Tesis sobre el tema "Fuzzy neural networks"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Fuzzy neural networks".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Glackin, Cornelius. "Fuzzy spiking neural networks". Thesis, University of Ulster, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.505831.
Texto completoBrande, Julia K. Jr. "Computer Network Routing with a Fuzzy Neural Network". Diss., Virginia Tech, 1997. http://hdl.handle.net/10919/29685.
Texto completoPh. D.
Pirovolou, Dimitrios K. "The tracking problem using fuzzy neural networks". Diss., Georgia Institute of Technology, 1996. http://hdl.handle.net/1853/14824.
Texto completoFrayman, Yakov y mikewood@deakin edu au. "Fuzzy neural networks for control of dynamic systems". Deakin University. School of Computing and Mathematics, 1999. http://tux.lib.deakin.edu.au./adt-VDU/public/adt-VDU20051017.145550.
Texto completoLeng, Gang. "Algorithmic developments for self-organising fuzzy neural networks". Thesis, University of Ulster, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.405165.
Texto completoRENTERIA, ALEXANDRE ROBERTO. "TRAFFIC CONTROL THROUGH FUZZY LOGIC AND NEURAL NETWORKS". PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2002. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=2695@1.
Texto completoEste trabalho apresenta a utilização de lógica fuzzy e de redes neurais no desenvolvimento de um controlador de semáforos - o FUNNCON. O trabalho realizado consiste em quatro etapas principais: estudo dos fundamentos de engenharia de tráfego; definição de uma metodologia para a avaliação de cruzamentos sinalizados; definição do modelo do controlador proposto; e implementação com dados reais em um estudo de caso.O estudo sobre os fundamentos de engenharia de tráfego aborda a definição de termos,os parâmetros utilizados na descrição dos fluxos de tráfego, os tipos de cruzamentos e seus semáforos, os sistemas de controle de tráfego mais utilizados e as diversas medidas de desempenho.Para se efetuar a análise dos resultados do FUNNCON, é definida uma metodologia para a avaliação de controladores. Apresenta-se, também, uma investigação sobre simuladores de tráfego existentes, de modo a permitir a escolha do mais adequado para o presente estudo. A definição do modelo do FUNNCON compreende uma descrição geral dos diversos módulos que o compõem. Em seguida, cada um destes módulos é estudado separadamente: o uso de redes neurais para a predição de tráfego futuro; a elaboração de um banco de cenários ótimos através de um otimizador; e a criação de regras fuzzy a partir deste banco.No estudo de caso, o FUNNCON é implementado com dados reais fornecidos pela CET-Rio em um cruzamento do Rio de Janeiro e comparado com o controlador existente.É constatado que redes neurais são capazes de fornecer bons resultados na predição do tráfego futuro. Também pode ser observado que as regras fuzzy criadas a partir do banco de cenários ótimos proporcionam um controle efetivo do tráfego no cruzamento estudado. Uma comparação entre o desempenho do FUNNCON e o do sistema atualmente em operação é amplamente favorável ao primeiro.
This work presents the use of fuzzy logic and neural networks in the development of a traffic signal controller - FUNNCON. The work consists of four main sections: study of traffic engineering fundamentals; definition of a methodology for evaluation of traffic controls; definition of the proposed controller model; and implementation on a case study using real data.The study of traffic engineering fundamentals considers definitions of terms,parameters used for traffic flow description, types of intersections and their traffic signals,commonly used traffic control systems and performance measures.In order to analyse the results provided by FUNNCON, a methodology for the evaluation of controllers is defined. The existing traffic simulators are investigated, in order to select the best one for the present study.The definition of the FUNNCON model includes a brief description of its modules.Thereafter each module is studied separately: the use of neural networks for future traffic prediction; the setup of a best scenario database using an optimizer; and the extraction of fuzzy rules from this database.In the case study, FUNNCON is implemented with real data supplied by CET-Rio from an intersection in Rio de Janeiro; its performance is compared with that of the existing controller.It can be observed that neural networks can present good results in the prediction of future traffic and that the fuzzy rules created from the best scenario database lead to an effective traffic control at the considered intersection. When compared with the system in operation, FUNNCON reveals itself much superior.
Kim, Hung-man. "Implementing adaptive fuzzy logic controllers with neural networks". Diss., The University of Arizona, 1995. http://hdl.handle.net/10150/187160.
Texto completoGabrys, Bogdan. "Neural network based decision support : modelling and simulation of water distribution networks". Thesis, Nottingham Trent University, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.387534.
Texto completoBordignon, Fernando Luis. "Aprendizado extremo para redes neurais fuzzy baseadas em uninormas". [s.n.], 2013. http://repositorio.unicamp.br/jspui/handle/REPOSIP/259061.
Texto completoDissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação
Made available in DSpace on 2018-08-22T00:50:20Z (GMT). No. of bitstreams: 1 Bordignon_FernandoLuis_M.pdf: 1666872 bytes, checksum: 4d838dfb4ec418698d9ecd3b74e7c981 (MD5) Previous issue date: 2013
Resumo: Sistemas evolutivos são sistemas com alto nível de adaptação capazes de modificar simultaneamente suas estruturas e parâmetros a partir de um fluxo de dados, recursivamente. Aprendizagem a partir de fluxos de dados é um problema contemporâneo e difícil devido à taxa de aumento da dimensão, tamanho e disponibilidade temporal de dados, criando dificuldades para métodos tradicionais de aprendizado. Esta dissertação, além de apresentar uma revisão da literatura de sistemas evolutivos e redes neurais fuzzy, aborda uma estrutura e introduz um método de aprendizagem evolutivo para treinar redes neurais híbridas baseadas em uninormas, usando conceitos de aprendizado extremo. Neurônios baseados em uninormas fundamentados nas normas e conormas triangulares generalizam neurônios fuzzy. Uninormas trazem flexibilidade e generalidade a modelos neurais fuzzy, pois elas podem se comportar como normas triangulares, conormas triangulares, ou de forma intermediária por meio do ajuste de elementos identidade. Este recurso adiciona uma forma de plasticidade em modelos de redes neurais. Um método de agrupamento recursivo para granularizar o espaço de entrada e um esquema baseado no aprendizado extremo compõem um algoritmo para treinar a rede neural. _E provado que uma versão estática da rede neural fuzzy baseada em uninormas aproxima funções contínuas em domínios compactos, ou seja, _e um aproximador universal. Postula-se, e experimentos computacionais endossam, que a rede neural fuzzy evolutiva compartilha capacidade de aproximação equivalente, ou melhor, em ambientes dinâmicos, do que as suas equivalentes estáticas
Abstract: Evolving systems are highly adaptive systems able to simultaneously modify their structures and parameters from a stream of data, online. Learning from data streams is a contemporary and challenging issue due to the increasing rate of the size and temporal availability of data, turning the application of traditional learning methods limited. This dissertation, in addition to reviewing the literature of evolving systems and neuro fuzzy networks, addresses a structure and introduces an evolving learning approach to train uninorm-based hybrid neural networks using extreme learning concepts. Uninorm-based neurons, rooted in triangular norms and conorms, generalize fuzzy neurons. Uninorms bring flexibility and generality to fuzzy neuron models as they can behave like triangular norms, triangular conorms, or in between by adjusting identity elements. This feature adds a form of plasticity in neural network modeling. An incremental clustering method is used to granulate the input space, and a scheme based on extreme learning is developed to train the neural network. It is proved that a static version of the uninorm-based neuro fuzzy network approximate continuous functions in compact domains, i.e. it is a universal approximator. It is postulated and computational experiments endorse, that the evolving neuro fuzzy network share equivalent or better approximation capability in dynamic environments than their static counterparts
Mestrado
Engenharia de Computação
Mestre em Engenharia Elétrica
Aimejalii, K., Keshav P. Dahal y M. Alamgir Hossain. "GA-based learning algorithms to identify fuzzy rules for fuzzy neural networks". IEEE, 2007. http://hdl.handle.net/10454/2553.
