the source localization. We propose a Bayesian filtering framework to localize the position of a single, intermittent, possibly moving sound source. This framework jointly estimates the source location and its activity over time and is applicable to any micro- phone array geometry. Thanks to the movement of the robot, it can estimate the distance to the source and solve the front-back ambiguity which appears in the case of a linear microphone array. We propose two implementations of this framework based on an extended mixture Kalman filter (MKF) and on a particle filter, that we compare in terms of performance and computation time. We then extend our model to the context of multiple, intermittent, possibly moving sources. By implementing an extended MKF with joint probabilistic data association filter (JPDAF), we can jointly estimate the locations of two sources and their activities over time. Lastly, we make a contribution on long-term robot motion planning to optimally reduce the uncertainty in the source location. We define a cost function with two alternative criteria: the Shannon entropy or the standard deviation of the estimated belief. These entropies or standard deviations are integrated over time with a discount factor. We adapt the Monte Carlo tree search (MCTS) method for efficiently finding the optimal robot motion that will minimize the above cost function. Experiments show that the proposed method outperforms other robot motion planning methods for robot audition in the long run
Flageollet, Alexis. "Prévision de l'inflation et analyse des cycles économiques dans un environnement riche en données : une application des modèles à facteurs dynamiques à la zone euro". Paris 10, 2006. http://www.theses.fr/2006PA100044.
Texto completoWe have implemented several modeling strategies which are consistent with specific issues of the euro area, i. E. : the increasing amount of information available for euro area as well as the main concerns of the European Central Bank. In this thesis, we have investigated whether it is worth exploiting a large and heterogeneous set of data in order to forecast inflation and extract the common economic fluctuations in the euro area. The recent developments in statistics have allowed us to apply factor models to a large number of non-stationary data. We have been mainly focusing on providing a methodological approach in order to distinguish common effects from specific country effects on the one hand and short run dynamics from long run dynamics on the other hand. Finally, we have compared the forecasting performances of factor models to several indicator models and to a smaller-dimension model based on economic theory
Favier, Charly. "Hommes, Savanes, Forêts : modélisation de systèmes dynamiques liant l'homme à son environnement". Phd thesis, Université Paris Sud - Paris XI, 2003. http://tel.archives-ouvertes.fr/tel-00009014.
Texto completoDerrien, Olivier. "Optimisation de la quantification par modèles statistiques dans le MPEG advanced audio coder (AAC) : application à la spatialisation d'un signal comprimé en environnement MPEG-4". Paris, ENST, 2002. http://www.theses.fr/2002ENST0030.
Texto completoViandier, Nicolas. "Modélisation et utilisation des erreurs de pseudodistances GNSS en environnement transport pour l'amélioration des performances de localisation". Phd thesis, Ecole Centrale de Lille, 2011. http://tel.archives-ouvertes.fr/tel-00664264.
Texto completoCamanes, Alain. "Polymères Dirigés et Réseaux Conducteurs de Chaleur - Systèmes de mécanique statistique à l'équilibre et hors équilibre". Phd thesis, Université de Nantes, 2008. http://tel.archives-ouvertes.fr/tel-00344652.
Texto completoLes réseaux conducteurs de chaleur sont étudiés hors équilibre. Lorsque les potentiels d'interaction sont harmoniques, nous donnons une interprétation géométrique de la condition d'existence et d'unicité de la mesure invariante via un théorème de complétude. Dans le cas où cette condition fait défaut, nous explicitons une quantité invariante par le flot hamiltonien. Nous généralisons ensuite les résultats d'unicité à des potentiels analytiques. Nous montrons que la condition de Hörmander est suffisante pour avoir l'unicité de la mesure invariante via la contrôlabilité. Le principe de Lasalle est ensuite utilisé pour montrer l'unicité sans la condition d'Hörmander. Nous évoquons également le problème de l'existence de telles mesures.
Poisat, Julien. "Modèle d’accrochage de polymères en environnement aléatoire faiblement corrélé". Thesis, Lyon 1, 2012. http://www.theses.fr/2012LYO10056/document.
