Power industry restructuring has created many opportunities for customers to reduce their electricity bills. In order to facilitate the retail choice in a competitive power market, the knowledge of hourly load shape by customer class is necessary. Requiring a meter as a prerequisite for lower voltage customers to choose a power supplier is not considered practical at the present time. In order to be used by Energy Service Provider (ESP) to assign customers to specific load profiles with certainty factors, a technique which bases on load research and customers¡¦ monthly energy usage data for a preliminary screening of customer load profiles is required. Distribution systems supply electricity to different mixtures of customers, due to lack of field measurements, load point data used in distribution network studies have various degrees of uncertainties. In order to take the expected uncertainties in the demand into account, many previous methods have used fuzzy load models in their studies. However, the issue of deriving these models has not been discussed. To address this issue, an approach for building these fuzzy load models is needed. Load aggregation allows customers to purchase electricity at a lower price. In some contracts, load factor is considered as one critical aspect of aggregation. To facilitate a better load aggregation in distribution networks, feeder reconfiguration could be used to improve the load factor in a distribution subsystem. To solve the aforementioned problems, two data mining techniques, namely, the fuzzy c-means (FCM) method and an Artificial Neural Network (ANN) based pattern recognition technique, are proposed for load profiling and customer class assignment. A variant to the previous load profiling technique, customer hourly load distributions obtained from load research can be converted to fuzzy membership functions based on a possibility¡Vprobability consistency principle. With the customer class fuzzy load profiles, customer monthly power consumption and feeder load measurements, hourly loads of each distribution transformer on the feeder can be estimated and used in distribution network analysis. After feeder models are established, feeder reconfiguration based on binary particle swarm optimization (BPSO) technique is used to improve feeder load factors. Test results based on several simple sample networks have shown that the proposed feeder reconfiguration method could improve customers¡¦ position for a good bargain in electricity service.

The hybridization of soft computing methods of Radial Basis Function (RBF) neural networks, Multi Layer Perceptron (MLP) neural networks with back-propagation learning, fuzzy sets and rough sets are studied in the scope of this thesis. Conventional MLP, conventional RBF, fuzzy MLP, fuzzy RBF, rough fuzzy MLP, and rough fuzzy RBF networks are compared. In the fuzzy neural networks implemented in this thesis, the input data and the desired outputs are given fuzzy membership values as the fuzzy properties &ldquo / low&rdquo / , &ldquo / medium&rdquo / and &ldquo / high&rdquo / . In the rough fuzzy MLP, initial weights and near optimal number of hidden nodes are estimated using rough dependency rules. A rough fuzzy RBF structure similar to the rough fuzzy MLP is proposed. The rough fuzzy RBF was inspected whether dependencies like the ones in rough fuzzy MLP can be concluded.

Systems are becoming more complicated, complex, and interrelated. Designers have recognized the need to develop systems from a holistic perspective and design them as Systems-of-Systems (SoS). The design of the SoS, especially in the conceptual design phase, is generally characterized by significant uncertainty. As a result, it is possible for all three types of uncertainty (aleatory, epistemic, and error) and the associated factors of uncertainty (randomness, sampling, confusion, conflict, inaccuracy, ambiguity, vagueness, coarseness, and simplification) to affect the design process. While there are a number of existing SoS design methods, several gaps have been identified: the ability to modeling all of the factors of uncertainty at varying levels of knowledge; the ability to consider both the pernicious and propitious aspects of uncertainty; and, the ability to determine the value of reducing the uncertainty in the design process. While there are numerous uncertainty modeling theories, no one theory can effectively model every kind of uncertainty. This research presents a Hybrid Uncertainty Modeling Method (HUMM) that integrates techniques from the following theories: Probability Theory, Evidence Theory, Fuzzy Set Theory, and Info-Gap theory. The HUMM is capable of modeling all of the different factors of uncertainty and can model the uncertainty for multiple levels of knowledge. In the design process, there are both pernicious and propitious characteristics associated with the uncertainty. Existing design methods typically focus on developing robust designs that are insensitive to the associated uncertainty. These methods do not capitalize on the possibility of maximizing the potential benefit associated with the uncertainty. This research demonstrates how these deficiencies can be overcome by identifying the most robust and opportunistic design. In a design process it is possible that the most robust and opportunistic design will not be selected from the set of potential design alternatives due to the related uncertainty. This research presents a process called the Value of Reducing Uncertainty Method (VRUM) that can determine the value associated with reducing the uncertainty in the design problem before a final decision is made by utilizing two concepts: the Expected Value of Reducing Uncertainty (EVRU) and the Expected Cost to Reducing Uncertainty (ECRU).

