Orientador: Peter Sussner / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica / Made available in DSpace on 2018-08-07T23:05:00Z (GMT). No. of bitstreams: 1 Mesquita_MarcosEduardoRibeirodoValle_D.pdf: 1277085 bytes, checksum: 70e93671eb62f360b430f7b81b3c71e3 (MD5) Previous issue date: 2007 / Resumo: Uma Memória Associativa (AM, Associative Memory) é um modelo projetado para armazenar pares de entrada e saída. Sobretudo, uma AM deve ser capaz de recordar uma sida desejada ao mesmo após a apresentação de uma versão incompleta ou destorcida de um padrão de entrada. Essa tese de doutorado discute as Memórias Associativas Morfológicas Nebulosas (FMAMs, Fuzzi Morphological Associative Memories), uma classe de memórias associativas elaboradas para armazenar padrões nebulosas cujos neurÔnios realizam operações elementares da morfologia matemática, i.e., dilatação, erosão, anti-dilatação e anti-erosão. É verificado que os principais modelos de Memória Associativa Nebulosa (FAM, Fuzzy Associative Memory) pertencem à classe das FMAMs. Essa tese introduz as Memórias Associativas Nebulosas Implicativas (IFAMs, Implicative Fuzzy Associative Memories) e suas versões duas com respeito à negação e adjunção. Uma IFAM é uma FMAM onde os pares de entrada e saída são armazenados usando o armazenamento nebuloso implicativo. No armazenamento nebuloso implicativo, os pesos sinápticos. Resultados sobre a fase de armazenamento faz IFAMs e das IFAMs duas são apresentados. Em particular, são demonstrados teoremas sobre a convergência, capacidade de armazenamento, tolerância à ruído e pontos fixos das IFAMs e das IFAMs duais para o caso autoassoplos e resultados teóricos. Finalmente, são apresentadas duas aplicações das FMAMs em problemas de previsão de séries temporais. O primeiro problema trata da previsão da mão-de-obra requerida em industrias metalúrgicas enquanto que a segunda aplicação refere-se a previsão da vazão média mensal da usina hidrelétrica de Furnas / Abstract: Associative memories (AMs) are models that allow for the storage of pattern associations and the retrieval of the desired output pattern upon presentation of a possibly noisy or incomplete version of an input pattern. This thesis discusses fuzzy morphological associative memories (FMAMs), a general class of AMs designed to store fuzzy patterns and described by fuzzy neural networks. Each neuron of a FMAM model performs an elementary operation of mathematical morphology such as dilation, erosion, anti-dilation, and anti-erosion. We show that the most widely known models of fuzzy associative memories (FAMs) belong to the FMAM class. This thesis introduces the implicative fuzzy associative memories (IFAMs) and their dual versions with respect to negation and adjunction. An IFAM is a FMAM model where the patterns are stored by means of implicative fuzzy learning. Specifically, in implicative fuzzy learning, the synaptic weights are given by the minimum of the implication of pre- and postsynaptic activations. We present results concerning the recall and storing phase of IFAM and the dual IFAM models. In particular, we present theorems concerning the convergence, the storage capacity, the noise tolerance, and the fixed points of the IFAM and dual IFAM models in the auto-associative case. We compare the IFAMs with several others FAM models by means of theoretical results and examples. Finally, we present two applications of FMAM models in problems of time-series prediction. The first problem concerns the engineering manpower requirement in steel manufacturing industry while the second refers to the stream flow prediction of a large hydroelectric plant, namely Furnas / Doutorado / Doutor em Matemática Aplicada

