Ce manuscrit est dédié à l’analyse de performances en traitement d’antenne pour l’estimation des paramètres d’intérêt à l’aide d’un réseau de capteurs. Il est divisé en deux parties :– Tout d’abord, nous présentons l’étude de certaines bornes inférieures de l’erreur quadratique moyenne liées à la localisation de sources dans le contexte champ proche. Nous utilisons la borne de Cramér-Rao pour l’étude de la zone asymptotique (notamment en terme de rapport signal à bruit avec un nombre fini d’observations). Puis, nous étudions d’autres bornes inférieures de l’erreur quadratique moyenne qui permettent de prévoir le phénomène de décrochement de l’erreur quadratique moyenne des estimateurs (on cite, par exemple, la borne de McAulay-Seidman, la borne de Hammersley-Chapman-Robbins et la borne de Fourier Cramér-Rao).– Deuxièmement, nous nous concentrons sur le concept du seuil statistique de résolution limite, c’est-à-dire, la distance minimale entre deux signaux noyés dans un bruit additif qui permet une ”correcte” estimation des paramètres. Nous présentons quelques applications bien connues en traitement d’antenne avant d’étendre les concepts existants au cas de signaux multidimensionnels. Par la suite, nous étudions la validité de notre extension en utilisant un test d’hypothèses binaire. Enfin, nous appliquons notre extension à certains modèles d’observation multidimensionnels / This manuscript concerns the performance analysis in array signal processing. It can bedivided into two parts :- First, we present the study of some lower bounds on the mean square error related to the source localization in the near eld context. Using the Cramér-Rao bound, we investigate the mean square error of the maximum likelihood estimator w.r.t. the direction of arrivals in the so-called asymptotic area (i.e., for a high signal to noise ratio with a nite number of observations.) Then, using other bounds than the Cramér-Rao bound, we predict the threshold phenomena.- Secondly, we focus on the concept of the statistical resolution limit (i.e., the minimum distance between two closely spaced signals embedded in an additive noise that allows a correct resolvability/parameter estimation.) We de ne and derive the statistical resolution limit using the Cramér-Rao bound and the hypothesis test approaches for the mono-dimensional case. Then, we extend this concept to the multidimensional case. Finally, a generalized likelihood ratio test based framework for the multidimensional statistical resolution limit is given to assess the validity of the proposed extension.

The study examines the dynamic relationship between financial development and investment in three Southern African countries (Botswana, South Africa and Mauritius) during the period 1976 – 2014 using annual data. The motivation for selecting these countries is mainly based on their different characteristics in their economic and financial structure. Employing the Autoregressive Distributed Lag (ARDL) bounds test approach, the study examines the role of financial development in boosting investment; and the causal relationship between financial development and investment. The study makes use of composite financial development indices and divides financial development into bank-based and market-based financial development. In addition, both the impact of bank- and market-based financial development on investment, on the one hand; and the causality between bank- and market-based financial development and investment, on the other, were examined within the flexible accelerator model/framework. For both models, both bank-based and market-based financial development are assumed as having an accelerator-enhancing effect on investment. Empirical results show that, for Botswana, the impact of bank-based financial development on investment is positive in both the short run and the long run while no impact of market-based financial development is found for both periods. For South Africa, the effect of bank-based financial development on investment is found to be negative in the short run and has no impact in the long run. However, market-based financial development has only a positive effect on investment in the long run. For Mauritius, market-based financial development is the only type of financial development found to have a significant positive effect on investment, and only, in the short run. The results of the causality test show that: for Mauritius, both bank-based and market-based financial development tend to drive investment, both in the short run and in the long run; while- in South Africa, investment drives both bank-based and market-based financial development only in the short run. In Botswana, bank-based and market-based financial development and investment drive each other in the short run while investment tends to only drive bank-based financial development in the long run. Therefore, all three countries show differing results and tend to confirm that there are inter-country differences that determine the relationship between investment and financial development. The inter-country differences maybe as a result of the different stages of financial and economic development for each country. / Economics / D. Phil. (Economics)