Texto completoKaraboga, Dervis. "Design of fuzzy logic controllers using genetic algorithms". Thesis, Cardiff University, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.296639.
Texto completoMorphet, Steven Brian Işık Can. "Modeling neural networks via linguistically interpretable fuzzy inference systems". Related electronic resource: Current Research at SU : database of SU dissertations, recent titles available full text, 2004. http://wwwlib.umi.com/cr/syr/main.
Texto completoNejatali, Abdolhossein. "Electrical impedance tomography with neural networks and fuzzy sets". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/nq23645.pdf.
Texto completoDias, De Macedo Filho Antonio. "Microwave neural networks and fuzzy classifiers for ES systems". Thesis, University College London (University of London), 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.244066.
Texto completoHsu, Cheng-Yu. "Condition monitoring of fluid power systems using artificial neural networks". Thesis, University of Bath, 1995. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.295443.
Texto completoVetcha, Sarat Babu. "Fault diagnosis in pumps by unsupervised neural networks". Thesis, University of Sussex, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.300604.
Texto completoGonzález, Marek. "Fuzzy neuronové sítě". Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-234941.
Texto completoNukala, Ramesh Babu. "Neuro-fuzzy controllers for unstable systems". Thesis, Lancaster University, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.364362.
Texto completoJi, Wei. "Artificial neural networks and fuzzy systems in bladder cancer prognosis". Thesis, Coventry University, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.417616.
Texto completoRodriguez, Carlos Alberto Ramirez. "Fuzzy neural networks for classsification problems with uncertain data input". Thesis, University of Surrey, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.336530.
Texto completoMACHADO, MARIA AUGUSTA SOARES. "IDENTIFICATION OF NON-SEASONAL TIME SERIES THROUGH FUZZY NEURAL NETWORKS". PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2000. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=7554@1.
Texto completoObservando a dificuldade de batimento (match) dos padrões de comportamento das funções de autocorrelação e de autocorrelação parcial teóricas com as respectivas funções e as autocorrelação e de autocorrelação parcial estimadas de uma séries temporal, aliada ao fato da dificuldade em definir um número em específico como delimitador inequívoco do que seja um lag significativo, tornam clara a dose de julgamento subjetivo a ser realizado por um especialista de análise de séries temporais na tomada de decisão sobre a estrutura de Box & Jenkins adequada a ser escolhida para modelar o processo estocástico sendo estudado. A matemática nebulosa permite a criação de sistemas de inferências nebulosas (inferência dedutiva) e representa o conhecimento de forma explícita, através de regras nebulosas, possibilitando, facilmente, o entendimento do sistema em estudo. Por outro lado, um modelo de redes neurais representa o conhecimento de forma implícita, adquirido através de exemplos (dados), possuindo excelente capacidade de generalização (inferência indutiva). Esta tese apresenta um sistema especialista composto de cinco redes neurais nebulosas do tipo retropropagação para o auxílio na análise de séries temporais não sazonais. O sistema indica ao usuário a estrutura mais adequada, dentre as estruturas AR(1), MA (1), AR(2), MA(2) e ARMA(1,1), tomando como base a menor distância Euclidiana entre os valores esperados e as saídas das redes neurais nebulosas.
It is well known the difficulties associated with the tradicional procedure for model identification of the Box & Jenkins model through the pattern matching of the theoretical and estimated ACF and PACF. The decision on the acceptance of the null hypothesis of zero ACF (or PACF) for a given lag is based on a strong asymptotic result, particularly for the PACF, leading, sometimes, to wrong decisions on the identified order of the models. The fuzzy logic allows one to infer system governed by incomplete or fuzzy knowledge (deductive inference) using a staighforward formulation of the problem via fuzzy mathematics. On the other hand, the neural network represent the knowledge in a implicit manner and has a great generalization capacity (inductive inference). In this thesis we built a specialist system composed of 5 fuzzy neural networks to help on the automatic identificationof the following Box & Jenkins ARMA structure AR(1), MA(1), AR(2), MA(2) and ARMA (1,1), through the Euclidian distance between the estimated output of the net and the corresponding patterns of each one of the five structures.
Ramirez-Rodriguez, Carolos Alberto. "Fuzzy neural networks for classification problems with uncertain data input". Thesis, University of Surrey, 1996. http://epubs.surrey.ac.uk/843376/.
Texto completoTripathi, Nishith D. "Generic Adaptive Handoff Algorithms Using Fuzzy Logic and Neural Networks". Diss., Virginia Tech, 1997. http://hdl.handle.net/10919/29267.
Texto completoPh. D.
Jin, Y. "Intelligent neural control and its applications in robotics". Thesis, University of the West of England, Bristol, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.240830.
Texto completoCanuto, Anne Magaly de Paula. "Combining neural networks and fuzzy logic for applications in character recognition". Thesis, University of Kent, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.344107.
Texto completoStyliandidis, Orestis. "Knowledge from data : concept induction using fuzzy and neural methods". Thesis, University of Bristol, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.361076.
Texto completoVasilic, Slavko. "Fuzzy neural network pattern recognition algorithm for classification of the events in power system networks". Diss., Texas A&M University, 2004. http://hdl.handle.net/1969.1/436.