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-26T15:06:30Z (GMT). No. of bitstreams: 1 Bueno_FelipeRoberto_M.pdf: 1499339 bytes, checksum: 85b58d8b856fafa47974349e80c1729e (MD5) Previous issue date: 2015 / Resumo: Perceptrons morfológicos (MPs) pertencem à classe de redes neurais morfológicas (MNNs). Estas redes representam uma classe de redes neurais artificiais que executam operações de morfologia matemática (MM) em cada nó, possivelmente seguido pela aplicação de uma função de ativação. Vale ressaltar que a morfologia matemática foi concebida como uma teoria para processamento e análise de objetos (imagens ou sinais), por meio de outros objetos chamados elementos estruturantes. Embora inicialmente desenvolvida para o processamento de imagens binárias e posteriormente estendida para o processamento de imagens em tons de cinza, a morfologia matemática pode ser conduzida de modo mais geral em uma estrutura de reticulados completos. Originalmente, as redes neurais morfológicas empregavam somente determinadas operações da morfologia matemática em tons de cinza, denominadas de erosão e dilatação em tons de cinza, segundo a abordagem umbra. Estas operações podem ser expressas em termos de produtos máximo aditivo e mínimo aditivo, definidos por meio de operações entre vetores ou matrizes, da álgebra minimax. Recentemente, as operações da morfologia matemática fuzzy surgiram como funções de agregação das redes neurais morfológicas. Neste caso, falamos em redes neurais morfológicas fuzzy. Perceptrons híbridos lineares/morfológicos fuzzy foram inicialmente projetados como uma generalização dos perceptrons lineares/morfológicos existentes, ou seja, os perceptrons lineares/morfológicos fuzzy podem ser definidos por uma combinação convexa de uma parte morfológica fuzzy e uma parte linear. Nesta dissertação de mestrado, introduzimos uma rede neural artificial alimentada adiante, representando um perceptron híbrido linear/morfológico fuzzy chamado F-DELP (do inglês fuzzy dilation/erosion/linear perceptron), que ainda não foi considerado na literatura de redes neurais. Seguindo as ideias de Pessoa e Maragos, aplicamos uma suavização adequada para superar a não-diferenciabilidade dos operadores de dilatação e erosão fuzzy utilizados no modelo F-DELP. Em seguida, o treinamento é realizado por intermédio de um algoritmo de retropropagação de erro tradicional. Desta forma, aplicamos o modelo F-DELP em alguns problemas de classificação conhecidos e comparamos seus resultados com os produzidos por outros classificadores / Abstract: Morphological perceptrons (MPs) belong to the class of morphological neural networks (MNNs). These MNNs represent a class of artificial neural networks that perform operations of mathematical morphology (MM) at every node, possibly followed by the application of an activation function. Recall that mathematical morphology was conceived as a theory for processing and analyzing objects (images or signals), by means of other objects called structuring elements. Although initially developed for binary image processing and later extended to gray-scale image processing, mathematical morphology can be conducted very generally in a complete lattice setting. Originally, morphological neural networks only employed certain operations of gray-scale mathematical morphology, namely gray-scale erosion and dilation according to the umbra approach. These operations can be expressed in terms of (additive maximum and additive minimum) matrix-vector products in minimax algebra. It was not until recently that operations of fuzzy mathematical morphology emerged as aggregation functions of morphological neural networks. In this case, we speak of fuzzy morphological neural networks. Hybrid fuzzy morphological/linear perceptrons was initially designed by generalizing existing morphological/linear perceptrons, in other words, fuzzy morphological/linear perceptrons can be defined by a convex combination of a fuzzy morphological part and a linear part. In this master's thesis, we introduce a feedforward artificial neural network representing a hybrid fuzzy morphological/linear perceptron called fuzzy dilation/erosion/linear perceptron (F-DELP), which has not yet been considered in the literature. Following Pessoa's and Maragos' ideas, we apply an appropriate smoothing to overcome the non-differentiability of the fuzzy dilation and erosion operators employed in the proposed F-DELP models. Then, training is achieved using a traditional backpropagation algorithm. Finally, we apply the F-DELP model to some well-known classification problems and compare the results with the ones produced by other classifiers / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-26T17:27:37Z (GMT). No. of bitstreams: 1 Schuster_Tiago_M.pdf: 2910336 bytes, checksum: 1f5147831dd6410a0fdb0c0fa53d94c8 (MD5) Previous issue date: 2015 / Resumo: As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). O advento de