A dissertação aborda e compara as características dos índices de Sharpe (SR) e suas variantes, SRc e SRd, Sharpe generalizado (GSR ) e potencial de investimento (IP), sendo os índices GSR e IP associados a alguma função de utilidade. Pelo fato de o GSR e o IP serem idênticos, testes empíricos foram realizados entre SRc e o GSR. Ambos foram avaliados teoricamente sob dois aspectos, o que definimos de análise retrospectiva, i.e., análise de séries de log-retornos mensais observados, e a análise prospectiva, i.e., séries a ocorrer. No âmbito prospectivo, ex ante facto, o SRc (índice de Sharpe com variável de estado normal) e o SRd (índice de Sharpe com variável de estado lognormal), por estarem associados à função de utilidade quadrática, apresentam distorções como o ponto bliss e o agente econômico bomba de dinheiro. O mesmo ocorre no âmbito retrospectivo, ex post facto, com o GSR (potencial de desempenho de ativos de risco para indivíduos com função de utilidade HARA) quando o coeficiente de aversão ao risco é igual a um negativo, gama=-1. No entanto, o GSR pode ser associado a funções de utilidade diferentes da quadrática evitando seus efeitos indesejáveis. Sob a suposição de movimento browniano geométrico (MBG) e da utilidade HARA para o preço mensal ajustado de ações brasileiras e americanas e para pontos mensais de índices brasileiros e americanos, entre janeiro de 2000 e março de 2008, obtivemos os seguintes resultados: (1) o índice GSR para utilidade quadrática apresentou elevada correlação com o SRc; (2) a menor correlação de GSR com SRc ocorreu para utilidade logarítmica; (3) para a utilidade exponencial, o GSR apresenta elevado grau de correlação com o SRc. Os resultados mostraram que o GSR com utilidade exponencial é o índice que menos se aproxima do comportamento do GSR com utilidade quadrática. Sabendo-se das distorções da utilidade quadrática, a adoção do GSR com gama=1 parece mais adequado para a classificação de ativos de risco. / This master dissertation studies and compares the characteristics of Sharpe ratio and its variants, SRc and SRd, generalized Sharpe ratio (GSR) and investment potential (IP), both GSR and IP associated to any utility function. By the fact that GSR and IP are identical indexes, empiric tests were conducted between SRc and GSR. The indexes were evaluated theoretically under two different aspects: retrospective analysis, i.e., analyze the observed monthly log-returns, and prospective analysis, i.e., series to occur. Under prospective view, ex ante facto, SRc (Sharpe ratio with normal state variable) and SRd (Sharpe ratio with lognormal state variable), for being associated to the quadratic utility function, show the inherent problems to utility functions such as the bliss point and the pump money economic agent. The same happens in a retrospective view, ex post facto, with the GSR (performance potential with HARA utility function family) when the risk aversion coefficient equals minus one, gama=-1. Therefore, the GSR can be associated to different utility functions avoiding the undesirable effects. Under the GBM (geometric Brownian motion) condition and HARA utility function for the Brazilian and American adjusted monthly stock prices and indexes monthly points during January 2000 and March 2008, we reached the following: (1) results indicate that GSR for quadratic utility has high correlation level with SRc; (2) while the logarithmic utility showed lowest correlation level between GSR and SRc; (3) exponential utilities showed a high level of correlation between GSR and SRc. The results showed that GSR with exponential utility kept the biggest behavior difference for the GSR with quadratic utility. Based on the knowing problems of the quadratic utility, GSR with gama=1 seems to be a better index choice for risk assets classification.

This study uses annual data for the period 1975-2014 for South Africa and Botswana, and 1979-2013 for Lesotho to examine empirically the impact of trade openness on economic growth in these three South African Customs Union (SACU) countries. The motivation for this study is that SACU countries are governed by the common agreement for the union that oversees the movement of goods that enter the SACU area. However, although these countries are in a com-mon union, they have quite different levels of development. Based on the country’s level of development, Lesotho is a lower middle-income and least developed country, whereas Botswana and South Africa are upper middle-income economies. Thus, these disparities in the levels of economic development of SACU countries i are expected to have different implications in relation to the extent to which trade openness affects economic growth. It is within this background that the current study seeks to examine what impact trade openness has on economic growth in each of the three selected countries. To check the robustness of the empirical results, this study uses four equations based on four different indicators of trade openness to examine the linkage between trade openness and economic growth. While Equation 1, Equation 2 and Equation 3 employ trade-based indicators of openness, Equation 4 uses a modified version of the UNCTAD (2012a) trade openness index that incorporates differences in country size and geography. Using the autoregressive distributed lag (ARDL) bounds testing approach to cointegration and error-correction modelling, the study found that the impact of trade openness on economic growth varies across the three SACU countries. Based on the results for the first three equations, the study found that trade openness has a positive impact on economic growth in South Africa and Botswana, whereas it has no significant impact on economic growth in Lesotho. Based on Equation 4 results, the study found that after taking the differences in country size and geography into account, trade openness has a positive impact on economic growth in Botswana, but an insignificant impact in South Africa and Lesotho. For South Africa and Botswana, the main recommendation from this study is that policy makers should pursue policies that promote total trade to increase economic growth in both the short and the long run. For Lesotho, the study recommends, among other things, the adoption of policies aimed at enhancing human capital and infrastructural development as well as the broadening of exports, so as to enable the economy to grow to a threshold level necessary for the realisation of significant gains from trade. / Economics / Ph. D. (Economics)