Texto completoWu, Tzung-Han y 吳宗翰. "Study on Ramsay Fuzzy Neural Networks". Thesis, 2008. http://ndltd.ncl.edu.tw/handle/8548kw.
Texto completo國立中山大學
電機工程學系研究所
96
In this thesis, M-estimators with Ramsay’s function used in robust regression theory for linear parametric regression problems will be generalized to nonparametric Ramsay fuzzy neural networks (RFNNs) for nonlinear regression problems. Emphasis is put particularly on the robustness against outliers. This provides alternative learning machines when faced with general nonlinear learning problems. Simple weight updating rules based on incremental gradient descent and iteratively reweighted least squares (IRLS) will be derived. Some numerical examples will be provided to compare the robustness against outliers for usual fuzzy neural networks (FNNs) and the proposed RFNNs. Simulation results show that the RFNNs proposed in this thesis have good robustness against outliers.
Chen, Shih-Chieh y 陳士傑. "Fuzzy modelling using hybrid neural networks". Thesis, 1996. http://ndltd.ncl.edu.tw/handle/03622777357915110698.
Texto completo國立中央大學
機械工程學系
84
A neural-network-based structure learning fuzzy controller is proposed.The consequent of a rule is assumed to be a linear combination of thefuzzy sets associated with an output linguistic variable as against thetraditional fuzzy rules whose consequents are decided by an experiencedoperator. The defuzzified result of these proposed fuzzy rules is provedto conform with the general meaning of a defuzzifier and is shown to berealizable through a neural network in which the coefficients associatedwith the linear combination are tuned from examples. The proposed fuzzyrules are also shown to be robust with respect to any reasonable changesin the antecedents, which means the parameter learning of the antecedentsis unnecessary in our scheme. Lastly, the capability of learning of theproposed fuzzy logic controller is demonstrated through examples.
Wu, Hsu-Kun y 吳旭焜. "Research on Robust Fuzzy Neural Networks". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/24109251503970382326.
Texto completo國立中山大學
電機工程學系研究所
99
In many practical applications, it is well known that data collected inevitably contain one or more anomalous outliers; that is, observations that are well separated from the majority or bulk of the data, or in some fashion deviate from the general pattern of the data. The occurrence of outliers may be due to misplaced decimal points, recording errors, transmission errors, or equipment failure. These outliers can lead to erroneous parameter estimation and consequently affect the correctness and accuracy of the model inference. In order to solve these problems, three robust fuzzy neural networks (FNNs) will be proposed in this dissertation. This provides alternative learning machines when faced with general nonlinear learning problems. Our emphasis will be put particularly on the robustness of these learning machines against outliers. Though we consider only FNNs in this study, the extension of our approach to other neural networks, such as artificial neural networks and radial basis function networks, is straightforward. In the first part of the dissertation, M-estimators, where M stands for maximum likelihood, frequently used in robust regression for linear parametric regression problems will be generalized to nonparametric Maximum Likelihood Fuzzy Neural Networks (MFNNs) for nonlinear regression problems. Simple weight updating rules based on gradient descent and iteratively reweighted least squares (IRLS) will be derived. In the second part of the dissertation, least trimmed squares estimators, abbreviated as LTS-estimators, frequently used in robust (or resistant) regression for linear parametric regression problems will be generalized to nonparametric least trimmed squares fuzzy neural networks, abbreviated as LTS-FNNs, for nonlinear regression problems. Again, simple weight updating rules based on gradient descent and iteratively reweighted least squares (IRLS) algorithms will be provided. In the last part of the dissertation, by combining the easy interpretability of the parametric models and the flexibility of the nonparametric models, semiparametric fuzzy neural networks (semiparametric FNNs) and semiparametric Wilcoxon fuzzy neural networks (semiparametric WFNNs) will be proposed. The corresponding learning rules are based on the backfitting procedure which is frequently used in semiparametric regression.
Lee, Chia-Yuan y 李家源. "Multiple Compensatory Neural Fuzzy Networks Fusion Using Fuzzy Integral". Thesis, 2004. http://ndltd.ncl.edu.tw/handle/vrez32.
Texto completo朝陽科技大學
資訊工程系碩士班
92
This thesis presents a novel method for combining multiple compensatory neural fuzzy networks (CNFNs) using fuzzy integral. The fusion of multiple classifiers can overcome the limitations of a single classifier since the classifiers complemen each other. A fuzzy integral is a better combination scheme than majority voting method that uses the subjectively defined relevance of classifiers. A combination of multiple CNFN classifiers with fuzzy integral (FI) is proposed to achieve data classification with higher accurate than existing traditional methods. We first apply multiple CNFNs fusion using fuzzy integral based on compensatory degree to establish the classification model. The advantage of the proposed method is that not only are the classification results combined but the relative importance of the different networks is also considered. Experimental results show that the fusion of multiple CNFNs using fuzzy integral can perform better than existing traditional methods.
Xue, Kuo Qiang y 薛國強. "An intelligent sales forecasting system through artificial neural networks and fuzzy neural network". Thesis, 1996. http://ndltd.ncl.edu.tw/handle/07455980576654976365.
Texto completoTsai, Chiachih y 蔡嘉志. "Applications of Wireless Sensor Networks Based on Fuzzy Neural Network". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/18594029970285141084.
Texto completo國防大學理工學院
國防科學研究所
100
Due to immense potential applications, wireless sensor networks (WSNs) have attracted research interests in recent years, including remote environmental monitoring, data fusion, sensing (temperature, pressure, speed) and military applications. This dissertation applies the fuzzy logic and neural network technologies to a monitored area which deployed miniature wireless sensor nodes. With the advantages of inherent accuracy and simplicity, the fuzzy logic and neural network technologies manifests the effectiveness on the environmental monitoring and control applications of wireless sensor networks. First, we apply the fuzzy technology to control the air-conditioning strength and blade angle of a car conditioner to equalize the comfortable temperature in the front- and rear-seat areas. The wireless nodes equipped with temperature sensor are installed to gather temperature information and then transmit this information to the central control terminal which executes the fuzzy inference control logic. The experiments show that the fuzzy technology would greatly improve the response for the automotive control and smart computation in the wireless sensor network systems. And then we develop a novel fuzzy logic algorithm to the remote environmental monitoring applications. Through a simple and effective fuzzy logic algorithm, every interesting node in the monitored area can be effectively calculated. This novel algorithm manifests their simplicity and accuracy and its performance characterized by root mean square error is better than the one with the standard Mamadni fuzzy logic method. Our study focuses on two particular neural network models, back-propagation network (BPN) and general regression neural network (GRNN) for the temperature prediction in a monitored factory. The prediction accuracy of these two models is evaluated by practical monitored data. We found that the model based on GRNN can accelerate the learning speed and rapidly converge to the optimal regression surface with large number of data sets. With the simulation results, we can show that the model based on GRNN effectively improve the predictability of the one based on BPN. Finally, we combine the genetic algorithm (GA) and the radial basis function (RBF) neural network in study of event detection for factory monitoring. As we know, the center of RBF, the width of RBF and output weight of RBF have a great influence on the performance of RBF neural network. In this study, we apply genetic algorithm to determine these parameters to improve the performance of the event detection. The experiments indicate that the GA-RBF algorithm is better than the traditional BPN and RBF neural network algorithms in both speed and precise of convergence. In this work, we find a responsive and effective algorithm in the WSN applications by integrating fuzzy theory and neural network technology. The combination of fuzzy theory and neural network technology should be a powerful strategy for the various WSN applications.
