The made-up software let to construct the cylindrical shell with composition in laminate by chosen test (reinforcement’s corner, number of shells), also it offer to simulate a reliability of construction and to optimise it by chosen in statistic parameters. Shell’s parameters can be evaluated like episodic variables, which are modulated with Monte - Carlo method. There is given opportunity to evaluate construction’s reliability: of the supposition that distribution of strain at shell is known, construction can be optimised when we are minimizing mass. If we want to show construction’s distribution of limitary state in dotted chart, we have to model strain’s value in every Monte – Carlo step. It is computed factors, which have influence for shell’s strain in construction’s stability. In such succession of operations is controlled the reliability of model’s evaluation. There are analysed parameters, which have the biggest influence for strain at shell. Studied the minimal shell’s mass fluctuation in dependence with dispersion and also parameter’s, of construction strain, overtop probability.

Image segmentation is important with applications to several problems in biology and medicine. While extensively researched, generally, current segmentation methods perform adequately in the applications for which they were designed, but often require extensive modifications or calibrations before used in a different application. We describe a system that, with few modifications, can be used in a variety of image segmentation problems. The system is based on a supervised learning strategy that utilizes intensity neighborhoods to assign each pixel in a test image its correct class based on training data. In summary, we have several innovations: (1) A general framework for such a system is proposed, where rotations and variations of intensity neighborhoods in scales are modeled, and a multi-scale classification framework is utilized to segment unknown images; (2) A fast algorithm for training data selection and pixel classification is presented, where a majority voting based criterion is proposed for selecting a small subset from raw training set. When combined with 1-nearest neighbor (1-NN) classifier, such an algorithm is able to provide descent classification accuracy within reasonable computational complexity. (3) A general deformable model for optimization of segmented regions is proposed, which takes the decision values from previous pixel classification process as input, and optimize the segmented regions in a partial differential equation (PDE) framework. We show that the performance of this system in several different biomedical applications, such as tissue segmentation tasks in magnetic resonance and histopathology microscopy images, as well as nuclei segmentation from fluorescence microscopy images, is similar or better than several algorithms specifically designed for each of these applications. In addition, we describe another general segmentation system for biomedical applications where a strong prior on shape is available (e.g. cells, nuclei). The idea is based on template matching and supervised learning, and we show the examples of segmenting cells and nuclei from microscopy images. The method uses examples selected by a user for building a statistical model which captures the texture and shape variations of the nuclear structures from a given data set to be segmented. Segmentation of subsequent, unlabeled, images is then performed by finding the model instance that best matches (in the normalized cross correlation sense) local neighborhood in the input image. We demonstrate the application of our method to segmenting cells and nuclei from a variety of imaging modalities, and quantitatively compare our results to several other methods. Quantitative results using both simulated and real image data show that, while certain methods may work well for certain imaging modalities, our software is able to obtain high accuracy across several imaging modalities studied. Results also demonstrate that, relative to several existing methods, the template based method we propose presents increased robustness in the sense of better handling variations in illumination, variations in texture from different imaging modalities, providing more smooth and accurate segmentation borders, as well as handling better cluttered cells and nuclei.

efeitos são frequentemente observados na morbidade e mortalidade por doenças respiratórias e cardiovasculares, câncer de pulmão, diminuição da função respiratória, absenteísmo escolar e problemas relacionados com a gravidez. Estudos também sugerem que os grupos mais suscetíveis são as crianças e os idosos. Esta tese apresenta estudos sobre o efeito da poluição do ar na saúde na saúde na cidade do Rio de Janeiro e aborda aspectos metodológicos sobre a análise de dados e imputação de dados faltantes em séries temporais epidemiológicas. A análise de séries temporais foi usada para estimar o efeito da poluição do ar na mortalidade de pessoas idosas por câncer de pulmão com dados dos anos 2000 e 2001. Este estudo teve como objetivo avaliar se a poluição do ar está associada com antecipação de óbitos de pessoas que já fazem parte de uma população de risco. Outro estudo foi realizado para avaliar o efeito da poluição do ar no baixo peso ao nascer de nascimentos a termo. O desenho deste estudo foi o de corte transversal usando os dados disponíveis no ano de 2002. Em ambos os estudos foram estimados efeitos moderados da poluição do ar. Aspectos metodológicos dos estudos epidemiológicos da