Texto completoIn this dissertation we study the pinning model with weakly correlated disorder.The pinning model applies to various situations such as localization of a polymernear a one-dimensional interface, wetting transition and DNA denaturation, whichall display a transition between a localized phase and a delocalized phase.We start by giving a survey of the available results concerning critical pointsand exponents, first for the homogeneous setup and then for the inhomogeneousone, in the case when disorder is given by a sequence of independent and identicallydistributed (i.i.d.) random variables. In the latter case, we also provide a hightemperaturebound on the quenched critical curve in a case of relevant disorder.We then study the random pinning model when disorder is gaussian and hascorrelations with finite range, using the theory of Markov renewal processes. Weexpress the annealed critical curve in terms of the largest eigenvalue of a transfermatrix and we give the annealed critical exponent. We then generalize the criteriafor disorder relevance/irrelevance that were proved for the i.i.d. case.Next we are interested in disorder sequences with infinite range correlations.At first we generalize the method used to deal with finite range correlations andobtain the annealed critical behaviour in the case of gaussian disorder assumingfast decay of correlations. We use to this end the spectral properties of transferoperators for shifts on integer sequences and potentials with summable variations.Secondly we provide some results when disorder is a Markov chain
Banterle, Marco. "Computing strategies for complex Bayesian models". Electronic Thesis or Diss., Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLED042.
Texto completoThis thesis presents contributions to the Monte Carlo literature aimed toward the analysis of complex models in Bayesian Statistics; the focus is on both complexity related to complicate models and computational difficulties.We will first expand Delayed Acceptance, a computationally efficient variant ofMetropolis--Hastings, to a multi-step procedure and enlarge its theoretical background, providing proper justification for the method, asymptotic variance bounds relative to its parent MH kernel and optimal tuning for the scale of its proposal.We will then develop a flexible Bayesian method to analyse nonlinear environmentalprocesses, called Dimension Expansion, that essentially consider the observed process as a projection from a higher dimension, where the assumption of stationarity could hold.The last chapter will finally be dedicated to the investigation of conditional (in)dependence structures via a fully Bayesian formulation of the Gaussian Copula graphical model
Fiche, Anthony. "Distributions alpha-stable pour la caractérisation de phénomènes aléatoires observés par des capteurs placés dans un environnement maritime". Phd thesis, Université de Bretagne occidentale - Brest, 2012. http://tel.archives-ouvertes.fr/tel-00835073.
Texto completoAlami, Réda. "Bandits à Mémoire pour la prise de décision en environnement dynamique. Application à l'optimisation des réseaux de télécommunications". Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG063.
Texto completoIn this PhD thesis, we study the non-stationary multi-armed bandit problem where the non-stationarity behavior of the environment is characterized by several abrupt changes called "change-points". We propose Memory Bandits: a combination between an algorithm for the stochastic multi-armed bandit and the Bayesian Online Change-Point Detector (BOCPD). The analysis of the latter has always been an open problem in the statistical and sequential learning theory community. For this reason, we derive a variant of the Bayesian Online Change-point detector which is easier to mathematically analyze in term of false alarm rateand detection delay (which are the most common criteria for online change-point detection). Then, we introduce the decentralized exploration problem in the multi-armed bandit paradigm where a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. We propose a first generic solution called decentralized elimination: which uses any best arm identification algorithm as a subroutine with the guar-antee that the algorithm ensures privacy, with a low communication cost. Finally, we perform an evaluation of the multi-armed bandit strategies in two different context of telecommunication networks. First, in LoRaWAN (Long Range Wide Area Network) context, we propose to use multi-armed bandit algorithms instead of the default algorithm ADR (Adaptive Data Rate) in order to minimize the energy consumption and the packet losses of end-devices. Then, in a IEEE 802.15.4-TSCH context, we perform an evaluation of 9 multi-armed bandit algorithms in order to select the ones that choose high-performance channels, using data collected through the FIT IoT-LAB platform. The performance evaluation suggests that our proposal can significantly improve the packet delivery ratio compared to the default TSCH operation, thereby increasing the reliability and the energy efficiency of the transmissions
Martin, Lucile. "Contribution à la localisation d'un drone par vision stéréoscopique en intérieur texture". Paris 6, 2007. http://www.theses.fr/2007PA066472.
