In this thesis, a discrete Markov chain model for analyzing memory interference in multiprocessors, is presented.

This project applies statistical inference methods to energy data from the island of Luzon in the Philippines. The goal of the project is to explore different ways of creating predictive models and to understand the assumptions that are made about reality when a certain model is selected. The main models discussed in the project are Simple Linear Regression and Markov Chain Models. The predictions were used to assess Luzon's progress towards the sustainable development goals. All models considered in this project suggest that they are not on target to meet the sustainability goal.

Our objective is to monitor the changes in a proportion with correlated binary observations. All of the published work on this subject used the first-order Markov chain model for the data. Increasing the order of dependence above one by extending a standard Markov chain model entails an exponential increase of both the number of parameters and the dimension of the transition probability matrix. In this dissertation, we develop a particular Markov chain structure, the Multilevel Model (MLM), to model the correlation between binary data. The basic idea is to assign a lower probability to observing a 1 when all previous correlated observations are 0's, and a higher probability to observing a 1 as the last observed 1 gets closer to the current observation. We refer to each of the distinct situations of observing a 1 as a "level". For a given order of dependence, , at most different values of conditional probabilities of observing a 1 can be assigned. So the number of levels is always less than or equal to . Compared to a direct extension of the first-order Markov model to higher orders, our model is considerably parsimonious. The number of parameters for the MLM is only one plus the number of levels, and the transition probability matrix is . We construct a CUSUM control chart for monitoring a proportion with correlated binary observations. First, we use the probability structure of a first-order Markov chain to derive a log-likelihood ratio based CUSUM control statistic. Then, we model this CUSUM statistic itself as a Markov chain, which in turn allows for designing a control chart with specified statistical properties: the Markov Binary CUSUM (MBCUSUM) chart. We generalize the MBCUSUM to account for any order of dependence between binary observations through implying MLM to the data and to our CUSUM control statistic. We verify that the MBCUSUM has a better performance than a curtailed Shewhart chart. Also, we show that except for extremely large changes in the proportion (of interest) the MBCUSUM control chart detects the changes faster than the Bernoulli CUSUM control chart, which is designed for independent observations. / Ph. D.

Le problème de la restauration est rencontré dans domaines très variés notamment en traitement de signal et de l'image. Il correspond à la récupération des données originales à partir de données observées. Dans le cas de données multidimensionnelles, la résolution de ce problème peut se faire par différentes approches selon la nature des données, l'opérateur de transformation et la présence ou non de bruit. Dans ce travail, nous avons traité ce problème, d'une part, dans le cas des données discrètes en présence de bruit. Dans ce cas, le problème de restauration est analogue à celui de la segmentation. Nous avons alors exploité les modélisations dites chaînes de Markov couples et triplets qui généralisent les chaînes de Markov cachées. L'intérêt de ces modèles réside en la possibilité de généraliser la méthode de calcul de la probabilité à posteriori, ce qui permet une segmentation bayésienne. Nous avons considéré ces méthodes pour des observations bi-dimensionnelles et nous avons appliqué les algorithmes pour une séparation sur des documents issus de manuscrits scannés dans lesquels les textes des deux faces d'une feuille se mélangeaient. D'autre part, nous avons attaqué le problème de la restauration dans un contexte de séparation aveugle de sources. Une méthode classique en séparation aveugle de sources, connue sous l'appellation "Analyse en Composantes Indépendantes" (ACI), nécessite l'hypothèse d'indépendance statistique des sources. Dans des situations réelles, cette hypothèse n'est pas toujours vérifiée. Par conséquent, nous avons étudié une extension du modèle ACI dans le cas où les sources peuvent être statistiquement dépendantes. Pour ce faire, nous avons introduit un processus latent qui gouverne la dépendance et/ou l'indépendance des sources. Le modèle que nous proposons combine un modèle de mélange linéaire instantané tel que celui donné par ACI et un modèle probabiliste sur les sources avec variables cachées. Dans ce cadre, nous montrons comment la technique d'Estimation Conditionnelle Itérative permet d'affaiblir l'hypothèse usuelle d'indépendance en une hypothèse d'indépendance conditionnelle / The restoration problem is usually encountered in various domains and in particular in signal and image processing. It consists in retrieving original data from a set of observed ones. For multidimensional data, the problem can be solved using different approaches depending on the data structure, the transformation system and the noise. In this work, we have first tackled the problem in the case of discrete data and noisy model. In this context, the problem is similar to a segmentation problem. We have exploited Pairwise and Triplet Markov chain models, which generalize Hidden Markov chain models. The interest of these models consist in the possibility to generalize the computation procedure of the posterior probability, allowing one to perform bayesian segmentation. We have considered these methods for two-dimensional signals and we have applied the algorithms to retrieve of old hand-written document which have been scanned and are subject to show through effect. In the second part of this work, we have considered the restoration problem as a blind source separation problem. The well-known "Independent Component Analysis" (ICA) method requires the assumption that the sources be statistically independent. In practice, this condition is not always verified. Consequently, we have studied an extension of the ICA model in the case where the sources are not necessarily independent. We have introduced a latent process which controls the dependence and/or independence of the sources. The model that we propose combines a linear instantaneous mixing model similar to the one of ICA model and a probabilistic model on the sources with hidden variables. In this context, we show how the usual independence assumption can be weakened using the technique of Iterative Conditional Estimation to a conditional independence assumption

