Orientador: Akebo Yamakami / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-08T23:52:00Z (GMT). No. of bitstreams: 1 Carvalho_MarciaBragade_M.pdf: 2154346 bytes, checksum: caafd847980349294a73d2ad38d6414c (MD5) Previous issue date: 2007 / Resumo: Dentre as várias técnicas heurísticas e exatas existentes para a resolução de problemas combinatórios, os algoritmos populacionais de otimização por colônia de formigas e genéticos têm se destacado devido à sua boa performance. Em especial os algoritmos de colônia de formigas são considerados atualmente como uma das técnicas mais bem sucedidas para a resolução de vários problemas combinatórios, dentre eles o problema do caixeiro viajante. Neste trabalho é apresentado um algoritmo híbrido que trabalha com as meta-heurísticas de sistema de colônia de formigas e genético conjuntamente aplicados no problema do caixeiro viajante simétrico. Além disso, apresentamos uma proposta para o algoritmo de formigas quando temos incertezas associadas aos parâmetros do problema. Os resultados obtidos com as metodologias propostas apresentam resultados satisfatórios para todas as instâncias utilizadas / Abstract: Amongst the several existing heuristical and accurate techniques for the resolution of combinatorial problems, the population algorithms ant colony optimization and genetic have been detached due to their good performance. In special the ant colony algorithms are considered currently as one of the techniques most succeeded for the resolution of some combinatorial problems, amongst them the travelling salesman problem. In this work is presented a hybrid algorithm which works with the ant colony system and genetic metaheuristics jointly applied in the symmetric travelling salesman problem. Moreover, we presented a proposal for the ant algorithm when we have uncertainties associated to problem parameters. The results gotten with the methodology proposals present resulted satisfactory for all the used instances / Mestrado / Automação / Mestre em Engenharia Elétrica

Medication prescriptions constitute an important type of clinical intervention. Medication adherence is the degree to which a patient consumes their medication as agreed upon with a prescriber. Despite many years of research, medication non-adherence continues to be a problem of note, partially due to its multi-faceted in nature. Numerous interventions have attempted to improve adherence but none have emerged as definitive. A significant sub-problem is the lack of consensus regarding definitions and measurement of adherence. Several recent reviews indicate that discrepancies in definitions, measurement techniques, and study methodologies make it impossible to draw strong conclusions via meta-analyses of the literature. Technological interventions aimed at improving adherence have been the subject of ongoing research. Due to the increasing prevalence of the Internet of Things, technology can be used to provide a continuous stream of data regarding a patient's behaviour. To date, several researchers have proposed interventions that leverage data from the Internet of Things, however none have established an acceptable means of analyzing and acting upon this wealth of data. This thesis introduces a computational definition for adherence that can be used to support continued development of technological adherence interventions. A central part of the proposed definition is a formal language for specifying prescriptions that uses fuzzy set theory to accommodate imprecise concepts commonly found in natural language medication prescriptions. A prescription specified in this language can be transformed into an evaluation function which can be used to score the adherence of a given medication taking behaviour. Additionally, the evaluator function is applied to the problem of scheduling medication administrations. A compiler for the proposed language was implemented and had its breadth of expression and clinical accuracy evaluated. The results indicate that the proposed computational definition of adherence is acceptable as a proof of concept and merits further works. / Graduate

A huge amount of data is generated daily by digital technologies such as social media, web logs, traffic sensors, on-line transactions, tracking data, videos, and so on. This has led to the archiving and storage of larger and larger datasets, many of which are multi-modal, or contain different types of data which contribute to the problem that is now known as “Big Data”. In the area of Big Data, volume, variety and velocity problems remain difficult to solve. The work presented in this thesis focuses on the variety aspect of Big Data. For example, data can come in various and mixed formats for the same feature(attribute) or different features and can be identified mainly by one of the following data types: real-valued, crisp and linguistic values. The increasing variety and ambiguity of such data are particularly challenging to process and to build accurate machine learning models. Therefore, data heterogeneity requires new methods of analysis and modelling techniques to enable useful information extraction and the modelling of achievable tasks. In this thesis, new approaches are proposed for handling heterogeneous Big Data. these include two techniques for filtering heterogeneous data objects are proposed. The two techniques called Two-Dimensional Similarity Space(2DSS) for data described by numeric and categorical features, and Three-Dimensional