Texto completoMellah, Amine. "Modélisation statistique d'antennes dans leurs environnements". Phd thesis, Université Paris Sud - Paris XI, 2010. http://pastel.archives-ouvertes.fr/pastel-00006290.
Texto completoHue, Carine. "Méthodes séquentielles de Monte Carlo pour le filtrage non linéaire multi-objets dans un environnement bruité. Applications au pistage multi-cibles et à la trajectographie d'entités dans des séquences d'images 2D". Rennes 1, 2003. http://www.theses.fr/2003REN1A002.
Texto completoViandier, Nicolas. "Modélisation et utilisation des erreurs de pseudodistances GNSS en environnement transport pour l’amélioration des performances de localisation". Thesis, Ecole centrale de Lille, 2011. http://www.theses.fr/2011ECLI0006/document.
Texto completoToday, the GNSS are largely present in the transport field. Currently, the scientific community aims to develop transport applications with a high accuracy, availability and integrity. These systems offer a continuous positioning service. Performances are defined by the system parameters but also by signal environment propagation. The atmosphere propagation characteristics are well known. However, it is more difficult to anticipate and analyze the impact of the propagation environment close to the antenna which can be composed, for instance, of urban obstacles or vegetation.Since several years, the LEOST and the LAGIS research axes are driven by the understanding of the propagation environment and its use as supplementary information to help the GNSS receiver to be more pertinent. This approach aims to reduce the number of sensors in the localisation system, and consequently reduces its complexity and cost. The work performed in this thesis is devoted to provide more realistic pseudorange error models and reception channel model. After, a step of observation error characterization, several pseudorange error models have been proposed. These models are the finite gaussian mixture model and the Dirichlet process mixture. The model parameters are then estimated jointly with the state vector containing position by using adapted filtering solution like the Rao-Blackwellized particle filter. The noise model evolution allows adapting to an urban environment and consequently providing a position more accurate.Each step of this work has been tested and evaluated on simulation data and real data
Didier, Pascal. "Propriétés optiques de marqueurs fluorescents d'intérêt biologique en interaction avec leur environnement : étude par spectroscopie femtoseconde". Phd thesis, Université Louis Pasteur - Strasbourg I, 2004. http://tel.archives-ouvertes.fr/tel-00008127.
Texto completoErgenç, Belgin. "Un modèle d'exécution de requêtes mobiles pour des sources à accès restreints en environnement d'intégration de données". Toulouse 3, 2008. http://thesesups.ups-tlse.fr/168/.
Texto completoQuery optimization in data integration systems over large scale network, faces the challenges of dealing with autonomous, heterogeneous and distributed data sources, dynamic execution environment and changing user requirements. These issues initiate the need for crafting the traditional optimization methods in a way to produce stable query execution plans, use execution models which are able to adapt to run-time conditions and handle source restrictions. Centralization of the control in adaptive optimization methods result in bottleneck due to large amounts of message passing towards to the site of the central authority over large scale network where network bandwidth is low and network latency is high. In order to overcome this obstacle adaptive query optimization requires decentralized methods. A mobile execution model with mobile relational operators that are able to adapt in an autonomous way and focus on reducing of transfer cost is worth considering in large scale distributed data integration environment. However, this mobile query execution model needs to be extended with new operators to handle source restrictions. In this perspective we propose mobile relational operators developed for restricted sources. Another proposition is related with initial placement of mobile relational operators. The challenge is on defining a placement which would allow acceptable performance instead of a good placement which would cause dramatic performance sometimes at run-time. Finally we present and analyze a performance evaluation on the methods proposed
Beltaief, Slim. "Algorithmes optimaux de traitement de données pour des systèmes complexes d'information et télécommunication dans un environnement incertain". Thesis, Normandie, 2017. http://www.theses.fr/2017NORMR056/document.