Many animal groups benefit from making decisions collectively. For example, colonies of many ant species are able to select the best possible nest to move into without every ant needing to visit each available nest site. Similarly, honey bee colonies can focus their foraging resources on the best possible food sources in their environment by sharing information with each other. In the same way, groups of human individuals are often able to make better decisions together than each individual group member can on his or her own. This phenomenon is known as "collective intelligence", or "wisdom of crowds." What unites all these examples is the fact that there is no centralized organization dictating how animal groups make their decisions. Instead, these successful decisions emerge from interactions and information transfer between individual members of the group and between individuals and their environment. In this thesis, I apply mathematical modeling techniques in order to better understand how groups of social animals make important decisions in situations where no single individual has complete information. This thesis consists of five papers, in which I collaborate with biologists and sociologists to simulate the results of their experiments on group decision-making in animals. The goal of the modeling process is to better understand the underlying mechanisms of interaction that allow animal groups to make accurate decisions that are vital to their survival. Mathematical models also allow us to make predictions about collective decisions made by animal groups that have not yet been studied experimentally or that cannot be easily studied. The combination of mathematical modeling and experimentation gives us a better insight into the benefits and drawbacks of collective decision making, and into the variety of mechanisms that are responsible for collective intelligence in animals. The models that I use in the thesis include differential equation models, agent-based models, stochastic models, and spatially explicit models. The biological systems studied included foraging honey bee colonies, house-hunting ants, and humans answering trivia questions.

In this paper, we investigate three particular algorithms: A sto- chastic simulation algorithm (SSA), and explicit and implicit tau-leaping al- gorithms. To compare these methods, we used them to analyze two infection models: A Vancomycin-resistant enterococcus (VRE) infection model at the population level, and a Human Immunode ciency Virus (HIV) within host in- fection model. While the rst has a low species count and few transitions, the second is more complex with a comparable number of species involved. The relative effciency of each algorithm is determined based on computational time and degree of precision required. The numerical results suggest that all three algorithms have the similar computational effciency for the simpler VRE model, and the SSA is the best choice due to its simplicity and accuracy. In addition, we have found that with the larger and more complex HIV model, implementation and modication of tau-Leaping methods are preferred.

In this paper, we examine the feasibility of extending the Akaike information criterion (AIC) for deterministic systems as a potential model selection criteria for stochastic models. We discuss the implementation method for three different classes of stochastic models: continuous time Markov chains (CTMC), stochastic differential equations (SDE), and random differential equations (RDE). The effectiveness and limitations of implementing the AIC for comparison of stochastic models is demonstrated using simulated data from the three types of models and then applied to experimental longitudinal growth data for algae.