陳俊維. "Fuzzy Neural Networks Based Adaptive Cruise Control". Thesis, 2002. http://ndltd.ncl.edu.tw/handle/01697651922759359482.
Texto completo國立交通大學
電機與控制工程系
90
Adaptive Cruise Control (ACC) System is an important part of the Advanced Vehicle Control and Safety System (AVCSS) in Intelligent Transportation Systems (ITS). In this thesis we design an ACC controller based on fuzzy neural networks for following a leading vehicle to achieve the desired safety distance, or cruising at the pre-selected speed. The transmission between the two maneuvers is carried out automatically. The advantage of using fuzzy neural networks is that it doesn’t require the complete knowledge of nonlinear vehicle dynamics, and it can be applied to any vehicle regardless of its nonlinear or unobservable dynamics. We separate the ACC controller into three parts. The first one is used to determine the desired acceleration according to the current traffic situation (relative speed and relative distance) and driver’s driving style, the second one is used to determine the throttle angle or braking command depending on the current vehicle speed and desired acceleration, and the last one is used to compensate the modeling error and disturbances. The performance of ACC controller is evaluated based on a complex traffic model, which includes the accurate nonlinear vehicle dynamic model and various environments, and simulated by a computer with MATLAB software. The vehicle is assumed to be equipped with sensors that can measure the relative distance and vehicle speed. In addition, we also take maximum allowable jerks and the system delay into account. The fuzzy logic and neural networks based controller proposed in this thesis provides a safe, convenient and comfortable driving assistance system. The controller can switch between car following and cruise control automatically.
Hong, Shing-Fu y 洪清富. "VLSI Design of Fuzzy Functional Neural Networks". Thesis, 1996. http://ndltd.ncl.edu.tw/handle/08531360158426516811.
Texto completoTien-Sheng, Tang y 唐天生. "Fuzzy modelling using self-organizing neural networks". Thesis, 1999. http://ndltd.ncl.edu.tw/handle/97218540581668054505.
Texto completo國立中央大學
機械工程研究所
87
A neural-network-based structure learning fuzzy system is proposed. The consequent of a rule is assumed to be a linear combination of two fuzzy sets associated with an output variable as against the traditional fuzzy rules whose consequents are decided by an experienced operator. The defuzzified result of these proposed fuzzy rules is proved to conform with the general meaning of a defuzzifier and is shown to be realizable through a neural network in which the coefficients associated with the linear combination are tuned from input-output pairs. To improve its performance further, we incorporate the proposed system with a self-organizing heuristic method (SOHM) to generate necessary fuzzy rules automatically. Lastly, the capability of this approach is demonstrated through examples.
JIAN, YUAN-ZHEN y 簡源震. "Adaptive fuzzy logic controller using neural networks". Thesis, 1992. http://ndltd.ncl.edu.tw/handle/67432838151022219149.
Texto completoGuo-Yin, Chen y 陳國寅. "On the Study of the Learning Performance for Neural Networks and Neural Fuzzy Networks". Thesis, 1998. http://ndltd.ncl.edu.tw/handle/07825885643934324498.
Texto completo國立臺灣科技大學
電機工程技術研究所
86
Neural networks and fuzzy systems can be used to estimate functions frominput-output data pairs and behave as associative memories. Since both approaches are model-free estimators, the resultant systems can be said to directly model the input-output relationship from the given training patterns without requiring other knowledge. As a matter of fact, those two approaches have been proven to be universal approximators under certain circumstances. It is more than often that such a universal property cannot be satisfied in the actual cases due to poor learning capability. In this research, instead in pursuit of approaches to improve the learning schemes, we were aimed at studying the general learning concept and the fundamental differences between those two universal approximators. In this thesis, three kinds of numerical learning systems are discussed. They are neural networks, neural fuzzy systems, and neural fuzzy systems with structure learning. Three systems are used in our study; they are the fuzzy car system, the sinc function approximation, and the terrain location identification system. Those systems represent different kinds of learning problems. The fuzzy car system is to learn from the training data that are very noisy and with non-deterministic input-output relationship. The sinc function system is to learn form an exactly know system, and therefore, the system errors and the added noise magnitude can be defined exactly to evaluate the learning performance of the employed learning mechanisms. The terrain location identification problem on the other hand represents a very complicated learning target. Beside of noisy and non-deterministic training data, the training task must learn from a very large size of training data, which may cause lots of learning problems. In our implementation of the terrain location identification system, several phenomena have been discovered. The first phenomenon is called the fake convergence in our research. In this thesis, a fuzzy hierarchical approach is proposed to resolve the problem. With this fuzzy hierarchical structure, the learning process can become fast and the training errors are also significantly reduced. Another issue in the terrain location identification problem is regarding about embedding domain knowledge into the learning structure of neural fuzzy networks. The domain knowledge is used in a neural fuzzy network in which the TSK fuzzy rule model is equipped. With such inclusion of knowledge, the learning performance is dramatically improved. Finally, with the structure of using domain knowledge, a new way of fusing data other than the traditional Kalman filter type of data fusion is proposed and discussed. Our results have also demonstrate the superiority of our approach to the traditional Kalman filter. In our study of neural fuzzy networks with structure learning, two approaches of tuning the parameters in the linear functions of the consequent part of fuzzy rules can be found in the literature. They are the traditional backpropagation algorithm (BP) and the recursive least square method (RLS). From our implementation, we may say that it is not always a good idea to use the RLS training to replace the BP training.
"Learning algorithms for neural networks with fuzzy information". Chinese University of Hong Kong, 1990. http://library.cuhk.edu.hk/record=b5895362.