Texto completoThis thesis is devoted to the problem of non parametric estimation for continuous-time regression models. We consider the problem of estimating an unknown periodoc function S. This estimation is based on observations generated by a stochastic process; these observations may be in continuous or discrete time. To this end, we construct a series of estimators by projection and thus we approximate the unknown function S by a finite Fourier series. In this thesis we consider the estimation problem in the adaptive setting, i.e. in situation when the regularity of the fonction S is unknown. In this way, we develop a new adaptive method based on the model selection procedure proposed by Konev and Pergamenshchikov (2012). Firstly, this procedure give us a family of estimators, then we choose the best possible one by minimizing a cost function. We give also an oracle inequality for the risk of our estimators and we give the minimax convergence rate
Dembele, Sidi. "Structuration spatiale de la biodiversité agricole dans la zone cotonnière du Mali". Electronic Thesis or Diss., Normandie, 2018. http://www.theses.fr/2018NORMC046.
Texto completoThe diversity of cropping systems and varieties plays an important role in the ability of family farms to withstand socio-economic and environmental shocks. For better conservation, this agricultural diversity needs to be characterized and monitored in space and time. While they were dominated by elements of price, area and production until recently, agricultural monitoring systems are beginning to integrate diversity issues. The diversity of cropping systems and varieties plays an important role in the ability of family farms to resist socio-economic and environmental shocks, whereas until the end of the 1990s it was considered as a limiting factor in improving the productivity of farming systems in varietal selection processes. In a situation of uncertain rainfall, to reduce the risk of this hazard, farmers use several species and varieties to survive and produce through all the hazards encountered. The peasant strategy consists in cultivating several varieties with different agronomic characteristics (early maturity, yield, resistance to diseases, parasites and drought, etc.) and culinary in the same field or in different fields. This strategy allows farmers to cultivate the varieties best suited to the soil conditions of their fields and to meet their diverse needs.It is in this context that this thesis focuses on the spatial structuring of agrobiodiversity in the cotton zone. To achieve this objective, several methods and approaches have been used. The approach adopted combines the digital analysis of satellite imagery and the use of data from field surveys. The analysis of these data is based on the spatial distribution of biodiversity and its correlation with agro-ecological practices and conditions, agronomic performance and performance.The main results from the analysis of the study data are:a) There is a great heterogeneity and diversity of landscapes in the cotton zone of Mali-Sud with a total of eleven (11) landscape units;b) There is great diversity at the specific level and in cropping systems. The mean values of the most specific indicator of diversity are recorded in villages where the mean rainfall is between 700 and 1000 mm of water followed by villages of less than 700 mm;c) The specific pressure indicator shows a geographical distribution of the pressures of the different crop species. Indeed, in villages where cotton is at the head of rotation, it exerts strong pressure on other species. In these villages, the cotton area is much larger than for the other species;d) For yield, most villages have average yields of cotton above the national average in 2015. Analyzing its evolution between 2013 and 2015, there is a decline in yield in most villages if this decline is very often sawtooth with increases in 2013 and 2014.e) The yield stability indicator shows that yields are stable with all species except maize.These results open the way for a greater contribution of geography in agronomic analysis
Kwadjane, Jean-Marc. "Apport de la connaissance a priori de la position de l'émetteur sur les algorithmes MIMO adaptatifs en environnement tunnel pour les métros". Thesis, Lille 1, 2014. http://www.theses.fr/2014LIL10208/document.
Texto completoThis thesis focuses on the design of adaptive algorithms for wireless communications in a multiple input multiple output (MIMO) design for subway tunnel environment. MIMO system meet the requirement of high capacity and robustness. However, these performance decreased due to the spatial correlation in tunnels. In this thesis, we studied precoding MIMO algorithms that use the channel state information (CSI) at the transmitter. Generally, these algorithms require feedback from receiver. To minimize the loss of spectral efficiency due to the reverse link, we selected from the literature precoder that reduce the feedback. We conducted a complete and realistic simulation system to evaluate the performance of these precoders taking into account several levels of quantity and quality of the CSI. For simulation, we used both theoretical and measured channels. We also assessed the impact of impulsive noise measured in the railway environment. By assuming a Cauchy law, We propose a receiver and a theoretical upper bound of the error probability of max-dmin precoder in uncorrelated environments. Finally, we proposed a precoder based on knowledge of the correlation matrix and studied the possibility of removing the return link thanks to the knowledge of the channel statistiques based on the localization in the tunnel
Occelli, Florent. "Systèmes d’Information Géographique et Lien Environnement – Santé (SIGLES) : contribution au développement d'outils cartographiques d'aide à la décision face aux risques sanitaires liés à l'environnement". Thesis, Lille 2, 2014. http://www.theses.fr/2014LIL2S043/document.