sistemas fuzzy tipo-2 sugere o desenvolvimento das FMAMs tipo-2 e em particular FMAMs tipo-2 intervalar, ou FMAMs intervalar (IV-FMAMs). Observemos aqui que a classe dos conjuntos fuzzy, assim como a dos conjuntos fuzzy tipo-2, fuzzy tipo-2 intervalar e fuzzy intervalar sobre um universo arbitrário em conjunção com diferentes escolhas de ordens parciais formam classes de conjuntos L-fuzzy, em que L denota um reticulado completo. Nessa dissertação de mestrado, introduzimos as memórias associativas L-fuzzy (L-FMAMs) com base na morfologia matemática L-fuzzy (L-FMM). Nosso foco está nas FMAMs fuzzy intervalar, uma vez que sistemas fuzzy intervalar têm sido aplicados com sucesso em problemas de engenharia, computação com palavras e raciocínio aproximado. Nós aplicamos os modelos de IV-FMAMs em conjunção com a técnica de clusterização fuzzy c-means intervalar a um problema de predição de série temporal, especificamente o prognóstico da vazão mensal de uma usina hidroelétrica localizada no sudeste brasileiro. Por fim, comparamos as predições produzidas pela abordagem das IV-FMAMs com aquelas produzidas por modelos competitivos da literatura / Abstract: The last decade has witnessed the emergence of a variety of lattice computing approaches towards computational intelligence such as morphological neural networks and fuzzy lattice reasoning / neuro-computing models. Here, the technical term "lattice" refers to a lattice in the mathematical sense of Birkhoff's seminal work. Lattice theory grew out of Boolean algebra and has found a wide range of applications such as mathematical morphology, formal concept analysis, computational intelligence, and fuzzy set theory. Mathematical morphology on complete lattices represents the theoretical basis for a range of computational intelligence models known as morphological neural networks (MNNs) including gray-scale and fuzzy morphological associative memories (FMAMs). The advent of type-2 fuzzy systems suggests the development of type-2 FMAMs and in particular interval type-2 FMAMs or interval-valued FMAMs. Recall that the class of fuzzy sets as well as the classes of type-2, interval type-2, and interval-valued fuzzy sets over an arbitrary universe together with different choices of partial orderings form classes of L-fuzzy sets, where L denotes a complete lattice. In this master's thesis, we introduce L-fuzzy morphological associative memories (L-FMAMs) on the basis of L-FMM. Our focus is on interval-valued FMAMs since interval type-2 fuzzy systems, have found various applications in engineering, computing with words, and approximate reasoning. We applied the aforementioned interval-valued FMAM models in conjunction with the interval-valued fuzzy c-means clustering technique to a time-series prediction problem in industry, namely the problem of forecasting the average monthly streamflow of a hydroelectric plant located in southeastern Brazil, and compared the predictions produced by the IV-FMAM approach with the ones produced by a number of competitive models from the literature / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

This master’s thesis is focused on the issues of utilization of artificial intelligence resources for decision-making support in company and is focused on detection of the client’s solvency for the purposes of loan providing. Fuzzy logic, expert systems and analysis in MS Excel are used here.

Master's thesis deals with the evaluation of suppliers of selected company using fuzzy logic. Designed fuzzy system allows firm to evaluate individual offers and serves as a support for decision-making.

Master's thesis deals with the evaluation of costemers of selected company using fuzzy logic. Designed fuzzy system allows firm to evaluate individual costemers and serves as a support for decision-making.

Compressive strength is one of the most monitored parameter of hardened concrete and it is usually determinated by destructive testing. Non-destructive testing applied on existing constructions uses regression analysis to estimate compressive strength. High variability of outputs and eventually failure of necessary requirements for using regression analysis complicate these methods. The aim of this thesis is to show posibility of using fuzzy clustering in this topic and to compare outputs with classic methods.

