Esta dissertação busca avaliar o comportamento da renda mediana e da desigualdade de rendimentos tratando o problema de seleção, através de uma abordagem ainda não utilizada em estudos semelhantes no Brasil. A metodologia empregada busca tratar o problema de seleção utilizando apenas hipóteses fracas e pautadas em argumentos econômicos, estimando os menores intervalos possíveis para a distribuição de renda da população. Os resultados obtidos mostram que as medianas dos rendimentos potenciais em 2002 e 2004 eram inferiores aos de 1996. Adicionalmente, a desigualdade de renda potencial recuou no Brasil entre 1996 e 2006. / This dissertation aims to evaluate the median income and income inequality behavior treating the selection problem with an approach not yet used in similar studies in Brazil. The present methodology tries to address the selection problem using only weak assumptions based on economic arguments, estimating the smallest possible intervals for the population income distribution. The results show that the mean potential income of 2002 and 2004 was smaller than the one of 1996. Additionally, the potential income inequality in Brazil fell from 1996 to 2006.

The automated analysis of patients’ biomedical data can be used to derive diagnostic and prognostic inferences about the observed patients. Many noninvasive techniques for acquiring biomedical samples generate data that are characterized by a large number of distinct attributes (i.e. features) and a small number of observed patients (i.e. samples). Deriving reliable inferences, such as classifying a given patient as either cancerous or non-cancerous, using these biomedical data requires that the ratio r of the number of samples to the number of features be within the range 5 < r < 10. To satisfy this requirement, the original set of features in the biomedical datasets can be reduced to an ‘optimal’ subset of features that most discriminates the observed patients. Feature selection techniques strategically seek the ‘optimal’ subset. In this thesis, I present a new feature selection technique - multilevel feature selection. The technique seeks the ‘optimal’ feature subset in biomedical datasets using a multilevel search algorithm. This algorithm combines a hierarchical search framework with a search method. The framework, which provides the capability to easily adapt the technique to different forms of biomedical datasets, consists of increasingly coarse forms of the original feature set that are strategically and progressively explored by the search method. Tabu search (a search meta-heuristics) is the search method used in the multilevel feature selection technique. I evaluate the performance of the new technique, in terms of the solution quality, using experiments that compare the classification inferences derived from the result of the technique with those derived from the result of other feature selection techniques such as the basic tabu-search-based feature selection, sequential forward selection, and random feature selection. In the experiments, the same biomedical dataset is used and equivalent amount of computational resource is allocated to the evaluated techniques to provide a common basis for comparison. The empirical results show that the multilevel feature selection technique finds ‘optimal’ subsets that enable more accurate and stable classification than those selected using the other feature selection techniques. Also, a similar comparison of the new technique with a genetic algorithm feature selection technique that selects highly discriminatory regions of consecutive features shows that the multilevel technique finds subsets that enable more stable classification. / February 2006

The automated analysis of patients’ biomedical data can be used to derive diagnostic and prognostic inferences about the observed patients. Many noninvasive techniques for acquiring biomedical samples generate data that are characterized by a large number of distinct attributes (i.e. features) and a small number of observed patients (i.e. samples). Deriving reliable inferences, such as classifying a given patient as either cancerous or non-cancerous, using these biomedical data requires that the ratio r of the number of samples to the number of features be within the range 5 < r < 10. To satisfy this requirement, the original set of features in the biomedical datasets can be reduced to an ‘optimal’ subset of features that most discriminates the observed patients. Feature selection techniques strategically seek the ‘optimal’ subset. In this thesis, I present a new feature selection technique - multilevel feature selection. The technique seeks the ‘optimal’ feature subset in biomedical datasets using a multilevel search algorithm. This algorithm combines a hierarchical search framework with a search method. The framework, which provides the capability to easily adapt the technique to different forms of biomedical datasets, consists of increasingly coarse forms of the original feature set that are strategically and progressively explored by the search method. Tabu search (a search meta-heuristics) is the search method used in the multilevel feature selection technique. I evaluate the performance of the new technique, in terms of the solution quality, using experiments that compare the classification inferences derived from the result of the technique with those derived from the result of other feature selection techniques such as the basic tabu-search-based feature selection, sequential forward selection, and random feature selection. In the experiments, the same biomedical dataset is used and equivalent amount of computational resource is allocated to the evaluated techniques to provide a common basis for comparison. The empirical results show that the multilevel feature selection technique finds ‘optimal’ subsets that enable more accurate and stable classification than those selected using the other feature selection techniques. Also, a similar comparison of the new technique with a genetic algorithm feature selection technique that selects highly discriminatory regions of consecutive features shows that the multilevel technique finds subsets that enable more stable classification.