Texto completoEnvironmental and social inequalities in health (ESIH) over territories are related to two cumulative dimensions: populations exposed to their living poor quality environment and the vulnerability of these populations to the environmental risk factors, which can affect health. This research deals with the Geographic Information Systems (GIS) applied to the field of environmental health. General purposes are the characterization of environmental media quality and the assessment of ESIH.Achieving these objectives requires a first step of harvest, genesis and formatting spatialized environmental databases. Such data are resulting from physico-chemical monitoring and biomonitoring. They were then mapped using GIS tools, including geostatistical spatial interpolation methods. On the over hand, spatial variability in the incidence of diseases were investigated using disease mapping methods (Standardized Incidence Ratios: SIR) and the detection of atypical clusters of events (scan statistics), which are based on disease registries. Finally, geographical ecological studies are developed to associate the environmental maps generated to health and socio-economic status. Thus, this work aims to answer the question \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"do people with poor state of health live in a poor quality environment?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\" This question has been studied through three main researches.The first relates the characterization of trace elements burdens in the environment and the assessment of ESIH on neighborhood scale, over three territories in the Nord-Pas de Calais (NPdC) region. This research is conducted from measurements of biological burdens performed both in epiphytic lichens and humans and from a localized index of deprivation. The measured metals were considered individually, but also holistically by developing an integrated multimetallic index, in order to describe the general status of environmental pollution by metals. Environmental inequalities were observed on neighborhood scale in Dunkerque. Our results assume that trace elements burdens in populations are affected by environmental burdens.In our second research we revealed spatial disparities in the incidence of end stage renal disease (ESRD) on small area in the NPdC. Unlike other factors (diabetes, cardiovascular disease, medical practices), we highlighted the role of socio-economic status in the occurrence of such disparities. Only a part of the ESRD variability is currently explained. It is therefore necessary to focus on the environmental hypothesis.The third research focuses on the spatial and spatio-temporal analysis of groundwater contamination by trace elements, in order to identify potential environmental risk factors in the incidence of chronic inflammatory bowel disease.This work is based on several collaborations with the REIN network, the EPIMAD registry, and several research teams (EA4483 and EA2694 Université Lille 2, TVES EA4477 ULCO).Following this thesis, the research prospects are to pursue the development of integrated indicators to assess population exposure to the multiple environmental media contamination. The results also indicate a lack of information in environmental databases compared to health registries. A work is thus needed to define the content of such databases. These are necessary to characterize the environmental quality and to help the assessment of interaction between the populations and their living environment
Voiculescu, Sorin. "Fiabilité des systèmes embarqués". Phd thesis, Université d'Angers, 2009. http://tel.archives-ouvertes.fr/tel-00468219.
Texto completoKeita, Abou. "Modèles statistiques précoces et robustes pour l’estimation de la concentration d’agents biologiques dans un système de surveillance en continu dans l’environnement". Thesis, Rouen, INSA, 2014. http://www.theses.fr/2014ISAM0017/document.
Texto completoThis thesis is part of the ANR project, Génétic EquipemeNt for biothrEat enviroNmental Analysis and SurveillancE (GENEASE). This project focuses on the study of a system for monitoring and continuous analysis of biological environment. This analysis is done by a molecular biology method for the detection and identificatio of varions biological agents simultaneously. The device referred must integrate aIl the functions of sample collection of the rendering of the result. This project is essentially part of the axis "crisis management" since it focuses on the study of a mobile and portable equipment for the biological detection and identification. Our task i to develop a system that detects (or not) the presence of the species and to estimate its concentration. This estimation is based on fluorescence data using the number of the reference cycle (or break time). It is therefore to integrate into the same approach to the discrimination detect and the régression to qualify. In addition, the aim is to build a statistical model which from the single observation of the fluorescence of a drop, calculates an estimatation of the reference cycle and deduce an estimation of the concentration of the species to qualify while minimizing the delay at the detection. The work is to present a statistical model to determine continuous time fror the moment we observe this reference cycle on the fluorescence
Bidon, Stéphanie. "Estimation et détection en milieu non-homogène : application au traitement spatio-temporel adaptatif". Phd thesis, Toulouse, INPT, 2008. https://hal.science/tel-04426860.
