• 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 the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.1
• /
• pp.42-48
• /
• 2006

In this study, a repetitive response surface enhancement technique (RRSET) is proposed as a new system approximation method for the efficient multidisciplinary design and optimization (MDO). In order to represent the highly nonlinear behavior of the response with second order polynomials, RRSET introduces a design space transformation using stretching functions and repetitive response surface improvement. The tentative optimal point is repetitively included to the set of experimental points to better approximate the response surface of the system especially near the optimal point, hence a response surface with significantly improved accuracy can be generated with very small experimental points and system iterations. As a system optimizer, the simulated annealing, which generates a global design solution is utilized. The proposed technique is applied to several numerical examples, and demonstrates the validity and efficiency of the method. With its improved approximation accuracy, the RRSET can contribute to resolve large and complex system design problems under MDO environment.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.719-722
• /
• 2011

본 연구에서는 이동최소제곱 차분법을 2차원 동적고체문제를 해석하기 위하여 확장시켰으며 Newmark ${\beta}$ 방법을 통해 explicit와 implicit 시간적분법을 모두 적용하여 그 차이를 비교하였다. 이동최소제곱 차분법은 Taylor 다항식을 이용하여 미분계산을 근사화 함으로써 내부 및 경계에서도 강형식을 그대로 이용할 수 있다. 그래서 계산이 빠르고 수치적분이 필요하지 않아 무요소법의 장점을 잘 살릴 수 있고 해석차수를 손쉽게 조정할 수 있어 cubic 등의 고차 근사계산이 간편하다. 두 가지 수치예제를 통하여 동적해석에 대한 이동최소제곱 차분법의 적용성과 안정성을 검증하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.3
• /
• pp.597-605
• /
• 1999

In this paper, we propose a cardioangiography sequence image coding scheme which use a subtraction between initial image and current frame inserted contrast dye. Stable regions are obtained by the multithreshold and meaningful region is extracted by the images with stable region. The image with meaningful region is classified into contour and texture information. Contour information is coded by contour coding. And texture information is approximated by two-dimensional polynomial function and each coefficients is coded. Experimental results confirm that the sequence of cardioangiography are well reconstructed at the low bit rate (0.02∼0.04 bpp) and high compression ratio.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1956-1957
• /
• 2011

본 연구는 White LED를 이용하여 주변 밝기 변화에 빠르게 적응하는 퍼지 뉴로 Dimming Control System을 설계한다. 본 논문에서는 방사형기저함수 신경회로망(Radial Basis Function Neural Network: RBFNN)을 설계하여 실제 White LED Dimming Control System에 적용시켜 모델의 근사화 및 일반화 성능을 평가한다. 제안한 모델에서의 은닉층은 방사형기저함수를 사용하여 적합도를 구현하였고, 후반부의 연결가중치는 경사하강법을 사용한다. 이때 멤버쉽 함수의 중심점은 HCM 클러스터링 (Hard C-Means Clustering)을 적용하여 결정한다. 연결가중치는 4가지 형태의 다항식을 대입하여 출력을 평가하였다. 최종 출력의 최적화를 위하여 PSO(Particle Swarm Optimization)을 이용하여 은닉층 노드수 및 다항식 형태를 결정한다. 본 논문에서 제안한 LED Dimming Control System은 Atmega8535를 사용하여 PWM 제어 방식을 사용하고, 조도계(Cds)를 이용하여 LED의 밝기에 따른 주변의 밝기를 감지하여 조명에 적응시키는 방법을 적용하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5A
• /
• pp.457-465
• /
• 2009

This study presents a moving least squares (MLS) finite difference method for solving elastic crack problems with stress singularity at the crack tip. Near-tip functions are intrinsically employed in the MLS approximation to model near-tip field inducing singularity in stress field. employment of the functions does not lose the merit of the MLS Taylor polynomial approximation which approximates the derivatives of a function without actual differentiating process. In the formulation of crack problem, computational efficiency is considerably improved by taking the strong formulation instead of weak formulation involving time consuming numerical quadrature Difference equations are constructed on the nodes distributed in computational domain. Numerical experiments for crack problems show that the intrinsically enriched MLS finite difference method can sharply capture the singular behavior of near-tip stress and accurately evaluate stress intensity factors.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.13 no.1
• /
• pp.39-46
• /
• 1993

The need to develop method which can improve the shape design efficiency using high quality approximation is being brought up. In this study, to perform shape optimal design of three-dimensional continuum structures an efficient approximation method for stress constraints is proposed, based on expanding the nodal forces in Taylor series with respect to shape variables. Numerical examples are performed using the 3-D cantilever beam and fixed-fixed beam and compared with other method to demonstrate the efficiency and convergence rate of the Force Approximation method. It is shown that by taking advantage of this high quality approximation, the total number of finite element analysis required for shape optimization of 3-D continuum structures can be reduced significantly, resulting to the same level of efficiency achieved previously in sizing optimization problems. Also, shape representation by super curve technique applied to obtain optimal shape finds useful method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.846-851
• /
• 2005

In this paper, we propose Genetic Algorithms(GAs)-based Optimized Polynomial Neural Networks(PNN). The proposed algorithm is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional neural networks and can be generated in a dynamic manner. As each node of PNN structure, we use several types of high-order polynomial such as linear, quadratic and modified quadratic, and it is connected as various kinds of multi-variable inputs. The conventional PNN depends on the experience of a designer that select the number of input variables, input variable and polynomial type. Therefore it is very difficult to organize optimized network. The proposed algorithm leads to identify and select the number of input variables, input variable and polynomial type by using Genetic Algorithms(GAs). The aggregate performance index with weighting factor is proposed as well. The study is illustrated with tile NOx omission process data of gas turbine power plant for application to nonlinear process. In the sequel the proposed model shows not only superb predictability but also high accuracy in comparison to the existing intelligent models.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.4
• /
• pp.493-499
• /
• 2007

The Taylor expansion expresses a differentiable function and its coefficients provide good approximations for the given function and its derivatives. In this study, m-th order Taylor Polynomial is constructed and the coefficients are computed by the Moving Least Squares method. The coefficients are applied to the governing partial differential equation for solid problems including crack problems. The discrete system of difference equations are set up based on the concept of point collocation. The developed method effectively overcomes the shortcomings of the finite difference method which is dependent of the grid structure and has no approximation function, and the Galerkin-based meshfree method which involves time-consuming integration of weak form and differentiation of the shape function and cumbersome treatment of essential boundary.

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.357-360
• /
• 2001

In this paper, we propose and evaluate a new interference cancellation method using low pass filtered data estimation method of the instantaneous decision sawnle obtained from each decision stage. With respect to the convergence to the optimal solution the superiority of the proposed method to parallel interference cancellation (PIC) referred as prevailing techniques is proved by its (asymptotic) spectral radius. Through the simulation under the various environment, we show the performance superiority of the IC scheme using proposed method to the PIC scheme. Furthermore, we show transcendence of the proposed method on the possibility of multirate transmission or multiple power scheduling and of performance in the various traffic environments.