• Journal of information and communication convergence engineering
• /
• v.8 no.4
• /
• pp.383-386
• /
• 2010

Pattern classification is one of the most important topics for machine learning research fields. However incomplete data appear frequently in real world problems and also show low learning rate in classification models. There have been many researches for handling such incomplete data, but most of the researches are focusing on training stages. In this paper, we proposed two classification methods for incomplete data using triangular shaped fuzzy membership functions. In the proposed methods, missing data in incomplete feature vectors are inferred, learned and applied to the proposed classifier using triangular shaped fuzzy membership functions. In the experiment, we verified that the proposed methods show higher classification rate than a conventional method.

• Journal of Korean Institute of Industrial Engineers
• /
• v.23 no.2
• /
• pp.371-383
• /
• 1997

This paper propose a fuzzy regression method using fuzzy neural networks when a membership value is attached to each input-output pair. First, a method of linear fuzzy regression analysis is described by interpreting the reliability of each input-output pair as its membership values. Next, an architecture of fuzzy neural networks with fuzzy weights and fuzzy biases is shown. The fuzzy neural network maps a crisp input vector to a fuzzy output. A cost function is defined using the fuzzy output from the fuzzy neural network and the corresponding target output with a membership value. A learning algorithm is derived from the cost function. The derived learning algorithm trains the fuzzy neural network so that the level set of the fuzzy output includes the target output. Last, the proposed method is illustrated by computer simulations on numerical examples.

• Annual Conference on Human and Language Technology
• /
• 1990.11a
• /
• pp.191-198
• /
• 1990

본 논문에서는 문서 자동 인식 시스템에서 다중 카테고리로 모호하게 인식되어 질 수 있는 조합 심볼을 하나의 메타 심볼로 간주하고, 이 심볼을 fuzzy set theory에 기초를 두어 분석을 하였다. 분석 과정에서는 메타 심볼이 갖는 프리미티브들의 기울기와 길이, 프리미티브들간의 연결 및 프리미티브의 위치등의 어트리뷰트들을 이용하였다. 모호성을 내재하고 있는 메타 심볼들을 ACS(Ambiguous Category Set)의 원소로 간주하였으며, ACS의 원소들은 모호성의 원인을 제공하는 부분패턴들을 공동으로 포함하고 있다. 부분패턴을 구성하고 있는 프리미티브를 분리하여 어트리뷰트 값을 측정하고, 정의한 MF(Membership 함수)의 파라메터로 사용하였다. MF에서 얻어진 MFV(Membership Function Value)는 모호한 메타 심볼이 어떤 카테고리로 분류될 수 있는지를 나타내도록 하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.209-215
• /
• 2015

Fuzzy c-means method is typical soft clustering, and requires a degree of membership that indicates the degree of belonging to each cluster at the time of clustering. Parameter values greater than 1 and less than 2 have been used by convention. According to the proposed data-generation scheme and the simulation results, some behaviors in the degree of "fuzziness" was derived.

• Publications of The Korean Astronomical Society
• /
• v.30 no.2
• /
• pp.271-273
• /
• 2015

The bulk motion of star clusters can be determined after careful membership analysis using parametric or non-parametric approaches. This study aims to implement non-parametric membership analysis based on Binned Kernel Density Estimators which takes into account measurements errors (simply called BKDE-e) to determine the average proper motion of each cluster. This method is applied to 178 selected star clusters with angular diameters less than 20 arcminutes. Proper motion data from UCAC4 are used for membership determination. Non-parametric analysis using BKDE-e successfully determined the average proper motion of 129 clusters, with good accuracy. Compared to COCD and NCOVOCC, there are 79 clusters with less than $3{\sigma}$ difference. Moreover, we are able to analyse the distribution of the member stars in vector point diagrams which is not always a normal distribution.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1414-1417
• /
• 1993

Wang and Medel proved (1991) that fuzzy systems with product inference, centroid defuzzification, and everywhere positive membership functions (in particular, Gaussians, Wang, 1992) are capable of approximating any real continuous control function on a compact set to arbitrary accuracy. Kosko (1992) proved that fuzzy systems, in which membership functions have compact support, and combination operation (V-operation) for rules is the sum, are also universal approximators. In this paper, we generalize this result of Kosko and prove that for any &- and V-operations, any defuzzification procedure, and any basic membership function with a compact support, the resulting fuzzy controls are universal approximators. Also, Wang's result is transfered to min-inference.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.933-936
• /
• 1993

A high speed fuzzy processor using bipolar technology is proposed in this paper. The hardware system uses a high-speed current-mode membership function circuit and normalization technique. The new membership function circuit generates an ideal membership function of the fuzzy set and its circuit is also simple and available for VLSI implementation. Several techniques have been implemented to speed up response of the processor. The fuzzy processor has been designed and implemented in bipolar circuit technology. The experiments and simulations show that the response speed is below 100ms. It can also be expected that the fuzzy processor can be integrated on one chip and its response time is only about the order of nanoseconds.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.2
• /
• pp.102-109
• /
• 1997

The width of fuzzy membership function and control rule has an effect on performance of the fuzzy controller for electric equipment systems. In this paper, the neuro-fuzzy controller is proposed to im¬prove the performance of fuzzy controller. It has the width of membership function, that is adapted to the electrical parameter using multi-layer neural network, it is applied to first order electric power system with dead time and various plant constant. The related simulation resolts show that the pro¬posed neuro fuzzy controller are superior characteristics of improved performance

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.489-491
• /
• 1993

Many optimization problem or multiple attribute, multiple alternative decision making problem may have fuzzy evaluation factors. In this case, fuzzy number operation technique is needed to evaluate and compare object functions which become fuzzy sets. Generally, fuzzy number operations can be defined by extension principle of fuzzy set theory, but it is tedious to do fuzzy number operations by using extension principle when the membership functions are defined by complex functions. Many fast methods which approximate the membership functions such as triangle, trapezoidal, or L-R type functions are proposed. In this paper, a fast fuzzy number operation method is proposed which do not simplify the membership functions of fuzzy numbers.

• Journal of Biosystems Engineering
• /
• v.20 no.1
• /
• pp.87-94
• /
• 1995

When farmer loads and unloads farm products with a trailer, linked to a tractor, the tractor-trailer is backed up to the loading duck. However, travelling backward is not easy and takes a time for even skilled operators. Therefore, unmanned backing up is necessary to save the effort. A backward controller of tractor-trailer was simulated using fuzzy logic and genetic algorithms. Operators drive the tractor-trailer back and forth several times for backing up to the loading duck. As the operators did it, a backward controller was designed using fuzzy logic. And genetic algorithms was applied to improve the performance of the backward controller. With the strings coded with the fuzzy membership functions, genetic operations were carried out. After 30 generations, the best fitted fuzzy membership functions were found. Those membership functions were used in the fuzzy backward controller. The fuzzy controller combined with genetic algorithms showed the better results than the fuzzy controller did alone.