Univ., Diss.--Münster (Westfalen), 2002.

Submitted by Livia Mello (liviacmello@yahoo.com.br) on 2016-10-06T19:50:59Z No. of bitstreams: 1 DissBKL.pdf: 2379155 bytes, checksum: 51e6509b53346c6cbb27ecc3a7faf016 (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-20T19:20:55Z (GMT) No. of bitstreams: 1 DissBKL.pdf: 2379155 bytes, checksum: 51e6509b53346c6cbb27ecc3a7faf016 (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-20T19:21:00Z (GMT) No. of bitstreams: 1 DissBKL.pdf: 2379155 bytes, checksum: 51e6509b53346c6cbb27ecc3a7faf016 (MD5) / Made available in DSpace on 2016-10-20T19:21:06Z (GMT). No. of bitstreams: 1 DissBKL.pdf: 2379155 bytes, checksum: 51e6509b53346c6cbb27ecc3a7faf016 (MD5) Previous issue date: 2016-05-19 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / The main aims of this work are to study the ways to model mathematically uncertainties using Fuzzy Sets Theory, and then propose a mathematical model to estimate the risk of an individual developing lung cancer through a system based rule fuzzy. Therefore, we consider risk factors, namely smoking, pollution, history of lung disease, family history and contact with chemical agents such as system input variables fuzzy. Lung cancer is a disease that has no symptoms in its early stages, making the diagnosis more difficult to be done and, therefore, most discovered when the cancer is already advanced. This type of cancer is highly lethal and frequent in the population, an increase of 2 % per year in its worldwide incidence. / Os principais objetivos desse trabalho são estudar as formas de modelar matematicamente certas incertezas por meio da Teoria dos Conjuntos Fuzzy e, em seguida, propor um modelo matemático para estimar o risco de um indivíduo desenvolver câncer de pulmão por meio um sistema baseado em regras fuzzy. Para isso, consideramos fatores de risco, tais como, tabagismo, poluição, histórico de doenças pulmonares, histórico familiar e contato com agentes químicos como variáveis de entrada do sistema fuzzy. O câncer de pulmão é uma doença que não apresenta sintomas em suas fases iniciais, tornando o diagnóstico mais difícil de ser feito e, por isso, a maioria descobre quando o câncer já está avançado. Esse tipo de câncer é altamente letal e frequente na população, apresentando aumento de 2% ao ano na sua incidência mundial.