Similarity Space(3DSS) for real-valued, crisp and linguistic data are proposed for filtering such data. Both filtering techniques are used in this research to reduce the noise from the initial dataset and make the dataset more homogeneous. Furthermore, a new similarity measure based on intuitionistic fuzzy set theory is proposed. The proposed measure is used to handle the heterogeneity and ambiguity within crisp and linguistic data. In addition, new combine similarity models are proposed which allow for a comparison between the heterogeneous data objects represented by a combination of crisp and linguistic values. Diverse examples are used to illustrate and discuss the efficiency of the proposed similarity models. The thesis also presents modification of the k-Nearest Neighbour classifier, called k-Nearest Neighbour Weighted Average (k-NNWA), to classify the heterogeneous dataset described by real-valued, crisp and linguistic data. Finally, the thesis also introduces a novel classification model, called FCCM (Filter Combined Classification Model), for heterogeneous data classification. The proposed model combines the advantages of the 3DSS and k-NNWA classifier and outperforms the latter algorithm. All the proposed models and techniques have been applied to weather datasets and evaluated using accuracy, Fscore and ROC area measures. The experiments revealed that the proposed filtering techniques are an efficient approach for removing noise from heterogeneous data and improving the performance of classification models. Moreover, the experiments showed that the proposed similarity measure for intuitionistic fuzzy data is capable of handling the fuzziness of heterogeneous data and the intuitionistic fuzzy set theory offers some promise in solving some Big Data problems by handling the uncertainties, and the heterogeneity of the data.

The increased demand for biofuels is expected to put additional strain on the available agricultural resources while at the same time causing environmental degradation. Hence, new energy policies need to be formulated and implemented in order to meet global energy needs while reducing the impact of biofuels farming and production. This research focuses on proving a decision support system which can aid the formulation of policies for the sustainable biofuel production. The system seeks to address policy formulation that requires reconciliation of the qualitative aspects of decision making (such as stakeholder’s viewpoints) with quantitative data, which often may be imprecise. To allow this, based on: Fuzzy logic and Multi Criteria Decision Making (MCDM) in the form of Analytical Hierarchy Process (AHP). Using these concepts, three software functionalities, “Options vs. Fuzzy Criteria Matrix”, “Analytical Hierarchy Process” and “Fuzzy AHP” were developed. These were added within the framework of pre-existing base software, Compendium (developed by the Open University, UK). A number of case study based models have been investigated using the software. These models made use of data from the Philippines and India in order to pinpoint suitable land and crop options for these countries. The models based on AHP and Fuzzy AHP were very successful in identifying suitable crop options for India by capturing both the stakeholder viewpoints and quantitative data. The software functionalities are very effective in scenario planning and selection of policies that would be beneficial in achieving a desired future scenario. The models further revealed that the newly developed software correctly identified many of the important issues in a consistent manner.

Esta tese busca, de início, pesquisar comparativamente, com a abrangência possível, os métodos e processos pelos quais as empresas componentes do setor siderúrgico nacional avaliam - sob o ponto de vista da viabililidade - a tomada de suas decisões relativamente a seus peculiares e vultosos investimentos em equipamentos de tecnologia avançada de manufatura. Revisita primária e metodologicamente amplo repertório de métodos de avaliação consagrados pela prática e pela literatura, tendo como cenário o setor em referência representado pelas várias modalidades industriais que o suportam. A pesquisa é realizada com base no estudo de múltiplos casos realizados em grandes empresas siderúrgicas, a partir de visitas a suas instalações e entrevistas com seus especialistas de análise de viabilidade de projetos de investimento. Ao final, oferece modelo de avaliação a ser adotado complementarmente aos critérios utilizados pelo setor em referência, a partir das observações e discussões efetuadas em campo. / This thesis initially seeks to search, in a comparative basis and with the permissible largeness, the methods and procedures through which the companies comprising the national siderurgic sector appraise their decisions referring to their peculiar and huge investments in AMT equipments, under a feasibility point of view. A primary review is made, in a comparative way, of a large well known evaluation methods repertoire, in a background at which act the various concerned industrial modalities. The search is accomplished based on the study of multiple cases realized at big siderurgic companies, by visiting their installations and by interviewing their specialists in investment feasibility project analysis. Eventually offers an evaluation model to be adopted by this sector, based upon the observation and discussions made in the related field research.