poluição do ar na saúde também são abordados na tese. Um método para imputação de dados faltantes é proposto e implementado numa biblioteca para o aplicativo R. A metodologia de imputação é avaliada e comparada com outros métodos frequentemente usados para imputação de séries temporais de concentrações de poluentes atmosféricos por meio de técnicas de simulação. O método proposto apresentou desempenho superior aos tradicionalmente utilizados. Também é realizada uma breve revisão da metodologia usada nos estudos de séries temporais sobre os efeitos da poluição do ar na saúde. Os tópicos abordados na revisão estão implementados numa biblioteca para a análise de dados de séries temporais epidemiológicas no aplicativo estatístico R. O uso da biblioteca é exemplificado com dados de internações hospitalares de crianças por doenças respiratórias no Rio de Janeiro. Os estudos de cunho metodológico foram desenvolvidos no âmbito do estudo multicêntrico para avaliação dos efeitos da poluição do ar na América Latina o Projeto ESCALA. / Air pollution is a public health problem in major urban areas and its effects are frequently observed in the morbidity and mortality due respiratory and cardiovascular causes, lung cancer, decreasing in the respiratory function, school absenteeism, and pregnancy outcomes. This thesis presents studies on the effects of air pollution on health in the Rio de Janeiro city and tackle some methodological issues on data analysis and missing data imputation in epidemiologic time series. Daily time series were used to estimate the effect of the air pollution on deaths among the elderly due to lung cancer during 2000 and 2001. The purpose of the study was to evaluate if air pollution is associated with premature deaths of people that already are in risk population. Another study was conducted to assess the relationship between air pollution and low birth weight of singleton full term babies. A crosssectional design was used on data available during the year 2002. Moderate effects of the air pollution were estimated in both studies. Methodological aspects of epidemiologic studies on air pollution are also approached. A data imputation method is presented and implemented as library for the statistical package R. The imputation methodology is evaluated and compared to others often used for data imputation in time series of air pollutant concentrations, through simulation techniques. The proposed method has shown best performance compared to those traditionally used. A brief review on the methodology used in the time series studies on the effects of air pollution on health is also presented. The issues approached in the review are also implemented as a library for the analysis of epidemiologic time series in R. The use of the library is exemplified with the analysis on the data of hospital admissions of children due to respiratory causes in the city of Rio de Janeiro. The methodological studies were carried out under the umbrella of the multi-city study to assess the effects of air pollution on health in the Latin America the ESCALA Project.

La part dû au test dans le coût de conception et de fabrication des circuits intégrés ne cesse de croître, d'où la nécessité d'optimiser cette étape devenue incontournable. Dans cette thèse, de nouvelles méthodes d'ordonnancement et de réduction du nombre de tests à effectuer sont proposées. La solution est un ordre des tests permettant de détecter au plus tôt les circuits défectueux, qui pourra aussi être utilisé pour éliminer les tests redondants. Ces méthodes de test sont basées sur la modélisation statistique du circuit sous test. Cette modélisation inclus plusieurs modèles paramétriques et non paramétrique permettant de s'adapté à tous les types de circuit. Une fois le modèle validé, les méthodes de test proposées génèrent un grand échantillon contenant des circuits défectueux. Ces derniers permettent une meilleure estimation des métriques de test, en particulier le taux de défauts. Sur la base de cette erreur, un ordonnancement des tests est construit en maximisant la détection des circuits défectueux au plus tôt. Avec peu de tests, la méthode de sélection et d'évaluation est utilisée pour obtenir l'ordre optimal des tests. Toutefois, avec des circuits contenant un grand nombre de tests, des heuristiques comme la méthode de décomposition, les algorithmes génétiques ou les méthodes de la recherche flottante sont utilisées pour approcher la solution optimale. / The share of test in the cost of design and manufacture of integrated circuits continues to grow, hence the need to optimize this step. In this thesis, new methods of test scheduling and reducing the number of tests are proposed. The solution is a sequence of tests for early identification of faulty circuits, which can also be used to eliminate redundant tests. These test methods are based on statistical modeling of the circuit under test. This model included several parametric and non-parametric models to adapt to all types of circuit. Once the model is validated, the suggested test methods generate a large sample containing defective circuits. These allow a better estimation of test metrics, particularly the defect level. Based on this error, a test scheduling is constructed by maximizing the detection of faulty circuits. With few tests, the Branch and Bound method is used to obtain the optimal order of tests. However, with circuits containing a large number of tests, heuristics such as decomposition method, genetic algorithms or floating search methods are used to approach the optimal solution.

