應用模糊調查與統計方法去瞭解國中數學評量試題在教師與學生間以及學生不同背景（性別、對數學喜歡程度、課後數學練習時間及有無參加數學相關課外活動）對試題難易度的認知差異。結果顯示：在教師與學生之間、性別、學生對數學喜歡程度及課後數學練習時間方面有顯著差異，但是在參加課後數學相關活動方面對於數學科試題的難易度認知並沒有顯著的差異性存在。 / Using fuzzy statistical methods to understand whether the cognitive difficulty scales of the junior high school mathematics assessment questions shows difference between those given by teachers and students, by students with different genders, with different preferences, with different amounts of time spent on math practice after school, with participation or not in various math related seminars. Result demonstrates that significant difference between teachers and students, between students with different genders, between students with different preferences, and between students with different amounts of time spent on math practice after school. However, there is no significant difference between students with participation or not in various math related seminars.

<p>Disertacija se bavi problematikom unapređenja informatičkih kompetencija studenata. Osnovna funkcija sistema je personalizacija nastavnih sadržaja prema trenutnom nivou znanja studenta. Na osnovu toga dizajniran je model inteligentnog tutorskog sistema koji se sastoji od osnovnih funkcionalnih dijelova: modela Tutor, modela Student i mehanizma za zaključivanje. U sistemu su razvijeni moduli za procjenu znanja studenta, isporuku nastavnih sadržaja, unapređenja kompetencija i automatsku sintezu IF...THEN pravila. Procjena znanja vr&scaron;i se pomoću Mamdani fazi inferentnog metoda. Mehanizam za isporuku nastavnih sadržaja radi na principu Alfa algoritma. Automatska sinteza IF...THEN pravila bazirana je na Teoriji grubih skupova. Unapređenje kompetencija vr&scaron;i se pomijeranjem u desno parametara funkcije pripadnosti koja predstavlja studentove kompetencije. Eksperimentalno testiranje rada sistema izvr&scaron;eno je na Java programskom jeziku.</p> / <p>The present dissertation deals with the issue of upgrading the students&rsquo; ICT competencies. The fundamental function of the system is aimed at personalization of educational contents in accordance with the student&rsquo;s current level of knowledge. On the basis of this, a model of the intelligent tutoring system that consists of basic functional components &ndash; the Tutor model, the Student model and a deduction mechanism &ndash; has been designed. Within this system the modules for assessing students&rsquo; knowledge, delivery of educational contents, competence upgrading and automatic synthesis of IF ... THEN rules have been developed. The knowledge assessment is carried out by means of a Mamdani&rsquo;s fuzzy inference method. The mechanism for educational content delivery operates on the principle of an Alpha algorithm. The automatic synthesis of IF ... THEN rules is based on a rough set theory. The upgrading of the competencies is performed by moving to the right the parameters of a membership function which represents the student&#39;s competence. Experimental testing of the system was carried out using the Java programming language.</p>

Orientador: Suely Cunha Amaro Mantovani / Resumo: No estudo dos manipuladores são utilizados os conceitos da cinemática direta e a inversa. No cálculo da cinemática direta tem-se a facilidade da notação de Denavit-Hartenberg, mas o desafio maior é a resolução da cinemática inversa, que se torna mais complexa conforme aumentam os graus de liberdade do manipulador, além de apresentar múltiplas soluções. As variáveis angulares obtidas pelas equações da cinemática inversa são utilizadas pelo controlador, para posicionar o órgão terminal do manipulador em um ponto específico de seu volume de trabalho. Na busca de alternativas para contornar estes problemas, neste trabalho utilizam-se os Modelos Adaptativos de Inferência Neuro-Fuzzy - ANFIS para a resolução da cinemática inversa, por meio de simulações, para obter o posicionamento de um manipulador robótico de 5 graus de liberdade, composto por sete servomotores controlados pela plataforma de desenvolvimento Intel® Galileo Gen 2, usado como caso de estudo. Nas simulações usamse ANFIS com uma arquitetura com três e quatro funções de pertinência de entrada, do tipo gaussiana. O desempenho da arquitetura da ANFIS implementada foi comparado com uma Rede Perceptron Multicamadas, demonstrando com os resultados favoráveis a ANFIS, a sua capacidade de aprender e resolver com baixo erro quadrático médio e com precisão, a cinemática inversa para o manipulador em estudo. Verifica-se também, que a performance das ANFIS melhora, quanto à precisão dos resultados, demonstrado pelo desvio médio d... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: In the study of manipulator’s, the concepts of direct and inverse kinematics are used. In the computation of forward kinematics, it has of the ease of Denavit-Hartenberg notation, but the biggest challenge is the resolution of the inverse kinematics, which becomes more complex as the manipulator's degrees of freedom increase, besides presenting multiple solutions. The angular variables obtained by the inverse kinematics equations are used by the controller to position the terminal organ of the manipulator at a specific point in its work volume. In the search for alternatives to overcome these problems, in this work, the Adaptive Neuro-Fuzzy Inference Models (ANFIS) are used to solve the inverse kinematics, by means of simulations, to obtain the positioning of a robot manipulator of 5 degrees of freedom, consisting of seven servomotors controlled by the Intel® Galileo Gen 2 development platform, used as a case's study . In the simulations ANFIS's architecture are used three and four Gaussian membership functions of input. The performance of the implemented ANFIS architecture was compared to a Multi-layered Perceptron Network, demonstrating with the favorable results the ANFIS, its ability to learn and solve with low mean square error and with precision, the inverse kinematics for the manipulator under study. It is also verified that the performance of the ANFIS improves, as regards the accuracy of the results in the training process, , demonstrated by the mean deviation of the... (Complete abstract click electronic access below) / Mestre