A seleção de fornecedores tem impacto significante no custo e na qualidade de produtos manufaturados. Por isso, a seleção de fornecedores passou a ser vista como uma atividade bastante crítica para o desempenho da empresa compradora. Muitos estudos da literatura propõem o uso dos métodos multicritério fuzzy TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) e fuzzy AHP (Analytic Hierarchy Process) para apoiar a seleção de fornecedores. Contudo, não são encontrados estudos que avaliem o desempenho destes métodos quando usados neste domínio de problema. Diante desta lacuna, este estudo compara os métodos fuzzy TOPSIS (CHEN, 2000) e fuzzy AHP (CHANG, 1996) no apoio à seleção de fornecedores. Esta pesquisa utiliza uma abordagem quantitativa descritiva empírica, baseada em modelagem e simulação. Os métodos fuzzy TOPSIS e fuzzy AHP foram aplicados em um caso ilustrativo de seleção de fornecedores. O desempenho dos fornecedores e o peso dos critérios foram avaliados por um especialista de uma empresa. Modelos de simulação foram implementados usando MATLAB® e aplicados na seleção de fornecedores de uma empresa de uma cadeia de suprimentos automotiva. Cinco fornecedores foram avaliados em relação à qualidade, custo, entrega, perfil e relacionamento. O peso dos critérios e o desempenho dos fornecedores foi avaliado por meio da opinião de um especialista da empresa. Posteriormente, os métodos fuzzy TOPSIS e fuzzy AHP foram comparados em relação à capacidade de apoiar a decisão em grupo, qualificação de fornecedores, escolha final de fornecedores, situações de compra e modelagem de decisões sob incerteza. A eficiência dos métodos em relação à complexidade computacional e à interação requerida com o usuário também foi comparada. Os resultados mostraram que o fuzzy TOPSIS é mais flexível e mais adequado que o fuzzy AHP para modelar diferentes tipos de cenários de seleção de fornecedores. A realização desta discussão é sugerida por Ertugrul e Karakasoglu (2008), e é relevante para ajudar pesquisadores e gestores na escolha de abordagens efetivas para lidar com diferentes cenários de seleção de fornecedores. / Supplier selection has a significant influence on the cost, quality and delivery of products of the buying company. Therefore, supplier selection has become a very critical activity to the performance of the buying company. Several studies presented in the literature propose the use of fuzzy TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) and fuzzy AHP (Analytic Hierarchy Process) to aid the decision process of supplier selection. However, there are no comparative studies of these two methods when applied to the problem of supplier selection. Thus, this paper presents a comparative analysis of the methods fuzzy TOPSIS (Chen, 2000) and fuzzy AHP (Chang, 1996) applied to the problem of supplier selection. A descriptive quantitative approach was adopted as the research method. Algorithms of the methods fuzzy TOPSIS and fuzzy AHP were developed in Matlab© and applied to the selection of suppliers of a company in the automotive production chain. Five suppliers were evaluated regarding quality of conformance, cost, delivery, profile and relationship. The weight of the criteria and the performance of the suppliers were evaluated by specialist opinion from the studied company. The methods Fuzzy TOPSIS e Fuzzy AHP were compared in terms of ability to support the group decision, supplier qualification, final choice of suppliers, buying situations and modeling decisions under uncertainty. The efficiency of the methods with respect to computational complexity and the required user interaction was also compared. The comparative analysis shows that Fuzzy TOPSIS presents better than Fuzzy AHP performance, especially in scenarios in wich many alternatives are evaluated. Thus, Fuzzy TOPSIS is more flexible and appropriate than Fuzzy AHP to deal with supplier selection problem. This paper presents a new study, comparing the methods Fuzzy TOPSIS and Fuzzy AHP. As commented by Ertugrul and Karakasoglu (2008), a study such as this can contribute to the advance of knowledge, helping researchers and practitioners choosing more effective approaches to supplier selection.