Made available in DSpace on 2016-06-02T19:50:10Z (GMT). No. of bitstreams: 1 3530.pdf: 3939391 bytes, checksum: 555a1e91c6d19c737e2b04d918e65d42 (MD5) Previous issue date: 2011-02-18 / Frequent changes in consumer behavior and the characteristics of complexity and competition involving the market demands constant innovation in products, technologies, management strategies and management systems, including the systems that make the integration between the company and its customers or suppliers, as well as systems that integrate or coordinate business processes. In this scenario, understanding and managing of the vendors and/or sales representatives of the company turn out to be an essential factor for the company to remain competitive in the market. In this light, the process of determining and allocating sales quotas appears as integral and important part of the sales management process, which allows, among other things, the evaluation of vendor performance toward the goals set by the company. The purpose of this thesis was to establish a set of procedures to forecast appropriately, sales in the footwear industry and from then on, build a model to determine sales quotas which meets the specific of a sector and integrate two important functions of the company: Sales and Production. Semi-structured interviews with sales professionals, as well as production planning and control were made to subsidize the development of the proposal. The evaluation of the proposal was made by means of a case study in a footwear company in the city of Franca (SP). It was concluded that demand management in the footwear industry, is connected to the quotas they should limit (directly or indirectly) to sales due to the production capacity available and the considered models, in this study, meet the criteria to the studied situation. / As frequentes mudanças no comportamento do consumidor e as características de complexidade e competição que envolvem o mercado demandam inovações constantes nos produtos, tecnologias, estratégias de gestão e sistemas de gestão, entre eles, os sistemas que fazem a integração entre a empresa e seus clientes ou fornecedores, bem como os sistemas que integram ou coordenam processos da empresa. Neste cenário, a compreensão e administração dos vendedores e/ou representantes de vendas da empresa revelam-se um fator essencial para a empresa manter-se competitiva no mercado. Sob esta ótica, o processo de determinação e alocação de quotas de vendas aparece como parte integrante e importante do processo de gestão de vendas, o que permite, entre outras coisas, a avaliação do desempenho do vendedor em direção aos objetivos traçados pela empresa. A proposta desta tese foi estabelecer um conjunto de procedimentos para prever, de forma adequada, as vendas na indústria de calçados e, a partir daí, construir um modelo para determinar quotas de vendas o qual atenda as especificidades do setor e integre duas importantes funções da empresa: Vendas e Produção. Para subsidiar a elaboração da proposta foram feitas entrevistas semiestruturadas com profissionais de vendas e planejamento e controle da produção. A avaliação da proposta deu-se por meio de um estudo de caso em uma empresa de calçados da cidade de Franca (S.P). Concluiu-se que a gestão de demanda na indústria calçadista está atrelada às quotas que devem limitar (direta ou indiretamente) as vendas em função da capacidade de produção disponível, e os modelos propostos neste estudo atendem bem à situação estudada.

efeitos são frequentemente observados na morbidade e mortalidade por doenças respiratórias e cardiovasculares, câncer de pulmão, diminuição da função respiratória, absenteísmo escolar e problemas relacionados com a gravidez. Estudos também sugerem que os grupos mais suscetíveis são as crianças e os idosos. Esta tese apresenta estudos sobre o efeito da poluição do ar na saúde na saúde na cidade do Rio de Janeiro e aborda aspectos metodológicos sobre a análise de dados e imputação de dados faltantes em séries temporais epidemiológicas. A análise de séries temporais foi usada para estimar o efeito da poluição do ar na mortalidade de pessoas idosas por câncer de pulmão com dados dos anos 2000 e 2001. Este estudo teve como objetivo avaliar se a poluição do ar está associada com antecipação de óbitos de pessoas que já fazem parte de uma população de risco. Outro estudo foi realizado para avaliar o efeito da poluição do ar no baixo peso ao nascer de nascimentos a termo. O desenho deste estudo foi o de corte transversal usando os dados disponíveis no ano de 2002. Em ambos os estudos foram estimados efeitos moderados da poluição do ar. Aspectos metodológicos dos estudos epidemiológicos da poluição do ar na saúde também são abordados na tese. Um método para imputação de dados faltantes é proposto e implementado numa biblioteca para o aplicativo R. A metodologia de imputação é avaliada e comparada com outros métodos frequentemente usados para imputação de séries temporais de concentrações de poluentes atmosféricos por meio de técnicas de simulação. O método proposto apresentou desempenho superior aos tradicionalmente utilizados. Também é realizada uma