Submitted by MELINA FUSHIMI (melinafushimi@yahoo.com.br) on 2016-06-27T15:24:06Z No. of bitstreams: 1 TESE_FINAL_Melina Fushimi.pdf: 21884758 bytes, checksum: 0c1b17ce557210c1ae752004961a846d (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-06-28T17:14:34Z (GMT) No. of bitstreams: 1 fushimi_m_dr_prud.pdf: 21884758 bytes, checksum: 0c1b17ce557210c1ae752004961a846d (MD5) / Made available in DSpace on 2016-06-28T17:14:34Z (GMT). No. of bitstreams: 1 fushimi_m_dr_prud.pdf: 21884758 bytes, checksum: 0c1b17ce557210c1ae752004961a846d (MD5) Previous issue date: 2016-06-17 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / No atual momento histórico, diante das transformações aceleradas das paisagens, em que as dinâmicas da sociedade se interpenetram e, muitas vezes, se sobressaem às dinâmicas da natureza, a questão ambiental assume importância em vários campos do conhecimento, sobretudo, na Geografia. Em meio aos diversos trabalhos desenvolvidos no âmbito geográfico e ambiental, tem-se a erosão como um dos assuntos mais enfatizados. Neste contexto, o objetivo geral da tese foi analisar os principais elementos que influenciam na vulnerabilidade ambiental aos processos erosivos lineares (sulcos, ravinas e voçorocas) de parte dos municípios de Marabá Paulista-SP e Presidente Epitácio-SP. Sob a perspectiva teórico-metodológica do pensamento da complexidade, foram caracterizados os aspectos do relevo, declividade, solos, substrato rochoso, cobertura vegetal, curvatura da superfície e uso da terra, além da elaboração de documentos cartográficos em ambiente de Sistemas de Informação Geográfica, em especial, o mapa de vulnerabilidade ambiental aos processos erosivos lineares. Em virtude das possibilidades de integração dos dados e atribuição de pesos, o referido mapa foi realizado a partir da lógica fuzzy, especificamente, da Técnica do Processo Analítico Hierárquico (AHP), a qual proporcionou o mapeamento de maneira classificada: baixa (0.32%), média (65.15%), alta (34.45%) e muito alta vulnerabilidade (0.08%). A baixa vulnerabilidade está elencada às matas ciliares remanescentes. A média vulnerabilidade se localiza nos topos das colinas com declividades inferiores a 5%. O uso da terra predominante é a pastagem e os solos são, em sua maioria, desenvolvidos e arenosos. A alta vulnerabilidade está, principalmente, nas vertentes convexas e retilíneas, em que as inclinações podem alcançar 15%. A pastagem prevalece, todavia, verificou-se a expansão do cultivo de cana de açúcar e do solo exposto para seu consecutivo plantio. A muito alta vulnerabilidade apresenta-se nas vertentes côncavas, cuja curvatura favorece a convergência das águas pluviais e, portanto, o fluxo linear. Tal evento se intensifica perante às declividades acentuadas – superiores a 20% para a região. Combinado a estes atributos, sobre solos rasos tem-se o pastoreio intensivo do gado, o qual acelera a compactação do solo e acarreta a erosão, sendo uma das formas de degradação mais recorrente no Extremo Oeste Paulista. Assim, o presente estudo pode contribuir no sentido de orientar a implantação de medidas preventivas e corretivas de controle à erosão por intermédio do planejamento ambiental. / In the current historical moment, given the accelerated changes in landscapes, in which the dynamics of society interpenetrate and, often, exceed the dynamics of nature, the environmental issue assumes importance in several fields of knowledge, especially, Geography. Among the diverse assignments developed in geographical and environmental contexts, erosion is one of the most commonly emphasized subjects. Therefore, this thesis aimed to analyze the main elements that influence environmental vulnerability to linear erosive processes (rills, ravines and gullies) in parts of Marabá Paulista-SP and Presidente Epitácio-SP. From the theoretical-methodological perspective of thought complexity, the relief, slope plans, soils, bedrocks, vegetation, surface curvature and land use aspects were characterized, in addition to the elaboration of cartographic documents using the Geographic Information System, in particular, the map of environmental vulnerability to linear erosive processes. Due to the possibilities of integrating data and assigning weights, the map was performed based on fuzzy sets, specifically, the Analytical Hierarchy Process (AHP), which provided classified mapping: low (0.32%), medium (65.15%), high (34.45%) and very high vulnerability (0.08%). The low vulnerability is identified in the reminiscent cilliary forests. The medium vulnerability is located on the hilltops with slopes of less than 5%. The land use is predominantly for pasture and soils are for the most part developed and sandy. The high vulnerability is primarily the convex and rectilinear aspects, where the slopes can reach 15%. On the prevailing pasture, however, the expansion of the sugar cane crop was found and soil exposed to its successive planting. The very high vulnerability is present in the concave slopes, whose curvature favors the convergence of rainwater and thus, linear flow. This event is intensified towards the steep slopes – more than 20% of the region. Combined with these attributes, on shallow soils there is intensive grazing of livestock, which accelerates soil compaction and leads to erosion, one of the most recurrent means of degradation in the Far West of São Paulo. Thus, the present study may contribute to guiding the management of preventive and corrective measures to control erosion through environmental planning.