A seleção de fornecedores tem impacto significante no custo e na qualidade de produtos manufaturados. Por isso, a seleção de fornecedores passou a ser vista como uma atividade bastante crítica para o desempenho da empresa compradora. Muitos estudos da literatura propõem o uso dos métodos multicritério fuzzy TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) e fuzzy AHP (Analytic Hierarchy Process) para apoiar a seleção de fornecedores. Contudo, não são encontrados estudos que avaliem o desempenho destes métodos quando usados neste domínio de problema. Diante desta lacuna, este estudo compara os métodos fuzzy TOPSIS (CHEN, 2000) e fuzzy AHP (CHANG, 1996) no apoio à seleção de fornecedores. Esta pesquisa utiliza uma abordagem quantitativa descritiva empírica, baseada em modelagem e simulação. Os métodos fuzzy TOPSIS e fuzzy AHP foram aplicados em um caso ilustrativo de seleção de fornecedores. O desempenho dos fornecedores e o peso dos critérios foram avaliados por um especialista de uma empresa. Modelos de simulação foram implementados usando MATLAB® e aplicados na seleção de fornecedores de uma empresa de uma cadeia de suprimentos automotiva. Cinco fornecedores foram avaliados em relação à qualidade, custo, entrega, perfil e relacionamento. O peso dos critérios e o desempenho dos fornecedores foi avaliado por meio da opinião de um especialista da empresa. Posteriormente, os métodos fuzzy TOPSIS e fuzzy AHP foram comparados em relação à capacidade de apoiar a decisão em grupo, qualificação de fornecedores, escolha final de fornecedores, situações de compra e modelagem de decisões sob incerteza. A eficiência dos métodos em relação à complexidade computacional e à interação requerida com o usuário também foi comparada. Os resultados mostraram que o fuzzy TOPSIS é mais flexível e mais adequado que o fuzzy AHP para modelar diferentes tipos de cenários de seleção de fornecedores. A realização desta discussão é sugerida por Ertugrul e Karakasoglu (2008), e é relevante para ajudar pesquisadores e gestores na escolha de abordagens efetivas para lidar com diferentes cenários de seleção de fornecedores. / Supplier selection has a significant influence on the cost, quality and delivery of products of the buying company. Therefore, supplier selection has become a very critical activity to the performance of the buying company. Several studies presented in the literature propose the use of fuzzy TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) and fuzzy AHP (Analytic Hierarchy Process) to aid the decision process of supplier selection. However, there are no comparative studies of these two methods when applied to the problem of supplier selection. Thus, this paper presents a comparative analysis of the methods fuzzy TOPSIS (Chen, 2000) and fuzzy AHP (Chang, 1996) applied to the problem of supplier selection. A descriptive quantitative approach was adopted as the research method. Algorithms of the methods fuzzy TOPSIS and fuzzy AHP were developed in Matlab© and applied to the selection of suppliers of a company in the automotive production chain. Five suppliers were evaluated regarding quality of conformance, cost, delivery, profile and relationship. The weight of the criteria and the performance of the suppliers were evaluated by specialist opinion from the studied company. The methods Fuzzy TOPSIS e Fuzzy AHP were compared in terms of ability to support the group decision, supplier qualification, final choice of suppliers, buying situations and modeling decisions under uncertainty. The efficiency of the methods with respect to computational complexity and the required user interaction was also compared. The comparative analysis shows that Fuzzy TOPSIS presents better than Fuzzy AHP performance, especially in scenarios in wich many alternatives are evaluated. Thus, Fuzzy TOPSIS is more flexible and appropriate than Fuzzy AHP to deal with supplier selection problem. This paper presents a new study, comparing the methods Fuzzy TOPSIS and Fuzzy AHP. As commented by Ertugrul and Karakasoglu (2008), a study such as this can contribute to the advance of knowledge, helping researchers and practitioners choosing more effective approaches to supplier selection.

