• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.419-425
• /
• 2001

A method to detect lots of porno documents on the internet is presented in this parer. The proposed method applies fuzzy inference mechanism to the conventional information retrieval techniques. First, several example sites on porno arc provided by users and then candidate words representing for porno documents are extracted from theme documents. In this process, lexical analysis and stemming are performed. Then, several values such as tole term frequency(TF), the document frequency(DF), and the Heuristic Information(HI) Is computed for each candidate word. Finally, fuzzy inference is performed with the above three values to weight candidate words. The weights of candidate words arc used to determine whether a liven site is sexual or not. From experiments on small test collection, the proposed method was shown useful to detect the sexual sites automatically.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.541-543
• /
• 1998

Generally, PI control is simple and easy to implement and gains of PI control are determined by specifying a dynamics of the servo driver system. However, the gain-tuning is so difficult that it is relied on an expert's effort. This paper presents a gain auto-tuning method for PI controllers based on a fuzzy inference mechanism. First, the proposed fuzzy inference system identifies a system moment of inertia and adjusts control gains by using the difference in speed responses between a real plant and a reference model. Second, this paper proposes an improved fuzzy PI controller. To reduce the speed overshoot, we adapt a control method that selects a proper PI gains with respect to the load inertia variation. To prove the validity of the proposed gain tuning algorithm and the feasibility of the servo drive, a high performance servo drive will be implemented by DSP(TMS320C31) and intelligent power module (IPM). The proposed controller is applied to the speed control of the 300W AC servo motor. Some simulations and experimental results show that the proposed fuzzy PI controller is more robust than the conventional PI controller against the load inertia variation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.2 no.2
• /
• pp.3-33
• /
• 1992

The successful application of fuzzy reasoning models to fuzzy control systems depends on a number of parameters, such as fuzzy membership functions, that are usually decided upon subjectively. It is shown ill this paper that the performance of fuzzy control systems call be improved if the fuzzy reasoning model is supplemented by a genetic-based learning mechanism. The genetic algorithm enables us to generate all optimal set of parameters for the fuzzy reasoning model based either on their initial subjective selection or on a random selection. It is shown that if knowledge of the domain is available, it is exploited by the genetic algorithm leading to an even better performance of the fuzzy controller.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.849-855
• /
• 2008

The Diagnostic Unit of CLINAID can infer working diagnoses for general diseases from the information provided by a user. This user-provided information in the form of signs and symptoms, however, is usually not sufficient to make a final decision on a working diagnosis. In order for the Diagnostic Unit to reach a diagnostic conclusion, it needs to select suitable clinical investigations for the patients. Because different investigations can be selected for the same patient, we need a process that can optimize the selection procedure employed by the Diagnostic Unit. This process, called a selection algorithm, must work with the fuzzy relational method because CLINAID uses fuzzy relational structures extensively for its knowledge bases and inference mechanism. In this paper we present steps of the selection algorithm along with simulation results on this algorithm using fuzzy relational products, both harsh product and mean product. The computation results of applying several different fuzzy implication operators are compared and analyzed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.359-362
• /
• 1996

Our unicycle robot has simple mechanical structure. But unicycle's dynamical system is a very sensitive unstable system. Equation of motion of this simple unicycle robot was derived using Lagrange's method. In this paper a human inference control mechanism was established throughout an inquiry into hyman riding a unicycle, and we developed a hybrid controller to control our unicycle robot. Our controller is consisted with the PD and fuzzy controller containing fuzzy gain scheduling technique. Computer simulation shows good results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.929-932
• /
• 1993

A fuzzy microcontroller is presented implementing a simplified inference mechanism. Fuzzification, rule composition and defuzzification are carried out by means of (basically) analog current-mode CMOS circuits operating in strong inversion. Also a voltage interface is provided with the external world. Combining analog and digital techniques allow a programming capability.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.6
• /
• pp.152-160
• /
• 1996

This paper focuses on development and evaluation of a performance management algorithm for IEEE 802.4 token bus networks to serve large-scale integrated manufacturing systems. Such factory automation networks have to satisfy delay constraints imposed on time-critical messages while maintaining as much network capacity as possible for non-time-critical messages. This paper presents a network performance manager that adjusts queue capacity as well as timers by using a set of fuzzy rules and fuzzy inference mechanism. The efficacy of the performance management has been demonstrated by a series of simulation experiments.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1626-1629
• /
• 2002

This paper describes novel methods to construct fuzzy inference rules with gradient descent. The present methods have a constructive mechanism of the rule unit that is applicable in two parameters: the central value and the width of the membership function in the antecedent part. The first approach is to create the rule unit at the nearest position from the input space, for the central value of the membership function in the antecedent part. The second is to create the rule unit which has the minimum width, for the width of the membership function in the antecedent part. Experimental results are presented in order to show that the proposed methods are effective in difference on the inference error and the number of learning iterations.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.761-765
• /
• 1997

Our study of rider's postulator stability and tracking control on a unicycle began form the observation of a human riding. The system including unicycle and human operationg his unicycle is a fuzzy intelligent biomechanical model on basis of instinct and intuition search mechanisms. We proposed a robotic unicycle with one wheel and one body as a basic mode and derived equation of motion to this model. Our works is in making out fuzzy look-up table to control robotic unicycle. Fuzzy look-up table were determined for staight line and curve under reasonable inference emulating human's instinct and intuition riding a unicyale. Simulation results show that postulator stability and tracking control on both straight line and curve were successful by using proposed each fuzzy look-up table.