Texto completoThesis (M.Phil.)--Chinese University of Hong Kong, 1990.
Bibliography: leaves [128]-[130]
Chapter CHAPTER 1 --- INTRODUCTION --- p.1-1
Chapter 1.1 --- Introduction to Artificial Neural Networks --- p.1-4
Chapter 1.1.1 --- Fundamentals of Artificial Neural Networks --- p.1-5
Chapter 1.1.2 --- Various Artificial Neural Network Models ´ؤA Review --- p.1-11
Chapter 1.2 --- Introduction to Fuzzy Sets Theory --- p.1-17
Chapter 1.2.1 --- "Fuzziness, Fuzzy sets and Membership Function" --- p.1-17
Chapter 1.2.2 --- Applications of Fuzzy Sets --- p.1-19
Connective Summary --- p.1-21
Chapter CHAPTER 2 --- LEARNING WITH FUZZY INFORMATION --- p.2-1
Chapter 2.1 --- "Decision Making, Pattern Associating and Pattern Classification" --- p.2-3
Chapter 2.2 --- Artificial Neural Networks as Learning Decision Systems --- p.2-6
Chapter 2.3 --- Fuzziness in Decision Making Processes --- p.2-10
Chapter 2.4 --- Learning with Fuzzy Information --- p.2-12
Chapter 2.5 --- The Formulation of Our Approach --- p.2-16
Connective Summary --- p.2-18
Chapter CHAPTER 3 --- A MODIFIED BACKPROPAGATION ALGORITHM FOR MULTILAYER FEEDFORWARD NETWORKS --- p.3-1
Chapter 3.1 --- Preliminaries --- p.3-3
Chapter 3.2 --- The Error Backpropagation Algorithm (EBPA) --- p.3-8
Chapter 3.3 --- A Modified EBPA Learning with A Priori Fuzzy Information --- p.3-11
Chapter 3.3.1 --- The Membership-Weighed Objective Function --- p.3-11
Chapter 3.3.2 --- The Fuzzy Error Backpropagation Algorithm --- p.3-13
Chapter 3.4 --- Discussion on the Proposed Fuzzy EBPA --- p.3-15
Chapter 3.4.1 --- Methods of Determining Membership Functions --- p.3-15
Chapter 3.4.2 --- Fuzzy EBPA Alters the Effective Target Patterns --- p.3-19
Chapter 3.4.3 --- Estimating the Learning Rates Required for the Fuzzy EBPA --- p.3-21
Connective Summary --- p.3-24
Chapter CHAPTER 4 --- APPLICATION EXAMPLES --- p.4-1
Chapter 4.1 --- A Single Node Classifier --- p.4-2
Chapter 4.2 --- The Fuzzy XOR Problem --- p.4-29
Chapter 4.2.1 --- Network Configuration 1 --- p.4-36
Chapter 4.2.2 --- Network Configuration 2 --- p.4-46
Chapter 4.2.3 --- Comments on the Simulation Results --- p.4-50
Chapter 4.3 --- A Speech Recognition System --- p.4-54
Connective Summary --- p.4-59
Chapter CHAPTER 5 --- DISCUSSION AND CONCLUSION --- p.5-1
Chuang, Cheng-Ta y 莊政達. "RFID Fault Diagnosis by Using Fuzzy Neural Networks". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/b8e4m8.
Texto completo靜宜大學
資訊管理學系研究所
97
In recent years, Radio Frequency IDentification system (RFID) is considered the one of top ten technical progresses of this century. And the value of RFID consists in its automation. Therefore, ensuring the reliability of RFID system is the most important task on its application. Traditionally, system maintenance is based on the artificial experience, but this approach depends on ample experience in maintenance. Therefore, if there is an automatic fault classified system, it will be greatly helpful to enhance the maintenance efficiency. RFID fault diagnosis belongs to a classification-related research, and neural networks are often used to solve the classification-related issues. In addition, the fuzzy theory gets beyond the traditional concept of “0 and 1”, and is used to analyze semantic strength and avoid semantic ambiguity. Therefore, this research attempts to combine the fuzzy theory and neural networks in RFID fault diagnosis to assist the maintenance staff eliminating the system fault efficiently. In this research, we propose an approach that combines a fuzzy neural network and an additional probability diagnostic method. The proposed two-stage model significantly reduces the input units and output units of neural network, and effectively controls the fuzzy neural network learning speed and precision. Most importantly, and the proposed approach makes RFID fault diagnosis more accuracy.
Li, Zhi Ren y 李志仁. "Fingerprint recognition using neural networks and fuzzy theory". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/87999273234260416206.
Texto completoLee, Ching-Hung y 李慶鴻. "Analysis of Fuzzy Neural Networks and Its Applications". Thesis, 2000. http://ndltd.ncl.edu.tw/handle/53710177302734251220.
