• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2095-2096
• /
• 2006

본 논문에서는 복잡하고 비선형적인 시스템에 대하여 구체적이고 체계적인 방법에 의한 퍼지 모델을 동정하기 위해 유전자알고리즘을 이용하여 전반부 및 후반부의 구조와 파라미터 동정하기 위한 유전론적 접근을 소개한다. 정보 입자 기반 퍼지 모델의 구조를 동정하기 위하여 유전자 알고리즘을 이용하여 입력 변수의 수, 선택될 입력 변수, 멤버쉽함수의 수, 그리고 후반부 형태를 결정하고, 파라미터를 동정하기 위하여 전반부 멤버쉽 파라미터를 동조하여 최적의 퍼지 모델을 설계한다. 또한 구조 동정 및 파라미터 동정에 있어서 개별적인 방법과 동시적인 방법으로 접근하여 정보 입자 기반 퍼지 모델의 최적 동정을 도모한다. 마지막으로 제안된 퍼지 모델은 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.48-57
• /
• 1997

This paper presents the automatic construction and parameter optimization technique for fuzzy logic controllers using genetic algorithm. In general. the design of fuzzy logic controllers has difficulties in the acq~lisition of expert's knowledge and relies to a great extent on empirical and heuristic knowledge which, in many cases, cannot be objectively justified. So, the performance of the controllers c:an be degraded in the case of plant parameter variations or unpredictable incident which a designer may have ignored, and the parameters of fuzzy logic controllers obtained by expert's control action may not be optirnal. Some of these problems can be resolved by the use of genetic algorithm. The proposed method can tune the parameters of fuzzy logic controllers including scaling factors and determine: the appropriate number of fuzzy rulcs systematically. Finally, we provides the second order dead time plant to evaluate the feasibility and generality of the proposed method. Comparison shows that the proposed method can produce fuzzy logic controllers with higher accuracy and a smaller number of fuzzy rules than manually tuned fuzzy logic controllers.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.135-147
• /
• 2001

This study proposes bankruptcy prediction model using fuzzy neural networks. Neural networks offer preeminent learning ability but they are often confronted with the inconsistent and unpredictable performance for noisy financial data. The existence of continuous data and large amounts of records may pose a challenging task to explicit concepts extraction from the raw data due to the huge data space determined by continuous input variables. The attempt to solve this problem is to transform each input variable in a way which may make it easier fur neural network to develop a predictive relationship. One of the methods selected for this is to map each continuous input variable to a series of overlapping fuzzy sets. Appropriately transforming each of the inputs into overlapping fuzzy membership sets provides an isomorphic mapping of the data to properly constructed membership values, and as such, no information is lost. In addition, it is easier far neural network to identify and model high-order interactions when the data is transformed in this way. Experimental results show that fuzzy neural network outperforms conventional neural network for the prediction of corporate bankruptcy.

• Economic and Environmental Geology
• /
• v.41 no.6
• /
• pp.763-771
• /
• 2008

Uncertainties are pervasive in engineering geological problems. Therefore, the presence of uncertainties and their significance in analysis and design of slopes have been recognized. Since the uncertainties cannot be taken into account by the conventional deterministic approaches in slope stability analysis, the probabilistic analysis has been considered as the primary tool for representing uncertainties in mathematical models. However, some uncertainties are caused by incomplete information due to lack of information, and those uncertainties cannot be handled appropriately by the probabilistic approach. For those uncertainties, the theory of fuzzy sets is more appropriate. Therefore, in this study, fuzzy reliability analysis has been proposed in order to deal with the uncertainties which cannot be quantified in the probabilistic analysis due to the limited information. For the practical example, a slope is selected in this study and both the probabilistic analysis and the fuzzy reliability analysis have been carried out for planar failure. In the fuzzy reliability analysis, the dip angle and internal friction angle of discontinuity are considered as triangular fuzzy numbers since the random properties of the variables cannot be obtained completely under the conditions of limited information. In the study, the fuzzy reliability index and the probabilities of failure are evaluated from fuzzy arithmetic and compared to those from the probabilistic approach using Monte Carlo simulation and point estimate method. The analysis results show that the fuzzy reliability analysis is more appropriate for the condition that the uncertainties arise due to incomplete information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1684-1690
• /
• 2003