Atualmente, o ambiente industrial é caracterizado pela intensa globalização, competição entre cadeias de suprimentos, manutenção das competências centrais e terceirização dos demais serviços. Desta forma, a gestão das relações entre os agentes independentes da cadeia de suprimentos e do processo de aquisição são fatores potenciais para o aumento da competitividade empresarial. No contexto da construção civil, a seleção adequada dos parceiros de negócios é um elemento fundamental para o sucesso dos projetos, uma vez que uma grande proporção das atividades podem ser sub-contratadas e possuem relação de precedência entre si. Os suprimentos representam um percentual significativo dos custos das construções, 60%, dado que demonstra o potencial de lucratividade passível de ser atingida ao estruturar o processo de seleção de fornecedores na construção civil. Seleções baseadas no preço prejudicam os sub-empreiteiros e fornecedores mais responsáveis na concorrência, contribuindo para a queda do nível de desempenho e redução da eficiência global do projeto, uma vez que as ineficiências são somadas ao longo da cadeia. Através da estruturação do processo de seleção de fornecedores, é possível mitigar os riscos de suprimentos oriundos de falhas destes contratados ao longo da relação. O objetivo deste trabalho foi desenvolver uma sistemática para seleção de fornecedores críticos, considerando diversos critérios além do preço, entre qualitativos e quantitativos. A abordagem visa também, a eliminação da subjetividade do processo e a extração do melhor fornecedor de forma objetiva. Para tanto, foram definidas dimensões competitivas para avaliar os fornecedores e posteriormente foram utilizados dois métodos quantitativos, Teoria dos Conjuntos Difusos (TCD) e Análise de Componentes Principais (ACP), para selecionar o melhor fornecedor dentre as alternativas, com base na avaliação de múltiplos agentes. / Currently, the industrial environment is characterized by intense globalization, competition between supply chains, maintenance of core competencies and outsourcing of other services. Thus, the management of relationships between independent agents of the supply chain and the procurement process are potential factors for increasing enterprise competitiveness. In the construction context, the proper selection of business partners is a key element for the success of projects, since a large proportion of the activities can be sub-contracted and have precedence relationship between them. Supplies represent a significant percentage of the cost of buildings, 60%, information that demonstrates the potential of profitability that can be achieved by structuring the process of supplier selection in the construction industry. Selection based on price take off from competition the sub-contractors and suppliers more responsible, contributing to the decline in the level of performance and reduction in the overall project efficiency, since inefficiencies are summed through the chain. By structuring the supplier selection process, it is possible to mitigate the supply risk arising from failures of these suppliers during the relationship. The objective of this study was to develop a systematic for selection of critical suppliers, considering several criteria other than price, among qualitative and quantitative. The approach also aims at eliminating the subjectivity of the process and the extraction of the best supplier in an objective way. In order to that, competitive dimensions were set to evaluate vendors and subsequently two quantitative methods, Fuzzy Sets Theory (FST) and Principal Component Analysis (PCA) were used to select the best supplier among the alternatives based on multiple agents evaluation.

Spatial Decision Making as a branch of decision making science deals with geographically related data in order to achieve complex spatial decision problems. Fuzzy set theory is one of the methods that can be used to come up with these types of problems. On the other hand, Geographical Information Systems (GIS) is one of the most powerful tools that we can use to accomplish spatial decision problems. Selection of the suitable site or land-use for the real estate is also a spatial decision making problem. When we consider the initial dynamics of the suitably located property from the point of view of value and potential we observe that the &ldquo / good location&rdquo / is the dominating factor. This study reports on the development of a kind of decision support system for locational suitability of settlements that integrates the fuzzy set (FZ) theory, a rule-based system (RBS) and GIS. This study is thought as the assistant for the property managers that are buyers and sellers. It can function as the property consultant for the buyers when they are looking for a property to buy and also it helps the real estate agencies to sell their properties. On the other hand, different scenarios of the potential areas according to the different user&rsquo / s preferences are depicted and they are joined and compared with the results of the vulnerability to earthquake hazards&rsquo / of the same area. Odunpazari - Eskisehir area is selected for implementation of the case study because of the data availability. As a result of this study, it can be said that most suitable property changes depending on the people&rsquo / s preferences. In addition, it is seen that most of the buildings that are locationally suitable are highly vulnerable to the earthquake hazards.

