• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.1
• /
• pp.1-8
• /
• 2001

본 논문에서는 정규화된 데이터 공간과 가우스함수에 의한 산 함수 형성 그리고 형성된 산의 기울기를 이용한 산봉우리 붕괴를 특징으로 하는 개선된 산 클러스터링 방법을 제안한다. 이 개선된 방법은 기존의 Yager 등에 의하여 제안된 방법이 조정해야 하는 매개변수가 3개이고 발견된 클러스터 중심 주위에 원치 않는 다른 중심이 발생할 수 있는데 반하여 단지 하나의 매개변수 $\omega$의 조정으로 더욱 타당한 중심을 찾아내는 점에서 유용하다 할 수 있다. 또한 매개변수 $\omega$에 대한 적절한 선정 방법을 제시하고, 수치 자료에 대한 컴퓨터 모의실험을 통하여 개선된 산 클러스터링 방법의 유용성을 입증한다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.31-36
• /
• 2005

EDF에 근거한 Cramer-von Mises 형태의 통계량을 합교원리를 이용하여 다변량으로 일반화한다. 그리고 제안된 통계량의 귀무가설에서의 극한분포를 적절한 공분산함수를 가진 가우스 과정의 적분의 형태로 표현하고 통계량의 근사적인 계산방법을 고려한다.

• Journal of the Korean Geophysical Society
• /
• v.5 no.2
• /
• pp.131-142
• /
• 2002

Geomagnetic transfer function is generally estimated by choosing transfer to minimize the square sum of differences between observed values. If the error structure sccords to the Gaussian distribution, standard least square(LS) can be the estimation. However, for non-Gaussian error distribution, the LS estimation can be severely biased and distorted. In this paper, the Gaussian error assumption was tested by Q-Q(Quantile-Quantile) plot which provided information of real error structure. Therefore, robust estimation such as regression M-estimate that does not allow a few bad points to dominate the estimate was applied for error structure with non-Gaussian distribution. The results indicate that the performance of robust estimation is similar to the one of LS estimation for Gaussian error distribution, whereas the robust estimation yields more reliable and smooth transfer function estimates than standard LS for non-Gaussian error distribution.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.903-908
• /
• 2015

This paper has analyzed threshold voltage shift for doping profile of asymmetric double gate(DG) MOSFET. Ion implantation is usually used in process of doping for semiconductor device and doping profile becomes Gaussian distribution. Gaussian distribution function is changed for projected range and standard projected deviation, and influenced on transport characteristics. Therefore, doping profile in channel of asymmetric DGMOSFET is affected in threshold voltage. Threshold voltage is minimum gate voltage to operate transistor, and defined as top gate voltage when drain current is $0.1{\mu}A$ per unit width. The analytical potential distribution of series form is derived from Poisson's equation to obtain threshold voltage. As a result, threshold voltage is greatly changed by doping profile in high doping range, and the shift of threshold voltage due to projected range and standard projected deviation significantly appears for bottom gate voltage in the region of high doping concentration.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.115-122
• /
• 2012

We present here a new class of activation functions for neural networks, which herein will be called CosGauss function. This function is a cosine-modulated gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and gaussian activation functions, more ridges can be obtained by the CosGauss function. It will be proven that this function can be used to aproximate polynomials and step functions. The CosGauss function was tested with a Cascade-Correlation-Network of the multilayer structure on the Tic-Tac-Toe game and iris plants problems, and results are compared with those obtained with other activation functions.

• Journal of KIISE:Information Networking
• /
• v.29 no.5
• /
• pp.553-561
• /
• 2002

We present a novel service discipline, called linear service discipline, to serve multiple QoS queues sharing a resource and analyze its properties. The linear server makes the output traffic and the queueing dynamics of individual queues as a linear function of its input traffic. In particular, if input traffic is Gaussian, the distributions of queue length and output traffic are also Gaussian with their mean and variance being a function of input mean and input power spectrum (equivalently, autocorrelation function of input). Important QoS measures including buffer overflow probability and queueing delay distribution are also expressed as a function of input mean and input power spectrum. This study explores a new direction for network-wide traffic management based on linear system theories by letting us view the queueing process at each node as a linear filter.

• Journal of Korea Game Society
• /
• v.9 no.5
• /
• pp.137-144
• /
• 2009

This paper predicts 6 facial regions that may have sharply different scattering properties, rendering the face more realistically based on their diffusion profiles. The scattering properties are acquired in the form of high dynamic range by photographing the pattern formed around an unit ray incident on facial skin. The acquired data are fitted to a 'linear combination of Gaussian functions', which well approximates the original diffusion profile of skin and has good characteristics as the filter. During the process, to prevent its solutions from converging into local minima, we take advantage of the genetic algorithm to set up the initial value. Each Gaussian term is applied to the irradiance map as a filter, expressing subsurface scattering effect. In this paper, to efficiently handle the maximum 12 Gaussian filterings, we make use of the parallel capacity of CUDA.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.136-141
• /
• 1994

In this paper, we implemented an opto-electronical signal processing system for the edge detection using the diffusion neural network. The diffusion neural network performs a Gaussian and DOG operation efficiently by the diffusion process. The diffusion neural network is more efficient than the LOG masking method in hardware implementation because it has a few connections and the connection weights are fixed-valued. We implemented a diffusion neural network using the characteristics of the light intensity distribution function which is similar to the Gaussian function. We have shown that the system can detect the edge of an image exactly through the experimental results.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.3
• /
• pp.133-140
• /
• 2018

This paper is concerned with the 2-D micostructure generation for $Ni-A{\ell}_2O_3$ dual-phase composite materials and the numerical analysis of mechanical characteristic of hierarchical models of microstructure which are defined in terms of the scale of microstructure. The microstructures of dual-phase composite materials were generated by applying the mathematical RMDF(random morphology description functions) technique to a 2-D RVE of composite materials. And, the hierarchical models of microstructure were defined by the number of Gaussian points. Meanwhile, the volume fractions of metal and ceramic particles were set by adjusting the level of RMD functions. The microstructures which were generated by RMDF technique are definitely random even though the total number of Gaussian points is the same. The randomly generated microstructures were applied to a 2-D beam model, and the variation of normal and shear stresses to the scale of microstructure was numerically investigated. In addition, through the crack analyses, the influence of RMDF randomness and Gauss point number on the crack-tip stress is investigated.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.243-246
• /
• 1998

집속음장의 고조파성분을 이용한 초음파영상의 특성을 해석하기 위해 집속된 가우스 음원에 직선 edge를 초점면 및 초점면의 전, 후방에 삽입하여 edge의 후방에서 생성되는 음장을 조사하였다. 계산에서는 그린함수의 간단화를 위해 Fresnel근사를 이용하였고, 실험에서는 성형전극을 형성시킨 1.9MHz 요면진동자에 의한 가우스분포의 음장을 갖는 초음파빔에 수직하게 edge를 삽입시켰다. 음장의 이론해석 및 실험결과, 초점면의 제2고조파의 빔형상을 제외하고는 계산치와 실험치가 잘 일치하고 있으며, 제2고조파의 공간 분해능이 기본파에 비해 높음을 알았다.