• 대한수학회논문집
• /
• 제10권4호
• /
• pp.849-854
• /
• 1995

The interpolation of scattered data with radial basis functions is knwon for its good fitting. But if data get large, the coefficient matrix becomes almost singular. We introduce different knots and nodes to improve condition number of coefficient matrix. The singulaity of new coefficient matrix is investigated here.

• 전기학회논문지
• /
• 제64권1호
• /
• pp.128-135
• /
• 2015

In this study, we develop the very short-term precipitation forecasting model as well as classifier based on polynomial radial basis function neural networks by using AWS(Automatic Weather Station) and KLAPS(Korea Local Analysis and Prediction System) meteorological data. The polynomial-based radial basis function neural networks is designed to realize precipitation forecasting model as well as classifier. The structure of the proposed RBFNNs consists of three modules such as condition, conclusion, and inference phase. The input space of the condition phase is divided by using Fuzzy C-means(FCM) and the local area of the conclusion phase is represented as four types of polynomial functions. The coefficients of connection weights are estimated by weighted least square estimation(WLSE) for modeling as well as least square estimation(LSE) method for classifier. The final output of the inference phase is obtained through fuzzy inference method. The essential parameters of the proposed model and classifier such ad input variable, polynomial order type, the number of rules, and fuzzification coefficient are optimized by means of Particle Swarm Optimization(PSO) and Differential Evolution(DE). The performance of the proposed precipitation forecasting system is evaluated by using KLAPS meteorological data.

• 한국정보전자통신기술학회논문지
• /
• 제1권3호
• /
• pp.69-76
• /
• 2008

본 논문에서는 Mountain clustering 알고리즘을 이용한 Fuzzy Radial Basis Function Neural Network(FRBFNN)의 규칙 수를 자동생성 방법을 제시한다. FRBFNN은 기존 RBFNN에서 가우시안이나 타원형 형태의 특정 RBF를 사용하는 구조와 달리 클러스터의 중심값과의 거리에 기반을 둔 멤버쉽함수를 사용하여 전반부의 공간 분할 및 활성화 레벨을 결정한다. 또한 분할된 로컬영역에서의 입출력 특성을 나타내는 퍼지규칙의 후반부로서 고차 다항식을 고려하였다. 본 논문에서는 데이터의 밀집도에 기반을 두어 클러스터링을 수행하는 Mountain clustering 알고리즘을 사용하여 적합한 퍼지 규칙(클러스터)의 수와 클러스터의 중심값을 자동적으로 생성하는 방법을 제안한다. Mountain clustering으로부터 구해진 클러스터의 중심은 멤버쉽 값을 결정하는데 사용되며, Weighted Least Square Estimator (WLSE) 알고리즘을 사용하여 후반부 다항식의 계수를 추정한다. 제안된 알고리즘은 비선형 함수 모델링에 적용하여 성능의 우수성과 알고리즘의 타당성을 보인다.

• Bulletin of the Korean Chemical Society
• /
• 제6권5호
• /
• pp.264-266
• /
• 1985

Orthogonalized Slater-type orbitals and Ortho-normalized Slater-type orbitals were derived from the conventional Slater-type orbitals (STO's) by use of the continuous orthonormalizing which is expanded from the Schmidt's orthogonalizing procedure. These orbitals have the merits which STO's have not, such as; they are ortho-normalized each other and have the same numbers of the radial nodes that the real hydrogenlike wave functions do, so that they must be a good basis functions of LCAO MO procedures, i.e., the best approximate representation of SCF method.

• 한국지능시스템학회논문지
• /
• 제7권4호
• /
• pp.74-81
• /
• 1997

본 논문에서는 시그모이드 함수와 방사형 기저 함수 모두를 생성시킬 수 있는 특별한 은닉층 노드를 갖는 투영신경회로망에 대하여 알아롭고 그것을 훈련시키기 위한 진화 학습 기법을 제시한다. 제시된 기법은 신경회로망의 매개변수와 연결 가충치뿐만 아니라, 어떤 목적함수를 나타내기 위한 최적의 은닉층 노드개수 또한 구조 최적화를 위한 진화연산자를 통해 찾아낸다. 각각의 은닉층 노드의 역할은 진화를 거듭하면서 방사형 기저 함수를 나타낼지 시그모이드 함수를 나타낼지 결정된다. 알고리즘을 구현하기 위해서 투영신경회로망은 연결 고리 리스트 자료구조로 나타내었다. 모의 실험에서 기존으 오차역전파에 의한 학습과 구조 성장 방식보다 적은 노드로 투영신경회로망을 훈련시킬 수 있음을 볼수 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제28권3호
• /
• pp.709-720
• /
• 2017

In healthcare and medical research, many important variables have a measurement error such as body mass index and laboratory data. It is also not easy to collect samples of large size because of high cost and long time required to collect the target patient satisfied with inclusion and exclusion criteria. Beside, the demand for solving a complex scientific problem has highly increased so that a semiparametric regression approach could be of substantial value solving this problem. To address the issues of measurement error, small domain and a scientific complexity, we conduct a multivariable Bayesian smoothing under structural measurement error covariate in this article. Specifically we enhance our previous model by incorporating other useful auxiliary covariates free of measurement error. For the regression spline, we use a radial basis functions with fixed knots for the measurement error covariate. We organize a fully Bayesian approach to fit the model and estimate parameters using Markov chain Monte Carlo. Simulation results represent that the method performs well. We illustrate the results using a national survey data for application.

• Journal of applied mathematics & informatics
• /
• 제14권1_2호
• /
• pp.365-376
• /
• 2004

The purpose of this study is to show that the accuracy of the interpolation method can be at least doubled when additional smoothness requirements and boundary conditions are met. In particular, as a basis function, we are interested in using a conditionally positive definite function $\Phi$ whose generalized Fourier transform is of the form $\Phi(\theta)\;=\;F(\theta)$\mid$\theta$\mid$^{-2m}$ with a bounded function F > 0.

• Journal of Computing Science and Engineering
• /
• 제2권1호
• /
• pp.98-108
• /
• 2008

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.163.1-163
• /
• 2001

In this paper, we use time-frequency localization analysis method to analize the target function and the area of the target space. When we analize the function with the time and frequency axis simultaneously, the characteristic of the function is shown more precisely and the area is covered by a certain block. After we analize the target function in the time-frequency space, we can decide the activation functions and compose the hidden layer of the RBFN by choosing the radial basis function which can represent the characteristic of the target function, RBFN made by this method, designs the good structure proper to the target problem because we can decide the number of hidden node first.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1650-1653
• /
• 2002

In this paper, we propose the initial optimized structure of the Radial Basis function Networks that is simple in the part of the structure and fast converges more than neural networks with the analysis method using Time- Frequency Localization. We construct the hidden node with the Radial Basis functions their localization are similar with approximation target function in the plane of the Time and Frequency. We finally make a good decision of the initial structure for function approximation using genetic algorithm