Face à l'augmentation significative du taux de mortalité par cancer du sein chez les femmes ainsi que la croissance continue du nombre de mammographies réalisées chaque année, le diagnostic assisté par ordinateur devient de plus en plus impératif pour les experts. Dans notre travail de thèse, une attention particulière est accordée aux masses mammaires vu qu'elles représentent le signe de cancer du sein le plus couramment observé en mammographies. Néanmoins, ces images présentent un très faible contraste, ce qui fait que les frontières entre les tissus sains et les masses sont mal définies. C'est ainsi qu'il est difficile de pouvoir discerner avec précision ces masses et de leur définir un contour unique. En outre, la complexité et la grande variabilité des formes des masses mammaires rendent les tâches de diagnostic et de classification difficiles. Dans ce cadre, nous proposons un système d'aide au diagnostic dont le but est la segmentation de masses dans les régions d'intérêt et par la suite la classification de ces masses en deux catégories : bénignes et malignes. La première étape de segmentation est une étape assez délicate vu que les étapes postérieures à savoir la caractérisation et la classification y sont dépendantes. En effet, une mauvaise segmentation peut entrainer une mauvaise prise de décision. Un tel cas peut survenir en raison de l'incertitude et l'imprécision émanant de l'image mammographique. C'est pour cette raison que nous proposons une définition de contours flous permettant de prendre en compte ces types d'imperfections. Ces contours flous sont introduits dans l'énergie d'un contour actif pour modifier son mouvement et aboutir à une délimitation exacte des masses. Une fois les régions d'intérêt sont segmentées, nous présentons une méthode de classification de masses basée sur la théorie des possibilités qui permet de modéliser les ambigüités inhérentes aux connaissances exprimées par l'expert. En outre, cette méthode utilise essentiellement les descripteurs de forme pour caractériser les masses et décider de leur degré de gravité vu que la forme des masses constitue un bon indicateur de gravité.La validation et l'évaluation de ces deux méthodes sont réalisées en utilisant les régions d'intérêt contenant des masses extraites de la base MIAS. Les résultats obtenus sont très intéressants et les comparaisons effectuées ont mis en évidence leurs performances. / In view of the significant increase in breast cancer mortality rate among women as well as the continuous growth in number of mammograms performed each year, computer-aided diagnosis is becoming more and more imperative for experts. In our thesis work, special attention is given to breast masses as they represent the most common sign of breast cancer in mammograms. Nevertheless, mammographic images have very low contrast and breast masses possess ambiguous margins. Thus, it is difficult to distinguish them from the surrounding parenchymal. Moreover, the complexity and the large variability of breast mass shapes make diagnostic and classification challenging tasks.In this context, we propose a computer-aided diagnosis system which firstly segments masses in regions of interests and then classifies them as benign or malignant. Mass segmentation is a critical step in a computer-aided diagnosis system since it affects the performance of subsequent analysis steps namely feature analysis and classification. Indeed, poor segmentation may lead to poor decision making. Such a case may occur due to two types of imperfection: uncertainty and imprecision. Therefore, we propose to deal with these imperfections using fuzzy contours which are integrated in the energy of an active contour to get a fuzzy-energy based active contour model that is used for final delineation of mass.After mass segmentation, a classification method is proposed. This method is based on possibility theory which allows modeling the ambiguities inherent to the knowledge expressed by the expert. Moreover, since shape and margin characteristics are very important for differentiating between benign and malignant masses, the proposed method is essentially based on shape descriptors.The evaluation of the proposed methods was carried out using the regions of interest containing masses extracted from the MIAS base. The obtained results are very interesting and the comparisons made have demonstrated their performances.