A neuro-fuzzy system is the combined the advance feature of fuzzy logic and neural network, it is simply a fuzzy inference system that is trained by the learning concept of neural network. In NFS learning mechanism fine-tunes the underlying fuzzy inference system. This paper presents fundamental concepts and parameterized comparison in the aspects of fuzzy logic, neural network and neuro-fuzzy ...

In order to overcome weaknesses of the conventional crisp neural network and the fuzzy-operation-oriented neural network, we have developed a general fuzzy-reasoning-oriented fuzzy neural network called a Crisp-Fuzzy Neural Network (CFNN) which is capable of extracting high-level knowledge such as fuzzy IF-THEN rules from either crisp data or fuzzy data. A CFNN can eeectively compress a 5 5 fuz...

Several adaptation techniques have been investigated to optimize fuzzy inference systems. Neural network learning algorithms have been used to determine the parameters of fuzzy inference system. Such models are often called as integrated neuro-fuzzy models. In an integrated neuro-fuzzy model there is no guarantee that the neural network learning algorithm converges and the tuning of fuzzy infer...

Fire alarm system is important in high-rise building. In this paper, a fire alarm system of high-rise building is designed using fuzzy system theory and neural network. The fuzzy system has superiority in inference and the neural network has superiority in learning. The design parameters of the fuzzy system can be adjusted automatically by combining the fuzzy system with the neural network. The...

This paper considers the identification and fuzzy controller design for nonlinear uncertain systems in presence of unknown input time-delay. Firstly, a time-delay Takagi-Sugeno-Kang (TSK) type fuzzy neural system (TDFN) is proposed to identify a class of nonlinear input time-delay systems. The input-output signals of nonlinear systems are used to identify the system dynamics and unknown time-de...

K e y w o r d s C o m p e n s a t o r y , Fuzzy similarity measure, Inverted wedge system, Backpropagation algorithm. 1. I N T R O D U C T I O N Recently, the neural fuzzy approach to system modeling has become a popular research topic [110]. Moreover, the neural fuzzy method possesses the advantages of both the pure neural and the fuzzy methods; it brings the low-level learning and computation...

One benefit of fuzzy systems (Zadeh, 1965; Ruspini et al., 1998; Cox, 1994) is that the rule base can be created from expert knowledge, used to specify fuzzy sets to partition all variables and a sufficient number of fuzzy rules to describe the input/output relation of the problem at hand. However, a fuzzy system that is constructed by expert knowledge alone will usually not perform as required...

A method to extract a fuzzy rule based system from a trained artificial neural network for classification is presented. The fuzzy system obtained is equivalent to the corresponding neural network. In the antecedents of the fuzzy rules, it uses the similarity between the input datum and the weight vectors. This implies rules highly understandable. Thus, both the fuzzy system and a simple analysi...

By combining the fuzzy theory and neural network technology, a fuzzy neural network (FNN) is proposed in this paper, whose learning algorithms are developed by steep algorithm. The excitation system model based on FNN is also derived in this paper, which can be used for on-line and off-line analysis and control respectively. The simulation results demonstrate that the FNN models can give precis...