The automated analysis of patients’ biomedical data can be used to derive diagnostic and prognostic inferences about the observed patients. Many noninvasive techniques for acquiring biomedical samples generate data that are characterized by a large number of distinct attributes (i.e. features) and a small number of observed patients (i.e. samples). Deriving reliable inferences, such as classifying a given patient as either cancerous or non-cancerous, using these biomedical data requires that the ratio r of the number of samples to the number of features be within the range 5 < r < 10. To satisfy this requirement, the original set of features in the biomedical datasets can be reduced to an ‘optimal’ subset of features that most discriminates the observed patients. Feature selection techniques strategically seek the ‘optimal’ subset. In this thesis, I present a new feature selection technique - multilevel feature selection. The technique seeks the ‘optimal’ feature subset in biomedical datasets using a multilevel search algorithm. This algorithm combines a hierarchical search framework with a search method. The framework, which provides the capability to easily adapt the technique to different forms of biomedical datasets, consists of increasingly coarse forms of the original feature set that are strategically and progressively explored by the search method. Tabu search (a search meta-heuristics) is the search method used in the multilevel feature selection technique. I evaluate the performance of the new technique, in terms of the solution quality, using experiments that compare the classification inferences derived from the result of the technique with those derived from the result of other feature selection techniques such as the basic tabu-search-based feature selection, sequential forward selection, and random feature selection. In the experiments, the same biomedical dataset is used and equivalent amount of computational resource is allocated to the evaluated techniques to provide a common basis for comparison. The empirical results show that the multilevel feature selection technique finds ‘optimal’ subsets that enable more accurate and stable classification than those selected using the other feature selection techniques. Also, a similar comparison of the new technique with a genetic algorithm feature selection technique that selects highly discriminatory regions of consecutive features shows that the multilevel technique finds subsets that enable more stable classification.

Esta dissertação busca avaliar o comportamento da renda mediana e da desigualdade de rendimentos tratando o problema de seleção, através de uma abordagem ainda não utilizada em estudos semelhantes no Brasil. A metodologia empregada busca tratar o problema de seleção utilizando apenas hipóteses fracas e pautadas em argumentos econômicos, estimando os menores intervalos possíveis para a distribuição de renda da população. Os resultados obtidos mostram que as medianas dos rendimentos potenciais em 2002 e 2004 eram inferiores aos de 1996. Adicionalmente, a desigualdade de renda potencial recuou no Brasil entre 1996 e 2006. / This dissertation aims to evaluate the median income and income inequality behavior treating the selection problem with an approach not yet used in similar studies in Brazil. The present methodology tries to address the selection problem using only weak assumptions based on economic arguments, estimating the smallest possible intervals for the population income distribution. The results show that the mean potential income of 2002 and 2004 was smaller than the one of 1996. Additionally, the potential income inequality in Brazil fell from 1996 to 2006.