In this paper, we proposed a fuzzy controller for the evaluation of the quantization Parameters in the H.263 coder to optimize the subjective quality of each coded frame, keeping the transmission rate constant. We adopted the Mamdani method for fuzzification and the centroid method for defuzzification. The energy and entropy are correlated to features of the HVS in spatial domain, while motion vectors are used to estimate the temporal characteristics of the signal. And then, the fuzzy inputs adapted the variance and the entropy in spatial domain, and the motion vector in temporal domain. We induced the fuzzy membership function and decided the fuzzy relevance to be compatible in visual characteristics. And then, we designed FAM banks. The fuzzy technology has been applied to a practical video compression. This results is obtained an effective rate control technique, an optimum bit allocation and a high subjective quality using fuzzy quantization.

• Journal of Korean Society of Transportation
• /
• v.23 no.8 s.86
• /
• pp.171-179
• /
• 2005

This paper presents the algorithm using fuzzy inference that preestimates each link speed changed by different kinds of road situations. The elements we are considered are time zone, rainfall probability information and lane control information. This paper is consists of three parts. First of all we set up the fuzzy variables, and preestimate link speed changed by various road situations. For this process, we build the membership functions for each fuzzy variable and establish the fuzzy inference relations to find how fuzzy variables influence on link speed. Second, using backtracking method, we search the shortest route influenced by link speed changed by fuzzy inference. Third, we apply this algorithm to hypothetical network and find the shortest path. As a result, it is shown that this algorithm choose appropriate roundabout path according to the changing road situations.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.573-580
• /
• 2006

The Saturation headway is a major parameter in estimating the intersection capacity and setting the signal timing. But Existing algorithms are still far from being robust in dealing with factors related to the variation of saturation headways at signalized intersections. So this study apply the fuzzy inference system using ANFIS. The ANFIS provides a method for the fuzzy modeling procedure to learn information about a data set, in order to compute the membership function parameters that best allow the associated fuzzy inference system to track the given input/output data. The climate conditions and the degree of brightness were chosen as the input variables when the rate of heavy vehicles is 10-25 %. These factors have the uncertain nature in quantification, which is the reason why these are chosen as the fuzzy variables. A neuro-fuzzy inference model to estimate saturation headways at signalized intersections was constructed in this study. Evaluating the model using the statistics of $R^2$, MAE and MSE, it was shown that the explainability of the model was very high, the values of the statistics being 0.993, 0.0289, 0.0173 respectively.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1998.03a
• /
• pp.56-60
• /
• 1998

유고 감지 시스템은 검지기로부터 얻은 데이터를 분석하여 특정 구간의 유고 발생 여부를 판단하는 시스템으로 교통 관제의 측면에서 매우 중요한 역할을 한다. 본 논문에서는 속도, 밀도 그리고 교통량의 변화와 같은 다양한 유고 감지 변수를 어떻게 퍼지 시스템에 사용하는가를 보여주고 기존의 알고리즘이 안고 있던 문제점들을 해결하기 위한 퍼지 유고 감지 알고리즘을 제안한다. 또한 시뮬레이션을 통해서 제안된 퍼지 유고 알고리즘의 성능을 평가한다.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.717-720
• /
• 2000

H.263의 시험모델인 TMN5를 최대한 적용하여 실험하였으며 분산, 엔트로피, 움직임 크기 등의 퍼지변수를 데이터 영역에서 추출하여 퍼지화하였다. 소속함수를 계산하기 위해 최소값으로 가장 분명한 퍼지값을 추출하였으며 퍼지집합을 위해서는 각 소속함수로부터의 요소를 더하는 의미에서 최대값을 선택하였다. 무게중심기법을 이용하여 최종 퍼지감도를 구하여 TMN5에 부가하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.767-778
• /
• 2003

This paper presents a method for generating optimal fuzzy rules using a genetic algorithm. Fuzzy rules are generated from the training data in the first stage. In this stage, fuzzy c-Means clustering method and cluster validity are used to determine the structure and initial parameters of the fuzzy inference system. A cluster validity is used to determine the number of clusters, which can be the number of fuzzy rules. Once the structure is figured out in the first stage, parameters relating the fuzzy rules are optimized in the second stage. Weights and variance parameters are tuned using genetic algorithms. Variance parameters are also managed with left and right for asymmetrical Gaussian membership function. The method ensures convergence toward a global minimum by using genetic algorithms in weight and variance spaces.