Using 1980 - 2012 annual data, the study empirically investigates the dynamic relationship between financial development and economic growth in three developing countries (South Africa, Brazil and Kenya) and three developed countries (United States of America, United Kingdom and Australia). The study was motivated by the current debate regarding the role of financial development in the economic growth process, and their causal relationship. The debate centres on whether financial development impacts positively or negatively on economic growth and whether it Granger-causes economic growth or vice versa. To this end, two models have been used. In Model 1 the impact of bank- and market-based financial development on economic growth is examined, while in Model 2 it is the causality between the two that is explored. Using the autoregressive distributed lag (ARDL) bounds testing approach to cointegration and error-correction based causality test, the results were found to differ from country to country and over time. These results were also found to be sensitive to the financial development proxy used. Based on Model 1, the study found that the impact of bank-based financial development on economic growth is positive in South Africa and the USA, but negative in the U.K – and neither positive nor negative in Kenya. Elsewhere the results were inconclusive. Market-based financial development was found to impact positively in Kenya, USA and the UK but not in the remaining countries. Based on Model 2, the study found that bank-based financial development Granger-causes economic growth in the UK, while in Brazil they Granger-cause each other. However, in South Africa, Kenya and USA no causal relationship was found. In Australia the results were inconclusive. The study also found that in the short run, market-based financial development Granger-causes economic growth in the USA but that in South Africa and Brazil, the reverse applies. On the other hand bidirectional causality was found to prevail in Kenya in the same period. / Economics / D. Com. (Economics)

Studying the internal characteristics of a network using measurements obtained from endhosts is known as network tomography. The foremost challenge in measurement-based approaches is the large size of a network, where only a subset of measurements can be obtained because of the inaccessibility of the entire network. As the network becomes larger, a question arises as to how rapidly the monitoring resources (number of measurements or number of samples) must grow to obtain a desired monitoring accuracy. Our work studies the scalability of the measurements with respect to the size of the network. We investigate the issues of scalability and performance evaluation in IP networks, specifically focusing on fault and congestion diagnosis. We formulate network monitoring as a machine learning problem using probabilistic graphical models that infer network states using path-based measurements. We consider the theoretical and practical management resources needed to reliably diagnose congested/faulty network elements and provide fundamental limits on the relationships between the number of probe packets, the size of the network, and the ability to accurately diagnose such network elements. We derive lower bounds on the average number of probes per edge using the variational inference technique proposed in the context of graphical models under noisy probe measurements, and then propose an entropy lower (EL) bound by drawing similarities between the coding problem over a binary symmetric channel and the diagnosis problem. Our investigation is supported by simulation results. For the congestion diagnosis case, we propose a solution based on decoding linear error control codes on a binary symmetric channel for various probing experiments. To identify the congested nodes, we construct a graphical model, and infer congestion using the belief propagation algorithm. In the second part of the work, we focus on the development of methods to automatically analyze the information contained in electron tomograms, which is a major challenge since tomograms are extremely noisy. Advances in automated data acquisition in electron tomography have led to an explosion in the amount of data that can be obtained about the spatial architecture of a variety of biologically and medically relevant objects with sizes in the range of 10-1000 nm A fundamental step in the statistical inference of large amounts of data is to segment relevant 3D features in cellular tomograms. Procedures for segmentation must work robustly and rapidly in spite of the low signal-to-noise ratios inherent in biological electron microscopy. This work evaluates various denoising techniques and then extracts relevant features of biological interest in tomograms of HIV-1 in infected human macrophages and Bdellovibrio bacterial tomograms recorded at room and cryogenic temperatures. Our approach represents an important step in automating the efficient extraction of useful information from large datasets in biological tomography and in speeding up the process of reducing gigabyte-sized tomograms to relevant byte-sized data. Next, we investigate automatic techniques for segmentation and quantitative analysis of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscope, and tomograms of Liposomal Doxorubicin formulations (Doxil), an anticancer nanodrug, imaged at cryogenic temperatures. A machine learning approach is formulated that exploits texture features, and joint image block-wise classification and segmentation is performed by histogram matching using a nearest neighbor classifier and chi-squared statistic as a distance measure.