breve revisão da metodologia usada nos estudos de séries temporais sobre os efeitos da poluição do ar na saúde. Os tópicos abordados na revisão estão implementados numa biblioteca para a análise de dados de séries temporais epidemiológicas no aplicativo estatístico R. O uso da biblioteca é exemplificado com dados de internações hospitalares de crianças por doenças respiratórias no Rio de Janeiro. Os estudos de cunho metodológico foram desenvolvidos no âmbito do estudo multicêntrico para avaliação dos efeitos da poluição do ar na América Latina o Projeto ESCALA. / Air pollution is a public health problem in major urban areas and its effects are frequently observed in the morbidity and mortality due respiratory and cardiovascular causes, lung cancer, decreasing in the respiratory function, school absenteeism, and pregnancy outcomes. This thesis presents studies on the effects of air pollution on health in the Rio de Janeiro city and tackle some methodological issues on data analysis and missing data imputation in epidemiologic time series. Daily time series were used to estimate the effect of the air pollution on deaths among the elderly due to lung cancer during 2000 and 2001. The purpose of the study was to evaluate if air pollution is associated with premature deaths of people that already are in risk population. Another study was conducted to assess the relationship between air pollution and low birth weight of singleton full term babies. A crosssectional design was used on data available during the year 2002. Moderate effects of the air pollution were estimated in both studies. Methodological aspects of epidemiologic studies on air pollution are also approached. A data imputation method is presented and implemented as library for the statistical package R. The imputation methodology is evaluated and compared to others often used for data imputation in time series of air pollutant concentrations, through simulation techniques. The proposed method has shown best performance compared to those traditionally used. A brief review on the methodology used in the time series studies on the effects of air pollution on health is also presented. The issues approached in the review are also implemented as a library for the analysis of epidemiologic time series in R. The use of the library is exemplified with the analysis on the data of hospital admissions of children due to respiratory causes in the city of Rio de Janeiro. The methodological studies were carried out under the umbrella of the multi-city study to assess the effects of air pollution on health in the Latin America the ESCALA Project.

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2017-12-21T11:52:32Z No. of bitstreams: 1 luisguilherrmedasilvacosta.pdf: 2910682 bytes, checksum: da61cee3e668dc7356aa3ab54ff0c28c (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-12-22T11:58:44Z (GMT) No. of bitstreams: 1 luisguilherrmedasilvacosta.pdf: 2910682 bytes, checksum: da61cee3e668dc7356aa3ab54ff0c28c (MD5) / Made available in DSpace on 2017-12-22T11:58:44Z (GMT). No. of bitstreams: 1 luisguilherrmedasilvacosta.pdf: 2910682 bytes, checksum: da61cee3e668dc7356aa3ab54ff0c28c (MD5) Previous issue date: 2017 / Esta tese de doutorado apresenta, inicialmente, uma revisão sobre acopladores para power line communication (PLC), utilizados para acoplar o sinal dos transceptores PLC à rede de energia elétrica. As questões predominantes para o projeto de acopladores e, consequentemente, os diferentes tipos de acopladores são discutidos. Uma classificação dos acopladores PLC baseada nos tipos de acoplamentos (capacitivo, indutivo, resistivo e por antenas), níveis de tensão, largura de banda de frequência, modos de propagação e números de conexões com a rede de energia elétrica é apresentada. Em seguida, o projeto de circuitos PLC de acoplamento capacitivo não adaptativos, single input single output (SISO) de baixa tensão para aplicações banda larga e banda estreita são discutidos. O acoplador PLC banda estreita é projetado para a banda de frequência de 9 kHz-500 kHz, enquanto os acopladores banda larga são projetados para a banda de frequência de 1.7-50 MHz, 1.7-100 MHz e 1.7-500 MHz. Além disso, discute-se as especificações e o projeto dos protótipos desses circuitos de acoplamento PLC medindo seus parâmetros de espalhamento. A seguir, é discutida a medida da impedância de acesso da rede de energia elétrica de baixa tensão na banda de frequência 2- 500 MHz, visando apresentar prévio conhecimento da impedância de acesso da rede de energia elétrica no Brasil com base em uma campanha de medição realizada em várias instalações em três cidades brasileiras diferentes. Além disso, é proposto um procedimento para obter um modelo estatístico da impedância de acesso na referida faixa de frequência. Com base em uma série de medidas de impedâncias de acesso da rede de energia elétrica e critérios para a escolha de modelos estatísticos, esta tese sugere duas distribuições para modelar as componentes resistência e reatância da impedância de acesso da rede de energia elétrica. Uma vez que, os parâmetros de tais modelos mudam com a frequência e que a impedância de acesso