Texto completoSpace-time adaptive processing is required in future airborne radar systems to improve the detection of targets embedded in clutter. Performance of detectors based on the assumption of an homogeneous environment can be severely degraded in practical applications. Indeed real world clutter features can vary significantly in both angle and range. So far, different strategies have been proposed to overcome the deleterious effect of heterogeneity. This dissertation proposes to study two of these strategies. More precisely a new data model is introduced in a Bayesian framework: it allows to incorporate both an original relation of heterogeneity and a priori knowledge. New estimation and detection schemes are derived according to the model ; their performances are also studied through numerical simulations. Results show that the proposed model and algorithms allow to incorporate in an appropriate way a priori information in the detection scheme
Bidon, Stéphanie. "Estimation et détection en milieu non-homogène : application au traitement spatio-temporel adaptatif". Phd thesis, Toulouse, INPT, 2008. http://oatao.univ-toulouse.fr/7737/1/bidon.pdf.
Texto completoLô, Mame Diarra Bousso. "Étude paramétrique et analyse conjointe modélisations / mesures pour la définition d'indicateurs d'expositions aux ondes électromagnétiques en environnement urbain". Thesis, Poitiers, 2017. http://www.theses.fr/2017POIT2251/document.
Texto completoWith the increasing number of mobile phone users, new services and mobile applications, the proliferation of radio antennas has raised concerns about human exposure to electromagnetic waves. This is now a challenging topic to many stakeholders such as local authorities, mobile phone operators, citizen and consumer groups, etc. The assessment of human exposure to radiofrequency electromagnetic fields in the urban environment is mainly based on numerical modeling. The improvement of computational tools together with the quantity and quality of available topographic data has strongly promoted this approach. Numerical modeling is now used in combination with several types of measurements to perform risk analysis and management. It is the basis of decision-making tools and local regulations. It is also used during consultations between the public, the industry, local authorities, governments and associations. The results of these methods are therefore increasingly important. This research contributes to gain knowledge about quantifying the human exposure from base stations through the combination of measurements and simulations, while taking into account the concept of variability of the electrical field. A first part of this work establishes the benefits and limitations of computational methods as well as measurements when assessing exposure to electric fields in urban environment. A second part of this work is aimed at characterizing the spatial and temporal variability of the actual exposure, which is a very important requirement because of the high variability of the electrical field and the difficulty of finding a relevant indicator to quantify the real exposure
Kendira, Atman. "L' animation comportementale d'avatars comme support à la communication dans les environnements virtuels informés". Compiègne, 2010. http://www.theses.fr/2010COMP1875.
Texto completoThe subject of this thesis takes places within the context of informed virtual environments such as virtual environments with template-based knowledge on which it is possible to interact dynamically. It focuses particularly on the design of a new decision-making model which integrates the uncertainty and incompleteness of model data. This work is at the intersection of virtual reality and knowledge engineering. The application of this domain is interpersonal communication in a virtual environment. We focused on non-verbal communication. The selected scenario is to tell a story to an audience of many through this environment. One of the major goals of this work is to ensure, via avatars, realistic nonverbal behaviour, which has an important place in interpersonal communication. In this context, we have designed a behavioural module named as BAYBE (Bayesian Behavior), which manages the representation of the user during their interactions with the collaborative virtual environment. The problem is on one hand to identify the relevant interactions taking place and on the other hand to translate them into gestural animations to strengthen collaboration between user profiles via avatars. This also must be done by requiring the least amount of human intervention, who must remain primarily focused on the task at hand: collaborative work. We have analyzed a corpus of data to extract the prior knowledge necessary to develop a decision model. This led to the creation of a new behavioural module based on probabilities and by using Bayesian network techniques for constructing the BAYBE module. This resulted in an implementation for a collaborative technological platform dedicated to storytelling
Ponzoni, Carvalho Chanel Caroline. "Planification de perception et de mission en environnement incertain : Application à la détection et à la reconnaissance de cibles par un hélicoptère autonome". Thesis, Toulouse, ISAE, 2013. http://www.theses.fr/2013ESAE0011/document.