Texto completo國立交通大學
電機與控制工程系
88
In this dissertation, we investigate a fuzzy neural network (FNN) system that combines the advantages of the fuzzy logic and neural network systems. The FNN system is a straight-forward implementation of fuzzy inference system with four layered network structure. This system combines the advantages of the fuzzy logic control and neural networks. Base on this FNN system, a recurrent structure of the FNN (RFNN) are proposed in this dissertation. The RFNN is inherently a recurrent multilayered connectionist network for realizing fuzzy inference using dynamic fuzzy rules. Temporal relations are embedded in the network by adding feedback connections in the second layer of the fuzzy neural network (FNN). Results for the FNN -fuzzy inference engine, universal approximation, and convergence analysis are extended to the RFNN. Moreover, the RFNN extends the basic ability of the FNN to cope with temporal problems. Subsequently, we discuss the relationship between membership and mapping accuracy of the FNN system. A new method to fine-tune the Gaussian membership functions of the FNN is proposed to improve the approximation accuracy which subverts the commonly used property of membership functions. For illustrating the effectiveness of our approach, several applications of the FNN are also presented, including the PID tuning method based on gain and phase margin specifications, identification and control of Hammerstein systems, and fuzzy rules Acknowledgement i Abstract in Chinese ii Abstract in English iv Contents v List of Figures vi List of Tables xi 1 Introduction 1 1.1 Introduction and Motivation.......................... 1 1.2 Research objectives..............................2 1.3 Overview..................................3 1.3.1 Organization of this dissertation ...................... 3 1.3.2 Overview................................3 2 Fuzzy Neural Network 6 2.1 Outlines.................................. 6 2.2 Structure of the fuzzy neural network.......................8 2.3 Reasoning method.............................. 8 2.4 Basic nodes operation.............................10 2.5 Supervised learning..............................13 2.6 Universal approximation............................15 3 Fine Tuning of Membership Functions 17 3.1 Introduction.................................17 3.2 Fine tuning of membership functions....................... 19 3.2.1 Gaussian function series..........................19 3.2.2 Fine tuning method............................21 3.2.3 Tuning the FNN5............................. 22 3.2.4 Convergence analysis........................... 23 3.2.5 Normalization of membership functions.................... 24 3.3 Simulation results.............................. 26 4 Applications of the FNN systems 4.1 Tuning of PID controllers with specifications on gain and phase margins ......29 4.1.1 Introduction 4.1.2 Gain margin and phase margin 4.1.3 Tuning method using the FNN 4.1.4 Selection of training data and specification 4.1.5 Simulation results 4.2 Identification and Control of Hammerstein systems 4.2.1 Introduction 4.2.2 Hammerstein system 4.2.3 Identification model 4.2.4 Control design method 4.2.5 Convergence analysis 4.2.6 Simulation results 4.3 Fuzzy rules reduction 4.3.1 Introduction 4.3.2 Methods for reducing fuzzu rules 4.3.3 simulation result 2.6 Universal approximation............................15 5 Recurrent Fuzzy Neural Network 54 53.1 Introduction.................................54 5.2 Recurrent fuzzy neural networks: RFNN..................... 56 5.2.1 Structure of the RFNN...........................56 5.2.2 Layered operation ............................56 5.2.3 Fuzzy reasoning............................. 59 5.3 Training architecture............................. 61 5.3.1 Training architectures for identification and control............... 61 5.3.2 Learning algorithm............................63 5.4 Stability analysis .............................. 65 5.4.1 Stability analysis for identification......................66 5.4.2 Stability analysis for indirect control..................... 68 5.5 Simulation results.............................. 71 6 Conclusion and Future research 6.1 Conclusion 6.2 Future researches
Chung, I.-Fang y 鐘翊方. "Reinforcement Neural Fuzzy Inference Networks and Its Applications". Thesis, 2000. http://ndltd.ncl.edu.tw/handle/63962267050305328281.
Texto completo國立交通大學
電機與控制工程系
88
In this thesis, aiming at the problem of reinforcement learning, we propose the structure and associated learning algorithm of a neural fuzzy inference network for realizing the basic elements and functions of a traditional fuzzy logic controller. However, before we discuss the problem of reinforcement learning, we must construct a proper neural fuzzy inference network previously. Hence, at the beginning, we propose a basic five-layered connectionist network which could easily integrate the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure. If expert knowledge (or fuzzy rules) is provided from the outside world, here we could easily integrate expert knowledge into a network structure. Additionally, we derive the parameter learning method according to the network structure and backpropagation learning scheme. The derived parameter learning method can be further used to adjust the network parameters for obtaining the best performance. In addition, based upon the structure of the original five-layered connectionist network, we further propose a Fuzzy Adaptive Learning COntrol Network (FALCON). FALCON uses an on-line two-step learning algorithm, called FALCON-ART, for constructing the network structure dynamically. Compared with the original five-layered connectionist network, FALCON uses the fuzzy ART algorithm for structure learning in addition to the backpropagation learning scheme for parameter learning. The FALCON-ART can partition the input/output spaces on-line, tune membership functions and find proper fuzzy logic rules. All things are done automatically and dynamically. More notably, in this learning method, only the training data need to be provided from the outside world. That is, the users need not give the initial fuzzy partitions, membership functions and fuzzy logic rules. Hence, there is no input/output term nodes and no rule nodes in the beginning of learning. The FALCON-ART partitions the pattern space into irregular hyperboxes and thus can avoid the problem of combinatorial growing of partitioned grids in some complex systems. When the development of the structure and associated learning algorithm of a neural fuzzy inference network is finished, we extend the above network structure to the area of reinforcement learning: (1) We bring the genetic algorithms (GAs) into the structure learning of FALCON. GAs belong to a kind of search algorithms. Since GAs do not require or use derivative information, the most appropriate applications are problems where gradient information is unavailable or costly to obtain. Reinforcement learning is just one example of such a domain. Therefore, we can regard GAs as a kind of reinforcement learning. In addition, due to its global optimization capability, GAs have become another useful tool to the automatic design of fuzzy control systems. Here an improved structure/parameter learning algorithm, called FALCON-GA, is proposed for constructing the FALCON automatically. The FALCON-GA is a three-phase hybrid learning algorithm. Except for using GAs to find proper fuzzy logic rules, its learning algorithms, for partitioning input/output spaces and tuning membership functions, are the same as FALCON. By comparing the simulated results, we find that the performance of FALCON-GA is better than that of FALCON. (2) We propose a reinforcement Neuro-Fuzzy Combiner (NFC) for multiobjective control. Here the key component of NFC could be still FALCON. However, for solving the problems of complex multiobjective control and no instructive teaching information available, we add the concepts of the hierarchical control and the reinforcement learning into NFC structure. In more detail, the structure of the multiobjective control system is composed of the NFC and n existing low-level controllers. It is assumed that each low-level (fuzzy or nonfuzzy) controller has been well designed to serve a particular objective. The role of the NFC is to fuse the $n$ actions decided by the n low-level controllers and determine a proper action through reinforcement learning method to act on the environment (plant) at each time step. Hence, the NFC can combine low-level controllers and achieve multiple objectives (goals) at once. Capabilities and performances of the proposed reinforcement neural fuzzy inference network have been verified and compared through various computer simulations. We have used FALCON-GA in solving the problems of the chaotic time-series prediction and the control of the truck backer-upper. In the application of multiobjective control, we have also realized in a cart-pole balancing system and a crane system. Capabilities and performances of the proposed methods are all verified from these applications. Abstract in English Chapter 1: Introduction Chapter 2: A Basic Five-layered Neural Fuzzy Inference Network Chapter 3: A Fuzzy Adaptive Learning Control Network Chapter 4: A GA-Based Fuzzy Adaptive Learning Control Network Chapter 5: A Reinforcement Neuro-Fuzzy Combiner for Multiobjective Control Chapter 6: Conclusion
Yen, Chung-fu y 顏仲甫. "Defect Inspection Using Recurrent Fuzzy Cellular Neural Networks". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/49855127745617849325.
