• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.316-321
• /
• 2003

Recently, support vector learning attracts great interests in the areas of pattern classification, function approximation, and abnormality detection. It is well-known that among the various support vector learning methods, the so-called no-versions are particularly useful in cases that we need to control the total number of support vectors. In this paper, we consider the problem of function approximation utilizing both predetermined basis functions and a no-version support vector learning called $\nu-SVR$. After reviewing $\varepsilon-SVR$, $\nu-SVR$, and a semi-parametric approach, this paper presents an extension of the conventional $\nu-SVR$ method toward the direction that can utilize Predetermined basis functions. Moreover, the applicability of the presented method is illustrated via an example.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.464-466
• /
• 1999

필기 한글 문자 인식을 위해서는 패턴을 구성하는 획 성분을 분석하는 작업이 필수적이다. 기존 인식 방법들은 세선화와 직선 근사에 기반한 방법을 사용하였다. 하지만 세선화는 필기 패턴을 크게 왜곡하는 단점을 안고 있기 때문에 새로운 방법론의 필요성이 대두되고 있다. 본 논문에서는 필기 한글 패턴의 영역-기반 모양 분해 알고리즘을 제안한다. 외곽선 분석을 이용한 기존의 한 단계 알고리즘의 한계를 지적하고, 이 한계를 극복할 수 있는 두 단계 알고리즘을 기술한다. 첫 번째 단계에서는 우세점을 찾아 B접점과 T접점을 탐지한다. 두 번째 단계에서는 볼록 헐(convex hull) 연산을 적용하여 미분할된 부분에 대해 두 번째 분할 작업을 수행한다. PE92 데이터베이스에 대해 실험 한 결과는 세선화 방법보다 우수함을 보인다.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.137-142
• /
• 1995

코호넨의 SOFM(Self-Organizing Feature Map)온 빠른 검증 학습이 가능하여 다층 퍼셉트론의 단점을 보완할 수 있는 패턴분류기로 부각되고 있다. 그러나 기본적으로 고정된 크기와 구조의 네트워크를 사용하기 때문에 실재 문제에 적용하기가 쉽지 않다는 문제가 있다. 본 논문에서는 패턴에 대한 사전 정보없이 복잡한 패턴공간을 적응적으로 분할하기 위해 구조적응되는 자기조직화 신경망을 소개하고 이를 인쇄체 한글 문자의 인식에 적용한 결과를 보여준다. 여기에서 제안하는 신경망은 SOFM의 각 셀이 좀더 자세한 SOFM으로 확장될 수 있도록하며, 확률분포가 0인 셀을 제거함으로써 패턴 공간에 보다 근사한 분류를 가능하게 한다. 실제로 이러한 방식이 한글과 같은 복잡한 분류 문제에서 어떻게 작동하는지 설명하고, 한글 완성형 2350자에 대해 실험한 결과를 보여준다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.8
• /
• pp.99-104
• /
• 2004

This paper proposes a new error pattern ROM (EP-ROM) compression method for continuousdata. The EP-ROM reduces the ROM size by dividing the continuous data into coarse values and their errors and by storing the indices of error patterns instead of the non. This method significantly reduces the ROM size by exploiting the characteristic that the errors for continuous data possess the same patterns. The experiment results show that the EP-ROM achieves 60∼77% ROM size reductions for various continuous data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.51-52
• /
• 2014

Non-destructive technique to measure internal structure and constant distribution of material can be widely used to exploration of mineral resources, identification of underground cables and buried pipelines, and diagnostic imaging in medical area. In this paper, we considered 2-dimensional EM scattering problem. Radiation pattern in far field is estimated by using some measured information obtained from near-field solutions.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.681-687
• /
• 2001

In order to raise a class discrimination power by combining multiple classifiers under the Bayesian decision theory, the upper bound of a Bayes error rate bounded by the conditional entropy of a class variable and decision variables obtained from training data samples should be minimized. Wang and Wong proposed a tree dependence first-order approximation scheme of a high order probability distribution composed of the class and multiple feature pattern variables for minimizing the upper bound of the Bayes error rate. This paper presents an extended high order product approximation scheme dealing with higher order dependency more than the first-order tree dependence, based on the minimization of the upper bound of the Bayes error rate. Multiple recognizers for unconstrained handwritten numerals from CENPARMI were combined by the proposed approximation scheme using the Bayesian formalism, and the high recognition rates were obtained by them.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.98-106
• /
• 1998

This paper proposes an efficient learning algorithm for improving the training performance of the neural network. The proposed method improves the training performance by applying the backpropagation algorithm of a global optimization method which is a hybrid of a stochastic approximation and a conjugate gradient method. The approximate initial point for f a ~gtl obal optimization is estimated first by applying the stochastic approximation, and then the conjugate gradient method, which is the fast gradient descent method, is applied for a high speed optimization. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to those of the conventional backpropagation and the backpropagation algorithm which is a hyhrid of the stochastic approximation and steepest descent method.

• Journal of KIISE:Databases
• /
• v.28 no.4
• /
• pp.545-557
• /
• 2001

In this paper we propose a hierarchical classification algorithm based on rough membership function which can reason a new object approximately. We use the fuzzy reasoning method that substitutes fuzzy membership value for linguistic uncertainty and reason approximately based on the composition of membership values of conditional sttributes Here we use the rough membership function instead of the fuzzy membership function It can reduce the process that the fuzzy algorithm using fuzzy membership function produces fuzzy rules In addition, we transform the information system to the understandable minimal decision information system In order to do we, study the discretization of continuous valued attributes and propose the discretization algorithm based on the rough membership function and the entropy of the information theory The test shows a good partition that produce the smaller decision system We experimented the IRIS data etc. using our proposed algorithm The experimental results with IRIS data shows 96%~98% rate of classification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.677-680
• /
• 2008

The paper deals with the analysis of radiation characteristics of antenna in the multi-layered media structures. The dyadic Green's function for three layer medium is complex because the Green's functions belonging to the kernel of the integral equation are expressed as Sommerfeld integrals, in which surface wave effects are automatically included. When certain condition are met, the integral can be evaluated approximated by the method of Saddle-point integration. In this study, we propose a method to calculate a radiation pattern for several antennas by using the method of Saddle-point integration. Numerical results show how the radiation characteristics are affected by parameter of dielectric media.

• Journal of the Korean Home Economics Association
• /
• v.44 no.2 s.216
• /
• pp.127-135
• /
• 2006

This paper suggests guidelines for virtual clothes modeling and draping software suitable for clothes designers. We first analyze Maya Cloth, which is widely used in game and animation fields, and which has been adopted by Pad System as a 3D cloth draping system. We then discuss what functions and procedures would improve Maya Cloth to assist designers in being able to create the clothes they have conceptualized. While Maya Cloth has many good functions and features forvirtual cloth modeling and draping, it treats input 2D patterns as approximat and it creates 3D clothes by considering other factors such as the 3D body model. As a result, it is hard for clothes designers to control the shape of the 3D clothes by changing 2D patterns. Furthermore, Maya Cloth does not handle seamlines satisfactorily. We suggest that the following new features should be added to Maya Cloth : respecting the input 2D patterns, handling seamlines, and controlling the shape of the clothes in 3D space.