Over the past thirty years, clinical research has benefited substantially from the adoption of electronic medical record systems. As deployment has increased, so too has the number of researchers seeking to improve the overall analytical environment by way of tools and models. Although much work has been done, there are still many uninvestigated areas; two of which are explored in this dissertation. The first pertains to the physical storage of the data itself. There are two generally accepted storage models: relational and entity-attribute-value (EAV). For clinical data, EAV systems are preferred due to their natural way of managing many-to-many relationships, sparse attributes, and dynamic processes along with minimal conversion effort and reduction in federation complexities. However, the relational database management systems on which they are implemented, are not intended to organize and retrieve data in this format; eroding their performance gains. To combat this effect, we present the foundation for an EAV Database Management System (EDBMS). We discuss data conversion methodologies, formulate the requisite metadata and partitioned type-sensing index structures, and provide detailed runtime and experimental analysis with five extant methods. Our results show that the prototype, EAVDB, reduces space and conversion requirements while enhancing overall query performance. The second topic concerns query performance in a federated environment. One method used to decrease query execution time, is to pre-compute and store "beneficial" queries (views). The View Selection Problem (VSP) identifies these views subject to resource constraints. A federated model, however, has yet to be developed. In this dissertation, we submit three advances in view materialization. First, a more robust optimization function, the Minimum-Maintenance View Selection Problem (MMVSP), is derived by combining existing approaches. Second, the Federated View Selection Problem (FVSP), built upon the MMVSP, and federated data cube lattice are formalized. The FVSP allows for multiple querying nodes, partial and full materialization, and data propagation constriction. The latter two are shown to greatly reduce the overall number of valid solutions within the solution space and thus a novel, multi-tiered approach is given. Lastly, EAV materialization, which is introduced in this dissertation, is incorporated into an expanded, multi-modal variant of the FVSP. As models and heuristics for both the federated and EAV VSP, to the best of our knowledge, do not exist, this research defines two new branches of data warehouse optimization. Coupled with our EDBMS design, this dissertation confronts two main challenges associated with clinical data warehousing and federation.

In this study, we propose two biobjective mathematical models based on PROMETHEE V method for project selection problems. We develop an interactive approach (ib-PROMETHEE V) including data mining techniques to solve the first proposed mathematical model. For the second model, we propose NSGA-II with constraint handling method. We also develop a Preference Based Interactive Multiobjective Genetic Algorithm (IMGA) to solve the second proposed mathematical model. We test the performance of NSGA-II with constraint handling method and IMGA on randomly generated test problems.

Enabling more than one function in an entity provides a new cost-effective way to develop a highly reliable system. In this dissertation, we study the reliability of systems containing multi-functional entities. We derive the expressions for reliability of one-shot systems and reliability of each function. A step further, a redundancy allocation problem (RAP) with the objective of maximizing system reliability is formulated. Unlike constructing a system with only single-functional entities, the number of copies of a specific function to be included in each multi-functional entity (i.e., functional redundancy) needs to be determined as part of the design. Moreover, a start-up strategy for turning on specific functions in these components must be decided prior to system operation. We develop a heuristic algorithm and include it in a two-stage Genetic Algorithm (GA) to solve the new RAP. We also apply a modified Tabu search (TS) method for solving such NP-hard problems. Our numerical studies illustrate that the two-stage GA and the TS method are quite effective in searching for high quality solutions. The concept of multi-functional entities can be also applied in probabilistic site selection problem (PSSP). Unlike traditional PSSP with failures either at nodes or on edges, we consider a more general problem, in which both nodes and edges could fail and the edge-level redundancy is included. We formulate the problem as an integer programming optimization problem. To reduce the searching space, two corresponding simplified models formulated as integer linear programming problems are solved for providing a lower bound to the primal problem. Finally, a big challenge in reliability analysis is how to determine the failure distribution of components. This is especially significant for multi-functional entities as more levels of redundancy are considered. We provide an automated model-selection method to construct the best phase-type (PH) distribution for a given data set in terms of the model complexity and the adequacy of statistical fitting. To efficiently utilize the Akaike Information Criterion for balancing the likelihood value and the number of free parameters, the proposed method is carried out in two stages. The detailed subproblems and the related solution procedures are developed and illustrated through numerical studies. The results verify the effectiveness of the proposed model-selection method in constructing PH distributions.