é um processo aleatório no domínio da frequência, um modelo simples para gerar amostras em função desse processo aleatório, que leva em consideração as distribuições sugeridas, é detalhado. Por fim, é proposto um circuito de acoplamento adaptativo PLC, capacitivo, SISO de baixa tensão. Estes circuitos de acoplamento adaptativos usam três diferentes filtros analógicos passa-baixa com diferentes impedâncias de entrada. A impedância de entrada de cada filtro analógico é projetado de acordo com os valores obtidos através da campanha de medição, e a impedância de saída é projetada para 50 Ω. A escolha do filtro analógico que proporciona melhor casamento de impedância com a rede de energia elétrica é obtido por um microcontrolador, que através de um conversor analógico digital, monitora a tensão fornecida por um circuito que mede a potência dos sinais injetados nos acopladores PLC pelos transceptores PLC. A monitoração da potência é realizada continuamente pelo conversor analógico digital do microcontrolador que escolhe qual o filtro analógico proporciona o melhor casamento de impedância com a rede de energia elétrica e comuta os filtros analógicos através de uma chave de analógica conectando os transceptores PLC a rede de energia elétrica através dos acopladores PLC. Além disso, as medições dos valores do parâmetro de espalhamento S11 confirmam que a componente resistiva da impedância de acesso da rede de energia elétrica apresentou melhor casamento de impedância entre 50 Ω e 100 Ω. Por fim, os valores medidos do parâmetro de espalhamento S12 mostram que a atenuação cresce com o aumento da frequência devido ao comportamento indutivo da rede de energia elétrica. / This work outlines a comprehensive review of PLC coupling circuits, which are required for narrowband and broadband PLC transceivers. Prevailing issues that protract the design of couplers and consequently subtended the inventions of different types of couplers are clearly described. Also, it provides a useful classification of PLC couplers based on the type of physical couplings, voltage levels, frequency bandwidth, propagation modes and a number of connections. Next, the focus is on the design of non-adaptive capacitive, SISO and low-voltage (LV) PLC coupling circuits for both broadband and narrowband applications. The narrowband cover the frequency band 9 kHz-500 kHz, while broadband frequency bands are 1.7-50MHz, 1.7-100MHz and 1.7- 500 MHz. Moreover, it discusses the specification and design of the prototypes of the PLC coupling circuits measuring their scattering parameters. The access impedance of Brazilian in-home, broadband and low-voltage electric power grid in the frequency band 2-500 MHz is taken into account. Based on the use of a measurement setup a large measurement campaign that was carried out in several facilities in three different Brazilian cities is discussed. Also, a procedure to obtain a statistical model of the access impedance in the aforementioned broadband frequency is outlined. Based on a number of measured access impedances and well-known criteria for choosing statistical models, two distributions to model the resistance and reactance components of the access impedance are suggested. Due to the fact that the parameters of such models change with the frequency and the access impedance is a random process in the frequency domain, a simple and effective model to generate samples function of such random process, which takes into account the suggested distributions, is addressed. Finally, adaptive capacitive, SISO and LV PLC coupling circuits are proposed for broadband power line communication. These adaptive coupling circuits use three different analog low-pass filter for impedance matching. This filter is an array of analog low-pass irregular filters that separate the input and output signal into three analog low-pass filters, each one matching the impedance between the electric power grid and PLC transceiver. The input impedance of each filter has a different impedance value, chosen according to the impedance of the measurement campaign, and the output impedance is fixed in 50 Ω for all analog low-pass filter. The choice of the analog filter that provides better impedance matching to the electrical power grid is obtained by a microcontroller, which through an analog-to-digital converter (ADC), measure the voltage provided by a circuit that measures the power of the signals injected into the PLC coupling circuit by the PLC transceivers. The power is continuously measured by an ADC of the microcontroller which chooses which analog filter provides the best impedance matching with the electric power grid and switches the analog filters through an analog switcher connecting the PLC transceivers to the electric power grid through the PLC coupling circuit. In addition, the measured values of the scattering parameter S11 show that the best impedance matching occurs when the resistive impedance component of the access impedance is between 50 Ω and 100 Ω . For the scattering parameter S12 it has been found that the attenuation increases as the frequency increases because of the inductive behavior of the electric power grid.