Afin d'améliorer la qualité des produits et tendre vers des conceptions fiables et robustes, la simulation numérique joue de nos jours un rôle clé dans de nombreux secteurs de l'ingénierie. Malgré l'utilisation de modèles de plus en plus complexes et réalistes, les corrélations entre les mesures expérimentales et les simulations déterministes ne s'avèrent pas toujours évidentes, en particulier, si le phénomène observé est de nature fugace. Afin de prendre en compte les variations possibles de comportement, des techniques de tirages multiples comme les plans d'expériences, les analyses de sensibilité ou les approches non déterministes peuvent être exploitées. Cependant, ces simulations avancées conduisent inévitablement à des temps de calcul prohibitifs qui ne sont pas en adéquation avec des phases de conception de plus en plus courtes.L'objectif de cette thèse est d'explorer de nouvelles stratégies de résolution pour les problèmes mécaniques, où la non-linéarité de contact frottant et des variations sur les paramètres du modèle numérique sont considérés en même temps. Pour y parvenir, nous avons, dans un premier temps, étudié l'intégration de contrôleurs, basés sur la logique floue, pour résoudre un problème de contact frottant. L'idée proposée est de transformer le problème non linéaire en un ensemble de problèmeslinéaires de tailles réduites que l'on peut réanalyser grâce des développements homotopiques et des techniques de projection. Dans un second temps, nous avons étendu la démarche proposée au cas des problèmes de vibrations induites par le frottement comme le crissement. / To improve the quality of products and tend to reliable and robust designs, numerical simulations have nowadays taken a key role in many engineering domains. In spite of more complex and realistic numerical models, the correlation between a deterministic simulation and experimentations are not obvious, especially if the observed phenomenon have a fugitive nature. To take into account possible evolutions of behaviour, multiple samplings techniques such as designs of experiments, sensitivity analyses or non-deterministic approaches are currently performed. Nevertheless, these advanced simulations necessarily generate prohibitive computational times, which are not compatible with more and more shorter design steps.The aim of this work is to explore new numerical ways to solve mechanical problems including both the contact nonlinearity, the friction and several variability on model parameters. To achieve this objective, the integration of Fuzzy Logic Controllers has been first studied in the case of static frictional contact problems. The proposed idea is to decompose the non linear problem in a set of reduced linear problems. These last ones can be reanalyzed thanks to homotopy developments and projection techniques as a function of introduced perturbations. Second, the proposed strategy has been extended to the case of friction induced vibrations problems such as squeal.

Lors de la conception d’un frein, le confort et le bien-être du consommateur font partie des critères principaux. En effet, les instabilités de crissement, qui engendrent une des pollutions acoustiques les plus importantes, représentent un challenge actuel pour la communauté scientifique et les industriels du domaine. Dans le cadre de cette thèse, nous nous sommes intéressés à la mise en évidence du caractère variable du crissement, observé pour deux systèmes de freinage d’un même véhicule, grâce à des plans d’expériences, expérimental et numérique. Pour être représentatif d’une famille de structures, il est désormais indéniable qu’il faille prendre en compte les variabilités observées sur de multiples paramètres liés au système étudié dès la phase de conception. L’enrichissement des simulations déterministes actuelles nécessite la mise en place d’outils non déterministes rapides et respectant le conservatisme des solutions étudiées. Pour ce faire, nous avons contribué au développement de méthodes numériques dédiées à la propagation des données floues dans le cas des graphes de coalescence, à la détermination des positions d’équilibre de corps en contact frottant à partir d’une méthode de régulation basée sur la logique floue. Cette solution permet d’appliquer une technique de projection pour réduire le coût numérique en utilisant des bases modales des composants réanalysées par un développement homotopique. / During a brake design, consumer comfort and well-being are the main criteria. Indeed, squeal instabilities, that produce main acoustic pollution, represent a current challenge in the scientific community and for industrials. In this thesis, we interest first in the highlight of the variability of squeal, observed for two brake systems of a same vehicle, thanks to experimental and numerical designs of experiments. To be representative of a structure family, it is now undeniable that we must take into account variability observed in various parameters of the studied system, from the design phase. To enrich existing deterministic simulations, quick non deterministic tools must be established, respecting the studied solutions conservatism. For this, we have contributed to the development of numerical methods to propagate fuzzy data in the case of diagram of coalescence, to determine the equilibrium position of frictional contact bodies with a fuzzy logic controller. This solution allows to apply a projection technique for reducing the computational cost. The modal bases of components are reanalyzed by homotopy perturbation.

