• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집A
• /
• pp.655-660
• /
• 2000

This paper presents the construction of consistent coefficient matrix elements for jointed structures using the reduction of flexibility and mass matrices. The reduced flexibility coefficient matrix hat little structural complexity than Guyan's stiffness matrix reduction since the only element of the original matrix, corresponding to the selected nodal degrees of freedom, contributes. The proposed method was applied to building equivalent coefficient matrices for a clamp jointed structure in finite element modal analysis of a cantilevered beam. The theoretical analysis results were compared with those experimental modal analysis, Comparison of both shows good agreement each other.

• Communications for Statistical Applications and Methods
• /
• 제6권3호
• /
• pp.667-676
• /
• 1999

We investigate the effects of omission of initial observations in each individuals in the panel data regression model when the disturbances follow a serially correlated one way error components. We show that the first transformed observation can have a relative large hat matrix diagonal component and a large influence on parameter estimates when the correlation coefficient is large in absolute value.

• 한국지구물리탐사학회:학술대회논문집
• /
• 한국지구물리탐사학회 2003년도 Proceedings of the international symposium on the fusion technology
• /
• pp.402-409
• /
• 2003

Inversion of traveltime requires an efficient algorithm for computing the traveltime as well as its $Frech\hat{e}t$ derivative. We compute the traveltime of the head waves using the damped wave solution in the Laplace domain and then present a new algorithm for calculating the $Frech\hat{e}t$ derivative of the head wave traveltimes by exploiting the numerical structure of the finite element method, the modem sparse matrix technology, and SWEET algorithm developed recently. Then, we use a properly regularized steepest descent method to invert the traveltime of the Marmousi-2 model. Through our numerical tests, we will demonstrate that the refraction tomography with large aperture data can be used to construct the initial velocity model for the prestack depth migration.

• Journal of the Korean Statistical Society
• /
• 제15권2호
• /
• pp.131-142
• /
• 1986

By using the tool for finding influential cases in regrssion, we investigate teh properties of three types of diagonal elements of the hat matrix in central designs. From thses results, we determine the experimental points at axes ad teh number of replicates as the center and the otherpoints so that the experimental points give approximatly same influences to estimatoe teh response surface.

• Journal of the Korean Data and Information Science Society
• /
• 제6권1호
• /
• pp.63-71
• /
• 1995

We have consider the study of local influence for smoothing parameter estimates in spline regression model with heteroscedasticity. Practically, generalized cross-validation does not work well in the presence of heteroscedasticity. Thus we have proposed the local influence measure for generalized cross-validation estimates when errors are heteroscedastic. And we have examined effects of diagnostic by above measures through Hyperinflation data.

• 한국수자원학회논문집
• /
• 제32권6호
• /
• pp.657-664
• /
• 1999

본 논문은 이상호와 이길성(1995)에 의해서 제안된 LRCS(Linear Reservoir and Channel System) 강우-유출 모형의 기본 이론을 소개하였고, 모형의 민감도 분석 및 보정과정에서 나타나는 목적함수에 따른 모형 출력의 변화를 파악하고자 하였다. 보정시 매개변수 영향성 분석을 위한 "hat" 행렬과 영향성 척도의 사용을 제안하였고, 매개변수 추정시 오차 전파에 따른 모형 출력의 변화 정도 및 모형 예측치 분산과 매개변수 변화에 따른 모형 출력의 민감도와의 관련성을 조사하였다. 민감도계수와 hi의 대각 요소와 Di 값의 분석으로 매개변수 추정치의 정확성을 알 수 있었다.을 알 수 있었다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권2호
• /
• pp.549-557
• /
• 2016

In this paper we propose multiclassification method for large data sets by ensembling least squares support vector machines (LS-SVM) with principal components instead of raw input vector. We use the revised one-vs-all method for multiclassification, which is one of voting scheme based on combining several binary classifications. The revised one-vs-all method is performed by using the hat matrix of LS-SVM ensemble, which is obtained by ensembling LS-SVMs trained using each random sample from the whole large training data. The leave-one-out cross validation (CV) function is used for the optimal values of hyper-parameters which affect the performance of multiclass LS-SVM ensemble. We present the generalized cross validation function to reduce computational burden of leave-one-out CV functions. Experimental results from real data sets are then obtained to illustrate the performance of the proposed multiclass LS-SVM ensemble.

• Structural Engineering and Mechanics
• /
• 제13권3호
• /
• pp.277-298
• /
• 2002

In this study, free vibration analysis of Reissner plates on Pasternak foundation is carried out by mixed finite element method based on the G$\hat{a}$teaux differential. New boundary conditions are established for plates on Pasternak foundation. This method is developed and applied to numerous problems by Ak$\ddot{o}$z and his co-workers. In dynamic analysis, the problem reduces to the solution of a standard eigenvalue problem and the mixed element is based upon a consistent mass matrix formulation. The element has four nodes and bending and torsional moments, transverse shear forces, rotations and displacements are the basic unknowns. The element performance is assessed by comparison with numerical examples known from literature. Validity limits of Kirchhoff plate theory is tested by dynamic analysis. Shear locking effects are tested as far as $h/2a=10^{-6}$ and it is observed that REC32 is free from shear locking.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.561-567
• /
• 2010

Multiclassification is typically performed using voting scheme methods based on combining a set of binary classifications. In this paper we use multiclassification method with a hat matrix of least squares support vector machine (LS-SVM), which can be regarded as the revised one-against-all method. To tackle multiclass problems for large data, we use the $Nystr\ddot{o}m$ approximation and the quadratic Renyi entropy with estimation in the primal space such as used in xed size LS-SVM. For the selection of hyperparameters, generalized cross validation techniques are employed. Experimental results are then presented to indicate the performance of the proposed procedure.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제36권3호
• /
• pp.439-467
• /
• 2022

미래 사회에는 지식뿐만 아니라 창의성과 협동심, 융합적 사고 등을 포함하는 다양한 역량이 필요하다. 본 연구는 중요한 수학 교과 역량인 수학 문제해결력, 의사소통 능력 등의 함양을 기대하며 수학 정보과학 융합을 위한 프로그램을 개발하였다. 선행지식이 크게 요구되지 않고, 일상언어와 쉽게 접할 수 있는 도구만으로 동기유발이 가능하며 다자간 협력이 필수적인 창의적 문제해결 활동 기반 프로그램이다. 활동의 참가자 수가 증가함에 따라 수학의 유용성과 엄밀성을 경험할 수 있으며, 이론적 원리는 유한체 위에서의 행렬 이론을 바탕으로 한다. 또한 정보과학에서 주요 주제 중 하나인 오류정정코드와의 관련성을 강조할 수 있도록 구성하였다. 본 프로그램의 실세계 맥락이 수학적 의사소통 능력의 함양과 수학의 가치 경험 기회 제공에 도움이 되기를 바라고, 코딩을 수반하지 않는다는 점에서 교사들의 접근성이 높기를 기대한다.