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-16T05:02:12Z (GMT). No. of bitstreams: 1 Esmi_Estevao_M.pdf: 1708768 bytes, checksum: 81d1d15b597bdc13e41b87c4847aa2f7 (MD5) Previous issue date: 2010 / Resumo: Redes neurais morfológicas (MNN) são redes neurais artificiais cujos nós executam operações elementares da morfologia matemática (MM). Vários modelos de MNNs e seus respectivos algoritmos de treinamentos têm sido propostos nos últimos anos, incluindo os perceptrons morfológicos(MPs), o perceptron morfológico com dendritos, as memórias associativas morfológicas (fuzzy), as redes neurais morfológicas modulares e as redes neurais de pesos compartilhados e regularizados. Aplicações de MNNs incluem reconhecimento de padrão, previsão de séries temporais, detecção de alvos, auto-localização e processamento de imagens hiperespectrais. Nesta tese, abordamos dois novos modelos de redes neurais morfológicas.O primeiro consiste em uma memória associativa fuzzy denominada KS-FAM, e o segundo representa uma nova versão do perceptron morfológico para problemas de classificação de múltiplas classes, denominado perceptron morfológico com aprendizagem competitiva(MP/CL). Para ambos modelos, investigamos e demonstramos várias propriedades. Em particular para a KS-FAM, caracterizamos as condições para que uma memória seja perfeitamente recordada, assim como a formada saída produzida ao apresentar um padrão de entrada qualquer. Provamos ainda que o algoritmo de treinamento do MP/CL converge em um número finito de passos e que a rede produzida independe da ordem com que os padrões de treinamento são apresentados. Além disso, é garantido que o MP/CL resultante classifica perfeitamente todos os dados de treinamento e não produz regiões de indecisões. Finalmente, comparamos os desempenhos destes modelos com os de outros modelos similares em uma série de experimentos, que incluir e conhecimento de imagens em tons de cinza, para a KS-FAM, e classificação de vários conjuntos de dados disponíveis na internet, para o MP/CL / Abstract: Morphological neural networks (MNN) are artificial neural networks whose hidden neurons perform elementary operations of mathematical morphology (MM). Several particular models of MNNs have been proposed in recent years, including morphological perceptrons (MPs), morphological perceptrons with dendrites, (fuzzy) morphological associative memories, modular morphological neural networks as well as morphological shared-weight and regularization neural networks. Applications of MNNs include pattern recognition, time series prediction, target detection, self-location, and hyper-spectral image processing. In this thesis, we present two new models of morphological neural networks. The first one consists of a fuzzy associative memory called KS-FAM. The second one represents a novel version of the morphological perceptron for classification problems with multiple classes called morphological perceptron with competitive learning(MP/CL). For both KS-FAM and MP/CL models, we investigated and showed several properties. In particular, we characterized the conditions for perfect recall using the KS-FAM as well as the outputs produced upon presentation of an arbitrary input patern. In addition, we proved that the learning algorithm of the MP/CL converges in a finite number of steps and that the results produced after the conclusion of the training phase do not depend on the order in which the training patterns are presented to the network. Moreover, the MP/CL is guaranteed to perfectly classify all training data without generating any regions of indecision. Finaly, we compared the performances of our new models and a range of competing models in terms of a series of experiments in gray-scale image recognition (in case of the KS-FAM) and classification using several well-known datasets that are available on the internet (in case of the MP/CL) / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

Orientador: Jose Roberto de França Arruda / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-08-05T10:01:28Z (GMT). No. of bitstreams: 1 Nunes_RonaldoFernandes_D.pdf: 2368458 bytes, checksum: 01da7061fcacf61682f9aa00dceb6837 (MD5) Previous issue date: 2005 / Resumo: Neste trabalho, o problema da análise dinâmica de estruturas em médias freqüências é abordado. Em geral, métodos numéricos tais como elementos finitos e elementos de contorno não são apropriados para tratar estes casos. As principais razões são a necessidade do refinamento das malhas com o aumento da freqüência e o cálculo da influência dos parâmetros incertos, cujo efeito em particular, para médias e altas freqüências, tende a ser significativo. O problema do refinamento do modelo pode ser superado através de métodos semi-analíticos, como por exemplo, o método do elemento espectral. Em relação à simulação dos sistemas com parâmetros de entrada incertos, métodos baseados em conjuntos nebulosos e métodos probabilísticos são adotados. Nesta tese, uma proposta combinando o método do elemento espectral com conjuntos nebulosos é conduzida. O principal foco deste trabalho é apresentar uma nova abordagem para o problema em médias freqüências. Neste contexto, funções de resposta em freqüência são adotadas para representar o efeito dos parâmetros de entrada não determinísticos na resposta dinâmica de estruturas. Para ilustrar o procedimento proposto, exemplos numéricos são tratados, como o caso simples de uma placa retangular reforçada com vigas e também o caso de uma estrutura do tipo pórtico / Abstract: It is well-known that, in the mid-frequency range, numerical methods such as finite and boundary elements are not suitable for structural dynamic analysis. One of the reasons is the fine mesh resolution required to accurately model the physical problem, leading to large computational models. The other reason is associated with the difficulty in estimating the response statistics for system parameter variations. The mesh refinement problem can be addressed using semi-analytical methods, such as the spectral element method. However, in general, these methods are very limited with respect to the geometry and boundary conditions that can be treated. With respect to parameter variation, the simulation of systems with uncertain parameters has in the past been addressed with different techniques, such as finite elements applied to stochastic problems and fuzzy set based methods. In this thesis, the spectral element method is combined with a special implementation of a fuzzy set based method that avoids the well-know effect of overestimation in interval computations. In this regard, some efficient alternatives, such as the transformation method and the sparse grids approach are proposed. In this work, the main goal is to provide alternatives to address dynamic problems under uncertainty in the mid-frequency range. In this context, envelopes for frequency response functions are used to represent the effect of non-deterministic input parameters in the dynamic response of structures. To illustrate he proposed procedure, numerical examples are treated, such as a simple rectangular plate reinforced with beams and a frame-type model / Doutorado / Mecanica dos Sólidos e Projeto Mecanico / Doutor em Engenharia Mecânica

