• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• pp.233-240
• /
• 2001

This paper presents a time series prediction method using a fuzzy rule-based system. Extracting fuzzy rules by performing a simple one-pass operation on the training data is quite attractive because it is easy to understand, verify, and extend. The simplest method is probably to relate an estimate, x(n+k), with past data such as x(n), x(n-1), ..x(n-m), where k and m are prefixed positive integers. The relation is represented by fuzzy if-then rules, where the past data stand for premise part and the predicted value for consequence part. However, a serious problem of the method is that it cannot handle nonstationary data whose long-term mean is varying. To cope with this, a new training method is proposed, which utilizes the difference of consecutive data in a time series. In this paper, typical previous works relating time series prediction are briefly surveyed and a new method is proposed to overcome the difficulty of prediction nonstationary data. Finally, computer simulations are illustrated to show the improved results for various time series.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.170-173
• /
• 2002

본 논문에서는 여러 분야에서 널리 응용되고 있는 적응 뉴로-퍼지 시스템(ANFIS)에서의 효과적인 퍼지 규칙 생성방법을 제안한다. ANFIS의 성능 개선을 위해 구조동정을 수행함에 있어서 전제부 파라미터는 EM(Expectation-Maximization) 알고리즘을 적용하였으며, 파라미터학습은 Jang에 의한 하이브리드 방법을 적용한다. 여기서 초기의 중심과 분산을 구하기 위해 FCM(Fuzzy c-means) 클러스터링 기법을 사용하였다. 이렇게 함으로서 적은 규칙 수를 가지면서도 효율적인 퍼지 규칙을 얻을 수 있도록 하였다. 이들 방법의 유용함을 보이고자 Box-Jenkins의 가스로 데이터에 적용하여 제안된 방법이 이전의 연구보다 좋은 결과를 보임을 보이고자 한다

• Journal of Korea Multimedia Society
• /
• v.4 no.2
• /
• pp.189-196
• /
• 2001

Fuzzy logic ignores some information in the reasoning process. Neural networks are powerful tools for the pattern processing, but, not appropriate for the logical reasoning. To model human knowledge, besides pattern processing capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy inference is a fuzzy logical reasoning, we construct fuzzy inference network based on the neural logic network, extending the existing rule - inference network. and the traditional propagation rule is modified.

• Knowledge Management Research
• /
• v.9 no.4
• /
• pp.113-125
• /
• 2008

Net present value (NPV) and return on investment (ROI) are commonly used to evaluate investment in new technologies. Sometimes, however, measuring the value of investment in new IT becomes very difficult due to its wide scope of application coupled with embedded options in its adoption. Therefore, comprehensive but easily understandable methodologies are needed to solve the complicated problems resulting from the complexity of new technologies. This paper employs a real option analysis to evaluate RFID adoption in the supply chain. Real options analysis should be a better way to evaluate a disruptive technology like RFID. However, the pure (probabilistic) real option rule characterizes the present value of expected cash flows and the expected costs by a single number, which is not realistic in many cases. To solve the problem, this paper considers the real option rule in a more realistic setting, namely, when the present values of expected cash flows and expected costs are estimated by trapezoidal fuzzy numbers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1254-1259
• /
• 2005

In this paper, we proposed a learning algorithm for the neuro-fuzzy modeling using a learning rule to adapt clustering. The proposed algorithm includes the data partition, assigning the rule into the process of partition, and optimizing the parameters using predetermined threshold value in self-constructing algorithm. In order to improve the clustering, the learning method of neuro-fuzzy model is extended and the learning scheme has been modified such that the learning of overall model is extended based on the error-derivative learning. The effect of the proposed method is presented using simulation compare with previous ones.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.50-54
• /
• 1997

In general, the design of fuzzy logic controller has difficulties in the acquisition of expert's knowledge. So, some methods that can optimize the parameters for fuzzy logic controller automatically without expert knowledge was provided. Recently, tuning method for fuzzy logic controller using genetic algorithm(GA) were proposed in many papers. However, those are tuning methods for a part or some part of fuzzy logic controller. In this paper, we proposes auto tuning method for the whole part of tuzzy logic controller, such as parameters of membership functions for antecedence and consequence parts, rule base, scaling factor and the number of rule. Finally, second order dead time plant is provided to show the advantages of the proposed method.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.252-254
• /
• 1992

This paper proposes a new algorithm that finds fuzzy control law of the system in which little knowledge has been known. In view or conventional fuzzy method, making control law needs the sense and the knowledge of the system which are provided by expert. But fuzzy control using proposed algorithm needs no expert for hating control law. After construction of the 1st order approximated ARMA model using input-output pairs, new defuzzification method is applied. The deduced rule is stored in fuzzy input space and updated by the proposed algorithm adaptively. To show the validity and effectiveness of proposed control method. simulation result is presented.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.121-125
• /
• 2001

본 논문에서는 자동적인 퍼지 규칙 생성을 위해 퍼지 균등화(Fuzzy Equalization)와 유전알고리즘(Genetic Algorithm)을 이용한 TSK 퍼지 시스템의 구축을 다룬다. Pedrycz에 의해 제안된 퍼지 균등화 방법은 수치적인 데이터로부터 확률분포함수를 구축한 후 전체공간상에서 이들을 적절히 표현할 수 있는 소속함수를 생성한다. 이렇게 구축된 각 입력에 대한 소속함수는 유전알고리즘에 의해 입력공간이 분할되며 결론부 파라미터는 최소자승법에 의해 추정되어 진다. 제안된 방법은 그리드 분할로 인해 규칙의 수가 증가하는 문제를 해결하고 학습데이터와 검증데이터에 의해 타당한 입력공간분할과 퍼지 규칙을 생성할 수 있다. 시뮬레이션의 예로서 Box-Jenkins의 가스로 데이터의 모델링에 적용하여 제안된 방법의 유용성을 알 수 있다.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.702-704
• /
• 1995

In this paper, using a new adaptive fuzzy controller we have designed a power system stabilizer. The adaptive fuzzy controller constitutes of several parallel fuzzy controller. Each of them can maintain the robust stability for a specified parametric uncertainty region. If the parametric variation is so large that a rule-base cannot cope with that parametric region, the other appropriate rule-base is selected to control. Applying adaptive fuzzy controller to single machine infinite bus system, we simulate the stability of the system and compare the performance with conventional PSS controller.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.3
• /
• pp.324-328
• /
• 2007

An analytical framework for fuzzy modeling and control of nonlinear systems using a set of linear models is presented. Fuzzy clustering is applied on the aerodynamic coefficients of a missile to obtain an optimal number of rules in a Tagaki-Sugeno fuzzy rule-set. Next, the obtained membership functions and rule-sets are applied to a set of linear optimal controllers towards extraction of a global controller. Reported simulations demonstrate the performance, stability, and robustness of the controller.