• 대한산업공학회지
• /
• 제26권4호
• /
• pp.306-314
• /
• 2000

In this paper we present a new approach to estimate link travel speed based on the hybrid neuro-fuzzy network. It combines the fuzzy ART algorithm for structure learning and the backpropagation algorithm for parameter adaptation. At first, the fuzzy ART algorithm partitions the input/output space using the training data set in order to construct initial neuro-fuzzy inference network. After the initial network topology is completed, a backpropagation learning scheme is applied to optimize parameters of fuzzy membership functions. An initial neuro-fuzzy network can be applicable to any other link where the probe car data are available. This can be realized by the network adaptation and add/modify module. In the network adaptation module, a CBR(Case-Based Reasoning) approach is used. Various experiments show that proposed methodology has better performance for estimating link travel speed comparing to the existing method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.505-507
• /
• 1998

In this paper, a simple hierarchical fuzzy inference system using structured Takagi-Sugeno type fuzzy inference units(SFIUs) is proposed. The number of fuzzy rules of the proposed HFIS is minimum in the sense of that only the number of partitions of each system variables, not of intermediate outputs of layered fuzzy controllers, are concerned. And resulted number of fuzzy rules is a summation of partition in each system variables. Gradient descent algorithm is used for adaptation of fuzzy rules. The ball and beam control is performed in computer simulation to illustrate the performance of the proposed controller.

• 한국정밀공학회지
• /
• 제14권4호
• /
• pp.110-118
• /
• 1997

Multi-layer neural networks with error back-propagation algorithm have a great potential for identifying nonlinear systems with unknown characteristics. However, because they have a demerit that the speed of convergence is too slow, various methods for improving the training characteristics of backpropagition networks have been proposed. In this paper, a fuzzy division method is proposed to improve the convergence speed, which can find out an effective fuzzy division by the tuning of membership function and independently train each neural network after dividing the network model into several parts. In the simulations, the proposed method showed that the optimal fuzzy partitions could be found from the arbitray initial ones and that the convergence speed was faster than the traditional method without the fuzzy division.

• 한국시뮬레이션학회논문지
• /
• 제16권4호
• /
• pp.57-65
• /
• 2007

많은 센서 네트워크 응용에서, 센서 노드들은 개방된 환경에 배포되므로 노드의 암호 키 완전히 훼손하는 물리 공격에 취약하다. 위조 감지 보고서는 훼손된 노드를 통하여 네트워크에 주입될 수 있으며, 이는 거짓 경보를 울릴 수 있을 뿐만 아니라 전지로 동작하는 네트워크의 제한된 에너지 자원을 고갈시킬 수 있다. Fan Ye 등은 이에 대한 대안으로 전송과정에서 허위 보고서를 검증할 수 있는 통계적 여과 기법을 제안하였다. 이 기법에서 허위 보고서에 대한 검증이 가능한 인증키의 노출 정도인 훼손 허용도를 나타내는 분할 값은 전역 키 풀이 나눠진 구획들의 수로 소비 에너지와 서로 대치되는 관계에 있어 그 결정이 매우 중요하다. 전체 구획들의 인증키가 노출될 경우 허위 보고서를 더 이상 검증을 할 수 없고 각 구획들의 노출되지 않은 나머지 인증키들은 인증키로써의 기능도 잃게 된다. 본 논문에서는 전역 키 풀 분할에 퍼지 규칙 시스템을 사용해 다수의 구획들로 나누는 퍼지 기반의 적응형 분할 기법을 제안한다. 퍼지 로직은 훼손된 구획의 수, 노드의 밀도와 잔여 에너지양을 고려하여 분할 값을 결정한다. 이 퍼지 기반의 분할 값은 충분한 훼손 허용도를 제공하면서 에너지를 보존할 수 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.609-617
• /
• 2006

A new fuzzy c-regression algorithm for switching regression analysis is presented, which combines fuzzy c-means clustering and least squares support vector machine. This algorithm can detect outliers in switching regression models while yielding the simultaneous estimates of the associated parameters together with a fuzzy c-partitions of data. It can be employed for the model-free nonlinear regression which does not assume the underlying form of the regression function. We illustrate the new approach with some numerical examples that show how it can be used to fit switching regression models to almost all types of mixed data.