Texto completo國立成功大學
電機工程學系碩博士班
95
The use of human vision for defect inspection from product images is limited to a certain quality level. In electronics industrial production lines, it is important to inspect the products for defects. It is feasible to check for product defects in the production lines by artificial means. Therefore, there is a need to develop methods using computer intelligence to replace manpower for product defect identification. We propose a framework to integrate a set of CNNs in parallel for solving defect identification as image processing problems. Our framework was modified from a generic recurrent fuzzy cellular neural network (RFCNN) that consists of a set of fuzzy IF–THEN rules. We employ a k-means algorithm for constructing the antecedent and consequent parts in the structure learning. To obtain the parameters of CNN templates, we derive a recurrent parameter learning algorithm based on ordered derivatives. We name our network modified RFCNN, mRFCNN. To validate the effectiveness of the proposed mRFCNN, we experiment different types of defects and compare our approach with a conventional defect inspection method, wherein CNN templates are trained by genetic algorithms (GACNN). The results of the experiments conclude that mRFCNN, compared to GACNN, has superior performance on more difficult image processing tasks.
Lau, Chuang-Yeong y 劉全勇. "An Automatic Melody Generation Using Fuzzy Neural Networks". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/68017460390309814549.
Texto completo國立中央大學
通訊工程研究所
100
The generated music from automatic music composition is not completely match the rule of music theory in the past research. This thesis proposed using fuzzy neural network (FNN) to training a repeating pattern melody which called refrain in pop music. A refrain usually repeats many times in the music objects. The proposed learning algorithm is based on fuzzy back propagation algorithm (FBP). The main goal of a fuzzy inference system is to model composer decision making within conceptual as the process of composing music. The music theory knowledge of consonance intervals and key signature were adopted to check and adjust the output melody to prevent incorrectly. The simulation results show that the proposed learning algorithm have a good learning ability and well performance.
Lee, Hsin-Wei y 李芯瑋. "MVC-Architecture Based Fuzzy-Neural-Networks Cloud-Computing". Thesis, 2014. http://ndltd.ncl.edu.tw/handle/43793583221700537836.
Texto completo國立暨南國際大學
電機工程學系
102
Fuzzy Neural Network (FNN) is the most popular artificial intelligence research and is widely used in speech recognition, image processing, intelligent robotics, machine learning and data mining, etc. FNN combines the capability of fuzzy systems and artificial neural networks. The characteristic of fuzzy systems can mimic the vague information of the human brain and still make the right judgments. The most suitable FNN structure automatically adjusts after several iterations by the self-learning ability of artificial neural network. FNN has self-learning ability and fuzzy inference advantages, many researchers use fuzzy neural network to solve classification problems. Thus, a service platform-FNN online which combines fuzzy neural network and cloud computing is presented in this thesis. FNN online provides instant online training, so that users can take advantage of fuzzy neural network to solve classification problems. The FNN online is built using the model (Model), View (View) and Controller (Controller), collectively known as the MVC design pattern. The concept of MVC is simple. Its development process in the software clearly defines the roles and high maintainability of the application. In the future works, we hope to join a variety of algorithms to allow the user to select the fitness one or management of membership function to provide a more complete service.
Aghakhani, Sara. "Neuro-fuzzy architecture based on complex fuzzy logic". 2010. http://hdl.handle.net/10048/891.
Texto completoTitle from PDF file main screen (viewed on May 7, 2010). A thesis submitted to the Faculty of Graduate Studies and Research in partial fulfillment of the requirements for the degree of Master of Science in Software Engineering and Intelligent Systems, Department of Electrical and Computer Engineering, University of Alberta. Includes bibliographical references.
Lin, Jui-Wen y 林瑞文. "The Prediction of Crude Oil Futures Prices - Comparison aming Backpropagation Neural Networks,Elman Recurrent Neural Networks and Recurrent Fuzzy Neural Networks". Thesis, 2005. http://ndltd.ncl.edu.tw/handle/17140925737594266130.
Texto completo中原大學
企業管理研究所
94
During the past three years, oil price has changed dramatically and terrorists’ attacks caused the turbulent uneasiness of the global economy. Consequently, governments and corporate managers around the world actively sought effective methods to forecast the oil price more accurately than before for the purposes of hedging and arbitraging. The purpose of this study is to predict the crude oil futures prices more accurately than traditional methods by using three popular non-parametric methods, namely, Backpropagation Neutral Networks (BPNs), Elman Recurrent Neural Networks (ERNNs), and Recurrent Fuzzy Neral Networks (RFNNs). This work also compares the learning and predictive performance among BPNs, ERNNs and RFNNs, and explores how training time impacts predictive accuracy. The results show that the use of these three non-parametric methods to forecast the crude oil futures prices was appropriate since their values of MSE were all less than 0.0026767. Additionally, the learning ability was consistent by employing different training times. This investigation also indicates that the more training times the networks took, the better learning performance the networks have under most circumstances, the only exceptional case occurs at part two under FRNN model, where MSE is slightly less than that obtained from part three. Regarding the predictive power of the three artificial neural networks (ANNs), this study finds that RFNNs has the best predictive power and BPN has the least predictive power among the three ANNs. This investigation also confirms that the predictive power can be enhanced by combining Fuzzy theory with the Recurrent Neural Network.
Huang, Yu-Jie y 黃煜傑. "Multivariate High-Order Weighted Fuzzy Time Series Based on Fuzzy Neural Networks". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/33520562389555656153.
Texto completo朝陽科技大學
資訊管理系碩士班
100
There are many uncertainty problems in the Human society, such as the forecasting of economic growth rate, financial crisis, etc. Since Song and Chissom proposed the concept of fuzzy time series in 1993, many scholars have proposed different models to deal with these problems. However, previous studies usually do not consider the factor selection and transfer original data to the fuzzy linguistic value by the subjective opinions in fuzzy process, which cannot objectively show the characteristics of the data. In addition, the fuzzy rules usually assign equal weight in the forecasting process, and it failed to consider the importance of each fuzzy rule. Based on above concepts, this study adopt the self-organizing map network (SOM) for the purpose of factor selection and proposed a multivariate high-order weighted fuzzy time series model based on fuzzy neural network (Fuzzy-BPN) and ordered weighted averaging operator (OWA) to make forecasts. In order to verify the proposed method, the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) from the Taiwan Stock Exchange Corporation are used in the experiment and filter the appropriate factors, and the experiment results are compared with other methods in with this study. The forecasting performance shows that the proposed method has better forecasting ability.
"On the Synthesis of fuzzy neural systems". Chinese University of Hong Kong, 1995. http://library.cuhk.edu.hk/record=b5888338.
Texto completoThesis (Ph.D.)--Chinese University of Hong Kong, 1995.
Includes bibliographical references (leaves 166-174).