本文以人對事物現象認識的感覺與模糊性作為切入點，闡述模糊性是人對事物認識的一種表徵及反應。然後，引入模糊集合的定義及刻劃模糊集合的表示函數—隸屬度，對模糊集合的各種運算、模糊矩陣、模糊差集以及宇集等內容進行較詳細的討論，並以各種事例說明一些相關概念和運算。 最後，再深入探討如何以模糊矩陣表示圖學中有向圖的問題。 / This article is to focus on the understanding of human being to the phenomenon of things as well as the fuzziness. Then, by applying the definition of the fuzzy set and explaining the membership of fuzzy set, we are going to have a detailed discussion of the operation of fuzzy set, fuzzy matrix, fuzzy subtraction and universal set. Examples are given to demonstrate some of the related concepts and expression. Next, further questions about how to display directed graph in the graph theory with fuzzy matrix will be discussed .

In the dissertation the solution approaches for different fuzzy optimization problems are presented. The single-level optimization problem with fuzzy objective is solved by its reformulation into a biobjective optimization problem. A special attention is given to the computation of the membership function of the fuzzy solution of the fuzzy optimization problem in the linear case. Necessary and sufficient optimality conditions of the the convex nonlinear fuzzy optimization problem are derived in differentiable and nondifferentiable cases. A fuzzy optimization problem with both fuzzy objectives and constraints is also investigated in the thesis in the linear case. These solution approaches are applied to fuzzy bilevel optimization problems. In the case of bilevel optimization problem with fuzzy objective functions, two algorithms are presented and compared using an illustrative example. For the case of fuzzy linear bilevel optimization problem with both fuzzy objectives and constraints k-th best algorithm is adopted.

Η παρούσα διατριβή ασχολείται με τη μελέτη και την ανάπτυξη μοντέλων ταξινόμησης τα οποία βασίζονται στα Πιθανοτικά Νευρωνικά Δίκτυα (ΠΝΔ). Τα προτεινόμενα μοντέλα αναπτύχθηκαν ενσωματώνοντας στατιστικές μεθόδους αλλά και μεθόδους από διάφορα πεδία της Υπολογιστικής Νοημοσύνης (ΥΝ). Συγκεκριμένα, χρησιμοποιήθηκαν οι Διαφοροεξελικτικοί αλγόριθμοι βελτιστοποίησης και η Βελτιστοποίηση με Σμήνος Σωματιδίων (ΒΣΣ) για την αναζήτηση βέλτιστων τιμών των παραμέτρων των ΠΝΔ. Επιπλέον, ενσωματώθηκε η τεχνική bagging για την ανάπτυξη συστάδας μοντέλων ταξινόμησης. Μια άλλη προσέγγιση ήταν η ανάπτυξη ενός Μπεϋζιανού μοντέλου για την εκτίμηση των παραμέτρων του ΠΝΔ χρησιμοποιώντας τον δειγματολήπτη Gibbs. Επίσης, ενσωματώθηκε μια Ασαφή Συνάρτηση Συμμετοχής για την καλύτερη στάθμιση των τεχνητών νευρώνων του ΠΝΔ καθώς και ένα νέο σχήμα διάσπασης του συνόλου εκπαίδευσης σε προβλήματα ταξινόμησης πολλαπλών κλάσεων όταν ο ταξινομητής μπορεί να επιτύχει ταξινόμηση δύο κλάσεων.Τα προτεινόμενα μοντέλα ταξινόμησης εφαρμόστηκαν σε μια σειρά από πραγματικά προβλήματα από διάφορες επιστημονικές περιοχές με ενθαρρυντικά αποτελέσματα. / The present thesis is dealing with the study and the development of classification models that are based on Probabilistic Neural Networks (PNN). The proposed models were developed by the incorporation of statistical methods as well as methods from several fields of Computational Intelligence (CI) into PNNs. In particular, the Differential Evolutionary optimization algorithms and Particle Swarm Optimization algorithms are employed for the search of promising values of PNNs’ parameters. Moreover, the bagging technique was incorporated for the development of an ensemble of classification models. Another approach was the construction of a Bayesian model for the estimation of PNN’s parameters utilizing the Gibbs sampler. Furthermore, a Fuzzy Membership Function was incorporated to achieve an improved weighting of PNN’s neurons. A new decomposition scheme is proposed for multi-class classification problems when a two-class classifier is employed. The proposed classification models were applied to a series of real-world problems from several scientific areas with encouraging results.