Texto completoMobile and aerial robots are faced to the need of planning actions with incomplete information about the state of theworld. In this context, this thesis proposes a modeling and resolution framework for perception and mission planningproblems where an autonomous helicopter must detect and recognize targets in an uncertain and partially observableenvironment. We founded our work on Partially Observable Markov Decision Processes (POMDPs), because it proposes ageneral optimization framework for perception and decision tasks under long-term horizon. A special attention is given tothe outputs of the image processing algorithm in order to model its uncertain behavior as a probabilistic observationfunction. A critical study on the POMDP model and its optimization criterion is also conducted. In order to respect safetyconstraints of aerial robots, we then propose an approach to properly handle action feasibility constraints in partiallyobservable domains: the AC-POMDP model, which distinguishes between the verification of environmental properties andthe information about targets' nature. Furthermore, we propose a framework to optimize and execute POMDP policies inparallel under time constraints. This framework is based on anticipated and probabilistic optimization of future executionstates of the system. Finally, we embedded this algorithmic framework on-board Onera's autonomous helicopters, andperformed real flight experiments for multi-target detection and recognition missions
Allik, Amel. "La construction de la crise environnementale. Thèmes, stratégies et représentations". Electronic Thesis or Diss., Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCA038.
Texto completoThis thesis focuses on the construction of the environmental crisis through the flow of environmental discourses. We define the environmental crisis as a range of physical, social and discursive manifestations that are related to the Environment. They are caused by the separation of Man and nature, a relationship that derives from the Hellenistic concept of phusis. These manifestations oscillate between disruptions and uncertainties on the one hand, and on the other, the research of solutions whose objective is to find a new balance. The environmental crisis is composed of a set of public problems, as well as of numerous issues that have yet to be problematized or publicized in the public sphere. Through the careful study of some of environmental crisis discourses, we were able to examine these public problems and non-publicized issues as a wholeness. We analyzed a corpus of French and international environmental law foundation texts and Corporate Social Responsibility (CSR) reports, and reconstructed some of the contents of this crisis. As we had three research objectives, we combined three methods of analysis. The first, a quantitative method, allowed us to define the themes of the environmental crisis. The objective of the second, a qualitative discourse analysis method, was to identify and describe the different strategies used by the different issuers of both institutional texts and CSR reports. Finally, narrative and cultural semiotics facilitated the comprehension of the organization of environmental representations, by reconstructing the underlying narratives behind the environmental crisis discourses
Zalachori, Ioanna. "Prévisions hydrologiques d'ensemble : développements pour améliorer la qualité des prévisions et estimer leur utilité". Phd thesis, AgroParisTech, 2013. http://pastel.archives-ouvertes.fr/pastel-00927676.
Texto completoBalazard, Félix. "Contributions à la génétique et l'épidémiologie des maladies complexes pour une médecine personnalisée". Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS380.
Texto completoThis thesis concerns the identification of the genetic and environmental causes of complex diseases. Our central application is Isis-Diab a study of type 1 diabetes. We propose a method to use phase information to improve genetic risk predictions. We replicate an estimate of genetic risk on Isis-Diab patients. We prove an asymptotic equivalence result between two paired data analysis methods. We then analyze the Isis-Diab case-control study based on environmental questionnaires. We try to confirm the results of this study by crossing the genetic risk and environemental factors in Isis-Diab patients. This leads us to propose a new methodology based on collider bias and a study of its influence in case-only studies for gene-environment interactions. Finally, we study the possibility of using randomized clinical trials to personalize treatments. We propose a new methodology to evaluate the benefit of personalization and we recommend a choice of personalization strategy