• 전자공학회논문지S
• /
• 제35S권4호
• /
• pp.58-66
• /
• 1998

In many situations, it is very important to identify a certain unkown system, it from its input-output data. For this purpose, several system modeling algorithms have been suggested heretofore, and studies regarding the fuzzy modeling based on its nonlinearity get underway as well. Generatlly, fuzzy models have the capability of dividing input space into several subspaces, compared to linear ones. But hitherto subggested fuzzy modeling algorithms do not take into consideration the correlations between components of sample input data and address them independently of each other, which results in ineffective partition of input space. Therefore, to solve this problem, this letter proposes a new fuzzy modeling algorithm which partitions the input space more efficiently that conventional methods by taking into consideration correlations between components of sample data. As a way to use correlation and divide the input space, the method of principal component is ued. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.111-114
• /
• 1997

Generally, fuzzy models have the capability of dividing input space into several subspaces. compared to liner ones. But hitherto suggested fuzzy modeling algorithms not take into consideration the correlations between components of sample input data and address them independently of each other, which results in ineffective partition of input space. Therefore, to solve this problem. this letter proposes a new fuzzy modeling algorithm which partitions the input space more efficiently than conventional methods by taking into consideration correlations between components of sample data. As a way to use correlation and divide the input space. the method of principal component is used. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• Journal of Advanced Marine Engineering and Technology
• /
• 제21권4호
• /
• pp.393-403
• /
• 1997

In this paper, we proposed an optimal identification method of identifying the membership func¬tions and the fuzzy rules for the stabilization controller of the nonlinear system by RVEGA( Real Variable Elitist Genetic Algo rithm l. Although fuzzy logic controllers have been successfully applied to industrial plants, most of them have been relied heavily on expert's empirical knowl¬edge. So it is very difficult to determine the linguistic state space partitions and parameters of the membership functions and to extract the control rules. Most of conventional approaches have the drastic defects of trapping to a local minima. However, the proposed RVEGA which is similiar to the processes of natural evolution can optimize simulta¬neously the fuzzy rules and the parameters of membership functions. The validity of the RVEGA - based fuzzy controller was proved through applications to the stabi¬lization problems of an inverted pendulum system with highly nonlinear dynamics. The proposed RVEGA - based fuzzy controller has a swing -. up control mode(swing - up controller) and a stabi¬lization one(stabilization controller), moves a pendulum in an initial stable equilibrium point and a cart in an arbitrary position, to an unstable equilibrium point and a center of the rail. The stabi¬lization controller is composed of a hierarchical fuzzy inference structure; that is, the lower level inference for the virtual equilibrium point and the higher level one for position control of the cart according to the firstly inferred virtual equilibrium point. The experimental apparatus was imple¬mented by a DT -- 2801 board with AID, D/A converters and a PC - 586 microprocessor.

• 한국지능시스템학회논문지
• /
• 제13권2호
• /
• pp.222-230
• /
• 2003

의료 시스템이 개발되면 시스템이 사용하는 knowledge source의 신뢰도가 시스템의 수행능력에 큰 영향을 미치게 되므로, knowledge source의 신뢰도를 검증해야한다. 본 논문은 의료 시스템 CLINAID의 knowledge source의 신뢰성 조사에 대한 연구의 방법과 결과를 발표하였다. 그 방법으로는 CLINAID에 사용된 Cardiovascular body system 데이터에 fuzzy relational method를 적용하여 구조적 분석을 통해 만들어진 인공의 syndrome을 knowledge base에 저장되어있는 의료 전문가의 syndrome과 비교하였다. 7 가지 fuzzy implication operator를 사용하여 거의 비슷한 결과들을 산출해 냈으며, 그 결과들이 전문가가 제공한 syndrome과 거의 일치하였다.