-Fuzzy ARTMAP is one of the recently proposed neural network paradigm where the fuzzy logic is incorporated. In this paper, we compare the Fuzzy ARTMAP neural network and the well-known back-propagation based Multi-layer perceptron (MLP), in the context of hand-written character recognition problem. The results presented in this paper shows that the Fuzzy ARTMAP out-performs its counterpart, bo...

This paper discusses the design of neural network and fuzzy logic controllers using genetic algorithms, for real-time control of flows in sewerage networks. The soft controllers operate in a critical control range, with a simple set-point strategy governing "easy" cases. The genetic algorithm designs controllers and set-points by repeated application of a simulator. A comparison between neural ...

Received 20 April 2010; revised 14 August 2010; accepted 29 August 2010. ———————————————————————————————Abstract In this paper, we present a numerical method for solving fully fuzzy polynomials. The proposed method is based on approximating fuzzy neural network. This method can also lead to improving numerical methods. In this work, an architecture of fuzzy neural networks is also proposed to f...

A neural network can approximate a function, but it is impossible to interpret the result in terms of natural language. The consolidation of neural networks and fuzzy logic in neurofuzzy models provides learning as well as readability. This paper aims at modeling the input-output relationship with fuzzy IF-THEN rules by using fuzzy clustering technique. The main difference between fuzzy cluster...

Most of the recent research in the design of fuzzy controllers has been centered on automatic techniques using expert’s input-output data. The majority of these techniques rely on the use of Takagi-Sugeno type controllers and fuzzy-neural-network [3-5,11], fuzzy clustering and fuzzy partition approaches [1,2,6,7]. These controllers, however, are not fully-linguistic and the use of neural-networ...

Fuzzy relations as representational tools and fuzzy compositional operators as reasoning components, are user in this paper in order to represent knowledge expressed in semantic rules. Furthermore, neural representation and resolution of composite fuzzy relation equations provides knowledge refinement and adaptation to a specific context. A two-layer fuzzy compositional neural network is propos...

Function Points is an important and well-accepted software size metric. However, it is absolutely essential to accurately calibrate Function Point (FP), whose aims are to fit specific software application, to reflect software industry trend, and to improve cost estimation. Neuro-Fuzzy is a technique that incorporates the learning ability from neural network and the ability to capture human know...

This paper addresses the fault detection of a cracked cantilever beam using a hybrid artificial intelligence technique. The hybrid technique used here uses a fuzzy-neuro controller. The fuzzy-neuro controller has two parts. The first part is comprised of the fuzzy controller, and the second part is comprised of the neural controller. The input parameters of the fuzzy controller are relative dev...

This paper presents a novel learning algorithm of fuzzy perceptron neural networks (FPNNs) for classifiers that utilize expert knowledge represented by fuzzy IF-THEN rules as well as numerical data as inputs. The conventional linear perceptron network is extended to a second-order one, which is much more flexible for defining a discriminant function. In order to handle fuzzy numbers in neural n...

The dynamics of the Autonomous Underwater Vehicles (AUVs) are highly nonlinear and time varying and the hydrodynamic coefficients of vehicles are difficult to estimate accurately because of the variations of these coefficients with different navigation conditions and external disturbances. This study presents the on-line system identification of AUV dynamics to obtain the coupled nonlinear dyna...