Submitted by Abraham Weintraub (abrahambvw@gmail.com) on 2013-11-06T19:22:30Z No. of bitstreams: 1 AbrahamWeintraub_dissertação_MPA.pdf: 887510 bytes, checksum: 3bf28f60e8c4bf117132d0e01e958f40 (MD5) / Approved for entry into archive by Vera Lúcia Mourão (vera.mourao@fgv.br) on 2013-11-06T19:31:25Z (GMT) No. of bitstreams: 1 AbrahamWeintraub_dissertação_MPA.pdf: 887510 bytes, checksum: 3bf28f60e8c4bf117132d0e01e958f40 (MD5) / Made available in DSpace on 2013-11-06T20:01:43Z (GMT). No. of bitstreams: 1 AbrahamWeintraub_dissertação_MPA.pdf: 887510 bytes, checksum: 3bf28f60e8c4bf117132d0e01e958f40 (MD5) Previous issue date: 2013-10-30 / From a financial perspective, this dissertation analyzes the Brazilian mutual fund industry performance for an average retail client. The most representative funds for the local population, that are the fixed income open-end ones, will be selected and their performance will be measured aiming to answer if clients of this industry obtained a proper return over their investments in the period between August 2010 and August 2013. A proper return will be understood as the preservation of the purchasing power of the individual´s savings, what is achieved with a positive performance of a mutual fund after discounting taxes, administrative fees and inflation. After obtaining an answer for the previous question, this dissertation will explore a possible alternative solution: Tesouro Direto, that is an example of a financial approach that could foster the disintermediation between savings and investments through electronic channels. New electronic platforms, with a broader scope, could be utilized to increase the efficiency of funding productive investments through better remunerating Brazilian savings. Tesouro Direto may point towards a new paradigm.

The objectives of this thesis were to explore how effectiveness of school-based anti-bullying interventions (SBABI) evolves over time and to assess the possibility to predict the medium-term or long-term effectiveness of SBABIs on the basis of their short-term effectiveness. The first step included a literature review in order to understand the study designs and evaluation techniques that researches used to assess the effectiveness. This literature review described the methodologies based on which researchers collected evidence and concluded on the effectiveness of their SBABIs. In order to address the thesis objectives, a collaborative project was established, named SET-Bullying (“Statistical modelling of the Effectiveness of school based anti-bullying interventions and Time”). The above-mentioned literature review was used to identify potentially eligible studies. After addressing a call for collaboration to the corresponding authors of these studies, this project included data from two of them, the DFE-SHEFFIELD study from United Kingdom and the RESPEKT study from Norway. Both of these studies have used pupil self-reported frequencies on being bullied and bullying others as an effectiveness measure, but using different instruments to elicit this information. Thus, the subsequent step of this thesis was to harmonize the data from these studies using polychoric principal components analysis, in order to be able to perform the same analysis with the data from both studies. The data from both studies were analysed using mixed effect models in order to take into account the hierarchical (i.e. the responses of pupils from the same school may be more correlated with each other as opposed to the responses of pupils from different schools) and the longitudinal structure (i.e. same pupils are more likely to respond in a similar way in the repeated measurements of each studies) of the data. With regard to the primary objective of the thesis, it was observed that effectiveness (where it is observed) may evolve either in a linear fashion or a “delayed effect” may be observed. This refers to a minimal evolution of effectiveness over the first study measurements and a sharper evolution at the later study measurements. This finding is only hypothesis generating at this point. Would this be confirmed in future studies, it will have important implication of the design, implementation and evaluations of SBABIs. About the secondary objective of this thesis, there were some preliminary findings of the possibility to predict the medium-term or long-term effectiveness based on the short-term effectiveness. However, these predictions in some cases seemed to be very variable. Future research should focus on how to make these predictions more accurate in order that this allows for dynamic and adaptable delivery of SBABIs. / Doctorat en Santé Publique / info:eu-repo/semantics/nonPublished

The aim of the study was to evaluate dierent types of logistic regression to find the optimal model to predict the gender of hospitalized COVID-19 patients. The models were based on COVID-19 case series data from Pakistan using a set of 18 explanatory variables out of which patient age and BMI were numerical and the rest were categorical variables, expressing symptoms and previous health issues.  Compared were a logistic regression using all variables, a logistic regression that used stepwise variable selection with 4 explanatory variables, a logistic Ridge regression model, a logistic Lasso regression model and a logistic Elastic Net regression model.  Based on several metrics assessing the goodness of fit of the models and the evaluation of predictive power using the area under the ROC curve the Elastic Net that was only using the Lasso penalty had the best result and was able to predict 82.5% of the test cases correctly.