ACKNOWLEDGEMENT --- p.iii
ABSTRACT --- p.iv
Chapter 1. --- Introduction --- p.1
Chapter 1.1 --- Integration of Fuzzy Systems and Neural Networks --- p.1
Chapter 1.2 --- Objectives of the Research --- p.7
Chapter 1.2.1 --- Fuzzification of Competitive Learning Algorithms --- p.7
Chapter 1.2.2 --- Capacity Analysis of FAM and FRNS Models --- p.8
Chapter 1.2.3 --- Structure and Parameter Identifications of FRNS --- p.9
Chapter 1.3 --- Outline of the Thesis --- p.9
Chapter 2. --- A Fuzzy System Primer --- p.11
Chapter 2.1 --- Basic Concepts of Fuzzy Sets --- p.11
Chapter 2.2 --- Fuzzy Set-Theoretic Operators --- p.15
Chapter 2.3 --- "Linguistic Variable, Fuzzy Rule and Fuzzy Inference" --- p.19
Chapter 2.4 --- Basic Structure of a Fuzzy System --- p.22
Chapter 2.4.1 --- Fuzzifier --- p.22
Chapter 2.4.2 --- Fuzzy Knowledge Base --- p.23
Chapter 2.4.3 --- Fuzzy Inference Engine --- p.24
Chapter 2.4.4 --- Defuzzifier --- p.28
Chapter 2.5 --- Concluding Remarks --- p.29
Chapter 3. --- Categories of Fuzzy Neural Systems --- p.30
Chapter 3.1 --- Introduction --- p.30
Chapter 3.2 --- Fuzzification of Neural Networks --- p.31
Chapter 3.2.1 --- Fuzzy Membership Driven Models --- p.32
Chapter 3.2.2 --- Fuzzy Operator Driven Models --- p.34
Chapter 3.2.3 --- Fuzzy Arithmetic Driven Models --- p.35
Chapter 3.3 --- Layered Network Implementation of Fuzzy Systems --- p.36
Chapter 3.3.1 --- Mamdani's Fuzzy Systems --- p.36
Chapter 3.3.2 --- Takagi and Sugeno's Fuzzy Systems --- p.37
Chapter 3.3.3 --- Fuzzy Relation Based Fuzzy Systems --- p.38
Chapter 3.4 --- Concluding Remarks --- p.40
Chapter 4. --- Fuzzification of Competitive Learning Networks --- p.42
Chapter 4.1 --- Introduction --- p.42
Chapter 4.2 --- Crisp Competitive Learning --- p.44
Chapter 4.2.1 --- Unsupervised Competitive Learning Algorithm --- p.46
Chapter 4.2.2 --- Learning Vector Quantization Algorithm --- p.48
Chapter 4.2.3 --- Frequency Sensitive Competitive Learning Algorithm --- p.50
Chapter 4.3 --- Fuzzy Competitive Learning --- p.50
Chapter 4.3.1 --- Unsupervised Fuzzy Competitive Learning Algorithm --- p.53
Chapter 4.3.2 --- Fuzzy Learning Vector Quantization Algorithm --- p.54
Chapter 4.3.3 --- Fuzzy Frequency Sensitive Competitive Learning Algorithm --- p.58
Chapter 4.4 --- Stability of Fuzzy Competitive Learning --- p.58
Chapter 4.5 --- Controlling the Fuzziness of Fuzzy Competitive Learning --- p.60
Chapter 4.6 --- Interpretations of Fuzzy Competitive Learning Networks --- p.61
Chapter 4.7 --- Simulation Results --- p.64
Chapter 4.7.1 --- Performance of Fuzzy Competitive Learning Algorithms --- p.64
Chapter 4.7.2 --- Performance of Monotonically Decreasing Fuzziness Control Scheme --- p.74
Chapter 4.7.3 --- Interpretation of Trained Networks --- p.76
Chapter 4.8 --- Concluding Remarks --- p.80
Chapter 5. --- Capacity Analysis of Fuzzy Associative Memories --- p.82
Chapter 5.1 --- Introduction --- p.82
Chapter 5.2 --- Fuzzy Associative Memories (FAMs) --- p.83
Chapter 5.3 --- Storing Multiple Rules in FAMs --- p.87
Chapter 5.4 --- A High Capacity Encoding Scheme for FAMs --- p.90
Chapter 5.5 --- Memory Capacity --- p.91
Chapter 5.6 --- Rule Modification --- p.93
Chapter 5.7 --- Inference Performance --- p.99
Chapter 5.8 --- Concluding Remarks --- p.104
Chapter 6. --- Capacity Analysis of Fuzzy Relational Neural Systems --- p.105
Chapter 6.1 --- Introduction --- p.105
Chapter 6.2 --- Fuzzy Relational Equations and Fuzzy Relational Neural Systems --- p.107
Chapter 6.3 --- Solving a System of Fuzzy Relational Equations --- p.109
Chapter 6.4 --- New Solvable Conditions --- p.112
Chapter 6.4.1 --- Max-t Fuzzy Relational Equations --- p.112
Chapter 6.4.2 --- Min-s Fuzzy Relational Equations --- p.117
Chapter 6.5 --- Approximate Resolution --- p.119
Chapter 6.6 --- System Capacity --- p.123
Chapter 6.7 --- Inference Performance --- p.125
Chapter 6.8 --- Concluding Remarks --- p.127
Chapter 7. --- Structure and Parameter Identifications of Fuzzy Relational Neural Systems --- p.129
Chapter 7.1 --- Introduction --- p.129
Chapter 7.2 --- Modelling Nonlinear Dynamic Systems by Fuzzy Relational Equations --- p.131
Chapter 7.3 --- A General FRNS Identification Algorithm --- p.138
Chapter 7.4 --- An Evolutionary Computation Approach to Structure and Parameter Identifications --- p.139
Chapter 7.4.1 --- Guided Evolutionary Simulated Annealing --- p.140
Chapter 7.4.2 --- An Evolutionary Identification (EVIDENT) Algorithm --- p.143
Chapter 7.5 --- Simulation Results --- p.146
Chapter 7.6 --- Concluding Remarks --- p.158
Chapter 8. --- Conclusions --- p.159
Chapter 8.1 --- Summary of Contributions --- p.160
Chapter 8.1.1 --- Fuzzy Competitive Learning --- p.160
Chapter 8.1.2 --- Capacity Analysis of FAM and FRNS --- p.160
Chapter 8.1.3 --- Numerical Identification of FRNS --- p.161
Chapter 8.2 --- Further Investigations --- p.162
Appendix A Publication List of the Candidate --- p.164
BIBLIOGRAPHY --- p.166