Transitions between normal and pathological brain states are manifested differently in the electroencephalogram (EEG). Traditional discrimination of these states is often subject to bias and strict definitions. A fuzzy logic-based analysis can permit the classification and tracking of brain states in a non-subjective and unsupervised manner. In this thesis, the combination of fuzzy c-means (FCM) clustering, wavelet, and information theory has revealed notable frequency features in epilepsy and anaesthetic-induced unconsciousness. It was shown that entropy changes in membership functions correlate to specific epileptiform activity and changes in anaesthetic dosages. Seizure episodes appeared in the 31-39 Hz band, suggesting changes in cortical functional organization. The induction of anaesthetics appeared in the 64-72 Hz band, while the return to consciousness appeared in the 32-40 Hz band. Changes in FCM activity were associated with the concentration of anaesthetics. These results can help with the treatment of epilepsy and the safe administration of anaesthesia.

Transitions between normal and pathological brain states are manifested differently in the electroencephalogram (EEG). Traditional discrimination of these states is often subject to bias and strict definitions. A fuzzy logic-based analysis can permit the classification and tracking of brain states in a non-subjective and unsupervised manner. In this thesis, the combination of fuzzy c-means (FCM) clustering, wavelet, and information theory has revealed notable frequency features in epilepsy and anaesthetic-induced unconsciousness. It was shown that entropy changes in membership functions correlate to specific epileptiform activity and changes in anaesthetic dosages. Seizure episodes appeared in the 31-39 Hz band, suggesting changes in cortical functional organization. The induction of anaesthetics appeared in the 64-72 Hz band, while the return to consciousness appeared in the 32-40 Hz band. Changes in FCM activity were associated with the concentration of anaesthetics. These results can help with the treatment of epilepsy and the safe administration of anaesthesia.

The Intelligent Algorithm is designed for theusing a Battery source. The main function is to automate the Hybrid System through anintelligent Algorithm so that it takes the decision according to the environmental conditionsfor utilizing the Photovoltaic/Solar Energy and in the absence of this, Fuel Cell energy isused. To enhance the performance of the Fuel Cell and Photovoltaic Cell we used batterybank which acts like a buffer and supply the current continuous to the load. To develop the main System whlogic based controller was used. Fuzzy Logic based controller used to develop this system,because they are chosen to be feasible for both controlling the decision process and predictingthe availability of the available energy on the basis of current Photovoltaic and Battery conditions. The Intelligent Algorithm is designed to optimize the performance of the system and to selectthe best available energy source(s) in regard of the input parameters. The enhance function of these Intelligent Controller is to predict the use of available energy resources and turn on thatparticular source for efficient energy utilization. A fuzzy controller was chosen to take thedecisions for the efficient energy utilization from the given resources. The fuzzy logic basedcontroller is designed in the Matlab-Simulink environment. Initially, the fuzzy based ruleswere built. Then MATLAB based simulation system was designed and implemented. Thenthis whole proposed model is simulated and tested for the accuracy of design and performanceof the system.

Abstract In time series analysis, we often find the trend of dynamic data changing with time. Using the traditional model fitting can't get a good explanation for dynamic data. Therefore, many scholars developed various methods for model construction. The major drawback with most of the methods is that personal viewpoint and experience in model selection are usually influenced in them. Therefore, this paper presents a new approach on genetic-based modeling for the nonlinear time series. The research is based on the concepts of evolution theory as well as natural selection. In order to find a leading model from the nonlinear time series, we make use of the evolution rule: survival of the fittest. Through the process of genetic evolution, the AIC (Akaike information criteria) is used as the adjust function, and the membership function of the best-fitted models are calculated as performance index of chromosome. Empirical example shows that the genetic model can give an efficient explanation in analyzing Taiwan exchange rates, especially when the structure change occurs.