Récemment, plusieurs applications, dans lesquelles différentes entités interagissent dans un environnement dynamique, soulignent l’intérêt de l’utilisation des architectures multi-agents. Ces architectures offrent, dans ce cadre, un certain nombre d’avantages, tels que l’autonomie, la réactivité et la capacité de prise de décision. Elles manquent cependant de capacité sociale et de connaissances sur son environnement, notamment lorsqu’il s’agit d’un environnement dynamique. En effet, quand un agent interagit avec le monde réel, il doit prendre en compte les évènements qui peuvent survenir tout en considérant centaines contraintes telles que le temps et l’espace. En outre, les agents doivent faire face à l’incertitude liée aux applications réelles afin de fournir une représentation fidèle du monde réel. Dans le cadre de cette thèse, nous proposons un modèle formel de recommandation des plans qui améliore le processus de prise de décision des agents dans un environnement spatio-temporel et incertain. Pour formaliser les comportements cognitifs des agents dans notre système nommé CARS, en anglais ``Cognitive Agent-based Recommender System '', nous avons étendu l’architecture BDI qui se base sur le modèle `` Croyance-Désir-Intention'' pour prendre en compte les différents contextes liés à des applications réelles en particulier le contexte social. Par ailleurs, nous avons également utilisé la théorie possibiliste afin de considérer l’incertitude dans l’état motivationnel d’un agent (c’est à dire ses croyances, désirs, objectifs ou intentions). Pour répondre aux besoins des applications réelles, tels que les systèmes de recommandation relatives au trafic et navigation, nous proposons une représentation spatiotemporelle des croyances et des intentions d’un agent. Cette représentation permettra l’anticipation de certaines intentions, de manière à recommander un plan qui sera optimal pour un utilisateur. Compte tenu l’incomplétude/l’imprécision liée aux données spatiotemporelles, nous avons étendu le modèle proposé pour raisonner avec des croyances et intentions floues. Une évaluation du modèle proposé a été menée en utilisant une simulation multi-agent, dans un scenario réel de circulation routière. Cette simulation a offert un environnement virtuel qui a mis en lumière, après avoir testé les différentes fonctionnalités du modèle, les principaux points forts ainsi que leslacunes liées à l’architecture multi-agents proposée. / Recently, many real-world applications where different entities interact in a dynamic environment, consider the use of agents in their architectures due principally to their autonomy, reactivity and decision-making abilities. Though these systems can be made intelligent, using Artificial Intelligence (AI) techniques, agents still lack of social abilities and have limited knowledge of their environment and in particular when it comes to a dynamic environment. In fact, when operating in the real world, agents need to deal with unexpected events considering both changes in time and space. Moreover, agents must face the uncertainty, which pervades real-world scenarios in order to provide an accurate representation of the world. In this thesis, we introduce and evaluate a formal framework for recommending plans to agents in the decision making process, when they deal with uncertain spatio-temporal information. The agent-based architecture we propose to address this issue, called CARS (Cognitive Agent-based Recommender System), has been designed by extending the well-known Belief-Desire-Intention (BDI) architecture to incorporate further capabilities to support reasoning with different types of contextual information, including the social context. Uncertainty on the agent's beliefs, desires and intentions is modeled using possibility theory. To meet the requirements of real-world applications, e.g., traffic and navigation recommendation systems, we define a spatio-temporal representation of the agents' beliefs and intentions. Using such a formal framework, anticipatory reasoning about intentional dynamics can be performed with the aim to recommend an optimal plan to a certain user. Since spatio-temporal data is often considered as incomplete and/or vague, we extended the formal framework with a fuzzy representation of spatio-temporal beliefs and intentions. The framework is evaluated through an Agent Based Simulation (ABS) in a real-world traffic scenario. This ABS allowed us to create a virtual environment to test the impact of the different features of our framework as well as to evaluating the main strengths and weaknesses of the proposed agent architecture.