Orientadores: Akebo Yamakami, Marcia Tomie Takahashi / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-06T21:15:33Z (GMT). No. of bitstreams: 1 Almeida_TiagoAgostinhode_M.pdf: 1289408 bytes, checksum: 8b0b0e45d9ae8cee7d3c5343e9213cfc (MD5) Previous issue date: 2006 / Resumo: Este trabalho propoe meta-heuristicas baseadas em tecnicas da computaçao evolutiva, que visam encontrar um conjunto de arvores geradoras minimas para problemas de grafos, que possuem incertezas em relaçao as informaçoes associadas aos parametros. Resolver problemas dessa natureza e um processo NP-Completo, pois envolve um numero enorme de comparaçoes. A fim de contornar essa complexidade, este trabalho propoe um algoritmo genetico e um sistema imunologico artificial, capazes de explorar eficientemente o espaco de busca e de obter resultados satisfatorios, sem a necessidade de confrontar todas as solucoes entre si / Abstract: This work proposes heuristical approaches based on evolutionary computation, whose goal is to find a set of minimum spanning trees in graphs that contain uncertainties in their parameters. These kind of problems is a NP-hard one, because it involves an enormous number of comparisons. In order to avoid this complexity, this work proposes a genetic algorithm and an artificial immune system, that explore efficiently the search space of solutions to looking for satisfactory results, without the necessity of comparing all possible solutions. Keywords: Fuzzy Graph, Fuzzy Minimum Spanning Tree, Fuzzy Set Theory, Evolutionary Computation, Genetic Algorithm, Artificial Immune System / Mestrado / Telecomunicações e Telemática / Mestre em Engenharia Elétrica

Orientador: Fernando Antonio Campos Gomide / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-08T23:48:55Z (GMT). No. of bitstreams: 1 Amaral_WanessaMachadodo_M.pdf: 2424347 bytes, checksum: 390879b70ad2ca4dc593f415471fea5c (MD5) Previous issue date: 2007 / Resumo: A teoria de jogos é um ramo da teoria da decisão que modela e trata matematicamente situações de conflito de interesses entre entidades, onde o objetivo principal é escolher a melhor estratégia para cada uma delas, ou seja, aquela que se traduz em equilíbrio. Existem inúmeras áreas em que a teoria de jogos é utilizada. Uma das principais é a microeconomia, onde se aborda questões relativas ao comportamento de empresas e indústrias no mercado competitivo. A teoria de jogos é utilizada para encontrar a estratégia ótima para empresas com objetivos antagônicos, como exige o mercado. No entanto, os dados dos problemas reais nem sempre são precisos. A teoria de conjuntos nebulosos introduz flexibilidade na formulação desses problemas, pois permite a consideração de parâmetros imprecisos nos modelos. Esse trabalho aborda a teoria de jogos nebulosos. Estratégias de equilíbrio são analisadas e métodos computacionais desenvolvidos para a resolução dos modelos. É proposto um método baseado em computação evolutiva para obter soluções de equilíbrio de jogos nebulosos. Além disso propõe-se também um método baseado em a-cortes e no algoritmo de decomposição para a solução dos modelos bilineares associados a jogos nebulosos de soma não zero. Exemplos de aplicações são apresentados para ilustrar o potencial prático da teoria de jogos nebulosos / Abstract: Game theory is a branch of applied mathematics whose aim is to model and study decision making in conflicting situations. In these situations, the main goal is to choose the best strategy for all the players in the game, that is, to find the equilibrium solutions. Game theory can be defined as the study of how self-interested entities interact and make decisions. There are many applications of game theory in different areas. One of the main applications is in microeconomy, where situations of conflict between companies exist and there is a need to find the optimal strategies in that situation. In practice however, model parameters are imprecise. Fuzzy set theory allows modeling flexibility because imprecise data can be treated using fuzzy models. This work concerns Fuzzy Game Theory. Equilibrium strategies are studied and computational methods developed to solve fuzzy game problems. A new method to solve fuzzy games using evolutionary computation is introduced. A method based on a-cuts and on a decomposition algorithm to solve bilinear models also presented to solve fuzzy non zero-sum games. Algorithms were implemented and applications examples are discussed to illustrate the usefulness of fuzzy games in practice / Mestrado / Engenharia de Computação / Mestre em Engenharia Elétrica