O processo de escolha de portfólios é um problema clássico da área financeira. Neste problema, o investidor busca aplicar seu dinheiro em um mercado de ações de forma a obter um bom compromisso entre o retorno esperado e o risco. Em geral, quanto maior o retorno esperado da carteira, maior o risco a ela associado. Neste trabalho foram estudadas modelagens para o problema de escolha de portfólio ótimo e suas aplicações ao mercado brasileiro. Do ponto de vista de modelagem foi proposta a inclusão do risco diversificável e não-diversificável ao modelo linear estudado. O risco diversificável foi incluído através de uma restrição que impõe um número mínimo de ativos na composição do portfólio ótimo, enquanto o risco não-diversificável foi adicionado considerando o beta da carteira. Do ponto de vista de aplicação, foi considerada a atribuição de valores de probabilidade para os retornos históricos dos ativos utilizados na análise do problema, visando incorporar informações do comportamento apresentado pelo mercado nos resultados. Na geração dos resultados, foram desenvolvidos em CPLEX um método ótimo de solução para o problema e um método para geração de uma curva de soluções Pareto ótimas / The process of selecting a portfolio is a classical problem in finance, where the investor intends to invest money in the stock market in such way that a reasonable trade-off between expected return and risk is obtained. In general, the higher the expected return of the portfolio is, the higher his risk will be. In this work the single period portfolio optimization problem is studied in terms of modeling and application for the Brazilian stock market. Referring to the model, changes are proposed to include the diversifiable and nondiversifiable risk. The diversifiable risk is included by imposing a minimum number of assets on the portfolio, while the nondiversifiable risk is controlled by restricting the portfolios beta. On the applications side, a method to estimate the probability of the assets historical returns is proposed, so more information about the market behavior is considered on the problem. The results were obtained by a optimal method to find the best solution and another one to generate the Pareto-optimal solutions, both developed using CPLEX

O problema do caixeiro viajante (PCV) é um problema clássico de otimização que possui diversas variações, aplicações e instâncias. Encontrar a solução ótima para muitas instâncias desse problema é geralmente muito difícil devido o alto custo computacional. Vários métodos de otimização, conhecidos como meta-heurísticas (MHs), são capazes de encontrar boas soluções para o PCV. Muitos algoritmos baseados em diversas MHs têm sido propostos e investigados para diferentes variações do PCV. Como não existe um algoritmo universal que encontre a melhor solução para todas as instâncias de um problema, diferentes MHs podem prover a melhor solução para diferentes instâncias do PCV. Desse modo, a seleção a priori da MH que produza a melhor solução para uma dada instância é uma tarefa difícil. A pesquisa desenvolvida nesta tese investiga o uso de abordagens de meta-aprendizado para selecionar as MHs mais promissoras para novas instâncias de PCV. Essas abordagens induzem meta-modelos preditivos a partir do treinamento das técnicas de aprendizado de máquina em um conjunto de meta-dados. Cada meta-exemplo, em nosso conjunto de meta-dados, representa uma instância de PCV descrita por características (meta-atributos) do PCV e pelo desempenho das MHs (meta-atributo alvo) para essa instância. Os meta-modelos induzidos são usados para indicar os valores do meta-atributo alvo para novas instâncias do PCV. Vários experimentos foram realizados durante a investigação desta pesquisa e resultados importantes foram obtidos / The traveling salesman problem (TSP) is a classical optimization problem that has several variations, applications and instances. To find the optimal solution for many instances of this problem is usually a very hard task due to high computational cost. Various optimization methods, known as metaheuristics (MHs), are capable to generate good solutions for the TSP. Many algorithms based on different MHs have been proposed and investigated for different variations of the TSP. Different MHs can provide the best optimization solution for different TSP instances, since there is no a universal algorithm able to find the best solution for all instances. Thus, a priori selection of the MH that produces the best solution for a given instance is a hard task. The research developed in this thesis investigates the use of meta-learning approaches to select the most promising MHs for new TSP instances. These approaches induce predictive meta-models from the training of machine learning techniques on a set of meta-data. In our meta-data, each meta-example is a TSP instance described by problem characteristics (meta-features) and performance of MHs (target meta-features) for this instance. The induced meta-models are used to indicate the values of the target meta-feature for new TSP instances. During the investigation of this research, several experiments were performed and important results were obtained