No description available.

Le domaine lié à ce travail est appelé « désagrégation d’énergie », où la principale préoccupation est de décomposer, ou désagréger, la consommation globale d’énergie électrique (par exemple, la consommation de tout un ménage) en une consommation détaillée donnée comme information de consommation par usage (par exemple, par appareil). Cette dernière permet d’avoir un retour sur la consommation pour les consommateurs ainsi que pour les fournisseurs et est utile pour permettre des économies d’énergie. Dans ce domaine de désagrégation d’énergie, il existe trois grandes questions auxquelles il faut répondre : qui consomme ? quand ? et combien ? Les recherches menées dans cette thèse se concentrent sur l’identification des appareils électriques, c’est-à-dire la réponse à la première question, en considérant particulièrement des appareils ménagers. À cet effet, nous utilisons le courant transitoire de mise en marche que nous modélisons en utilisant un nouveau modèle que nous avons proposé. De plus, nous utilisons les paramètres estimés de ce dernier pour la tâche d’identification. / The related field to this work is called “energy disaggregation" where the main concern is to break down, or disaggregate, the global electrical energy consumption (e.g. wholehouse consumption) into a detailed consumption given as end-use (e.g. appliance-level) consumption information. This latter gives consumption feedback to consumers and electricity providers and is helpful for energy savings. Three main questions have to be answered in the energy disaggregation field : who is consuming ? when ? and how much ? The research conducted in this thesis focuses on electrical appliances identification, i.e. the who question, considering particularly home appliances. For this purpose, we use the turn-on transient current signal which we model using a new model we proposed and use its estimated model parameters for the identification task.

Dans le cadre de cette thèse, nous traitons le problème de flow-shop à deux machines avec temps de transport où l’objectif consiste à minimiser le temps de complétion maximal. Dans un premier temps, nous nous sommes intéressés à la modélisation de ce problème. Nous avons proposé plusieurs programmes linéaires en nombres entiers. En particulier, nous avons introduit une formulation linéaire basée sur une généralisation non triviale du modèle d’affectation pour le cas où les durées des opérations sur une même machine sont identiques. Dans un deuxième temps, nous avons élargi la portée de ces formulations mathématiques pour développer plusieurs bornes inférieures et un algorithme exact basé sur la méthode de coupe et branchement (Branch-and-Cut). En effet, un ensemble d’inégalités valides a été considéré afin d’améliorer la relaxation linéaire de ces programmes et d’accélérer leur convergence. Ces inégalités sont basées sur la proposition de nouvelles règles de dominance et l’identification de sous-instances faciles à résoudre. L’identification de ces sous-instances revient à déterminer les cliques maximales dans un graphe d’intervalles. En plus des inégalités valides, la méthode exacte proposée inclut la considération d’une méthode heuristique et d’une procédure visant à élaguer les nœuds. Enfin, nous avons proposé un algorithme par séparation et évaluation (Branch-and-Bound) pour lequel, nous avons introduit des règles de dominance et une méthode heuristique basée sur la recherche locale. Nos expérimentations montrent l’efficacité de nos approches qui dominent celles de la littérature. Ces expérimentations ont été conduites sur plusieurs classes d’instances qui incluent celles de la littérature, ainsi que des nouvelles classes d’instances où les algorithmes de la littérature se sont montrés peu efficaces. / In this thesis, we study the two-machine flow-shop problem with time delays in order to minimize the makespan. First, we propose a set of Mixed Integer Programming (MIP) formulations for the problem. In particular, we introduce a new compact mathematical formulation for the case where operations are identical per machine. The proposed mathematical formulations are then used to develop lower bounds and a branch-and-cut method. A set of valid inequalities is proposed in order to improve the linear relaxation of the MIPs. These inequalities are based on proposing new dominance rules and computing optimal solutions of polynomial-time-solvable sub-instances. These sub-instances are extracted by computing all maximal cliques on a particular Interval graph. In addition to the valid inequalities, the branch-and-cut method includes the consideration of a heuristic method and a node pruning procedure. Finally, we propose a branch-and-bound method. For which, we introduce a local search-based heuristic and dominance rules. Experiments were conducted on a variety of classes of instances including both literature and new proposed ones. These experiments show the efficiency of our approaches that outperform the leading methods published in the research literature.

A dissertação aborda e compara as características dos índices de Sharpe (SR) e suas variantes, SRc e SRd, Sharpe generalizado (GSR ) e potencial de investimento (IP), sendo os índices GSR e IP associados a alguma função de utilidade. Pelo fato de o GSR e o IP serem idênticos, testes empíricos foram realizados entre SRc e o GSR. Ambos foram avaliados teoricamente sob dois aspectos, o que definimos de análise retrospectiva, i.e., análise de séries de log-retornos mensais observados, e a análise prospectiva, i.e., séries a ocorrer. No âmbito prospectivo, ex ante facto, o SRc (índice de Sharpe com variável de estado normal) e o SRd (índice de Sharpe com variável de estado lognormal), por estarem associados à função de utilidade quadrática, apresentam distorções como o ponto bliss e o agente econômico bomba de dinheiro. O mesmo ocorre no âmbito retrospectivo, ex post facto, com o GSR (potencial de desempenho de ativos de risco para indivíduos com função de utilidade HARA) quando o coeficiente de aversão ao risco é igual a um negativo, gama=-1. No entanto, o GSR pode ser associado a funções de utilidade diferentes da quadrática evitando seus efeitos indesejáveis. Sob a suposição de movimento browniano geométrico (MBG) e da utilidade HARA para o preço mensal ajustado de ações brasileiras e americanas e para pontos mensais de índices brasileiros e americanos, entre janeiro de 2000 e março de 2008, obtivemos os seguintes resultados: (1) o índice GSR para utilidade quadrática apresentou elevada correlação com o SRc; (2) a menor correlação de GSR com SRc ocorreu para utilidade logarítmica; (3) para a utilidade exponencial, o GSR apresenta elevado grau de correlação com o SRc. Os resultados mostraram que o GSR com utilidade exponencial é o índice que menos se aproxima do comportamento do GSR com utilidade quadrática. Sabendo-se das distorções da utilidade quadrática, a adoção do GSR com gama=1 parece mais adequado para a classificação de ativos de risco. / This master dissertation studies and compares the characteristics of Sharpe ratio and its variants, SRc and SRd, generalized Sharpe ratio (GSR) and investment potential (IP), both GSR and IP associated to any utility function. By the fact that GSR and IP are identical indexes, empiric tests were conducted between SRc and GSR. The indexes were evaluated theoretically under two different aspects: retrospective analysis, i.e., analyze the observed monthly log-returns, and prospective analysis, i.e., series to occur. Under prospective view, ex ante facto, SRc (Sharpe ratio with normal state variable) and SRd (Sharpe ratio with lognormal state variable), for being associated to the quadratic utility function, show the inherent problems to utility functions such as the bliss point and the pump money economic agent. The same happens in a retrospective view, ex post facto, with the GSR (performance potential with HARA utility function family) when the risk aversion coefficient equals minus one, gama=-1. Therefore, the GSR can be associated to different utility functions avoiding the undesirable effects. Under the GBM (geometric Brownian motion) condition and HARA utility function for the Brazilian and American adjusted monthly stock prices and indexes monthly points during January 2000 and March 2008, we reached the following: (1) results indicate that GSR for quadratic utility has high correlation level with SRc; (2) while the logarithmic utility showed lowest correlation level between GSR and SRc; (3) exponential utilities showed a high level of correlation between GSR and SRc. The results showed that GSR with exponential utility kept the biggest behavior difference for the GSR with quadratic utility. Based on the knowing problems of the quadratic utility, GSR with gama=1 seems to be a better index choice for risk assets classification.