• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• Communications for Statistical Applications and Methods
• /
• 제27권1호
• /
• pp.129-140
• /
• 2020

In this paper, we introduce an efficient algorithm for the non-convex penalized multinomial logistic regression that can be uniformly applied to a class of non-convex penalties. The class includes most non-convex penalties such as the smoothly clipped absolute deviation, minimax concave and bridge penalties. The algorithm is developed based on the concave-convex procedure and modified local quadratic approximation algorithm. However, usual quadratic approximation may slow down computational speed since the dimension of the Hessian matrix depends on the number of categories of the output variable. For this issue, we use a uniform bound of the Hessian matrix in the quadratic approximation. The algorithm is available from the R package ncpen developed by the authors. Numerical studies via simulations and real data sets are provided for illustration.

• 대한기계학회논문집A
• /
• 제33권10호
• /
• pp.1144-1150
• /
• 2009

This paper investigates the feasibility of the Bayesian discrete time approximation method to estimate the parameters of Weibull distributions of failures for two non-identical components connected in series system. A Bayesian model based on the discrete time approximation method is formulated to infer the Weibull parameters of two non-identical components with the failure data of the virtual tests. The study of this paper comes to a conclusion that the method is feasible only for some special cases under the given constraints on the concerned parameters.

• 전자공학회논문지A
• /
• 제29A권2호
• /
• pp.1-7
• /
• 1992

A consideration for image improvement under the Born approximation in the microwave diffraction tomography is suggested by using a projection function. The limiting factors in the degrading reconstructed image due to Born approximation are identified in terms of projection function and its modification is suggested to improve the degraded image based upon the Born approximation. In order to verify the proposed method, the reconstructed images are shown by computer simulation from the back-scattered data of angular and frequency diversity for squared dielectric cylinder with a various relative dielectric constant. From simulation results, it was shown that the proposed method can lead to a fairly good improved image for a severe degraded one irrespective of homogeneous and inhomogeneous dielectric object. In the future, the analysis on the limitation of this method should be considered and performed by means of more quantitative method.

• 대한전자공학회논문지
• /
• 제27권3호
• /
• pp.47-53
• /
• 1990

곡선의 다각형 근사화 방법은 화상분석 또는 데이타 압축등에 많이 사용된다. 다각형 근사화 방법으로, 적은 break point수를 갖고, Sequential Process로 결과를 얻을 수 있는 Cone intersection 방법이 있다. 여기서는 화소간의 거리가 일정한 디지탈 곡선의 경우, 종래의 cone intersection 방법을 정수계산을 이용하여 속도를 향상시키는 방법을 제안한다.

• 응용통계연구
• /
• 제27권5호
• /
• pp.809-818
• /
• 2014

다변량 왜정규분포는 다변량 정규분포를 포함하는 분포로 최근 많은 응용분야에서 활용되고 있다. 본 논문에서는 다변량 왜정규분포를 기반으로 하는 선형결합통계량의 분포함수에 대한 안장점근사를 다루었다. 이는 단변량 왜정규분포 기반 표본평균에 대한 Na와 Yu (2013)의 결과를 선형결합 및 다변량의 경우로 확장한 것이다. 모의실험과 실제자료분석을 통해 제안된 근사법의 유용성과 정확도를 확인하였다.

• Journal of applied mathematics & informatics
• /
• 제27권3_4호
• /
• pp.463-473
• /
• 2009

A family of quasi-interpolatory wavelet system was introduced in [10], extending and unifing the biorthogonal Coiffman wavelet system. The corresponding refinable functions and wavelets have vanishing moment of a certain order (say, L), which is a key property for data representation and approximation. One of main advantages of this wavelet systems is that we can get optimal smoothness in the sense of smoothing factors in the scaling filters. In this paper, we first discuss the biorthogonality condition of the quisi-interpolatory wavelet system. Then, we study the properties of the scaling and wavelet filters, related to the polynomial reproduction and the vanishing moment respectively, which in fact determines the approximation orders of biorthogonal projections. In addition, we discuss the approximation orders of the wavelet projections.

• 대한조선학회논문집
• /
• 제35권4호
• /
• pp.118-125
• /
• 1998

본 연구는 B-spline 근사법과 유전자 알고리즘을 이용하여 기하학적 경계 조건-양끝점의 위치 벡터 및 접선 벡터-을 만족하는 혼합 곡선 근사법에 의한 선형 표현을 내용으로 한다. B-spline 근사법을 이용하여 선형을 표현하고, 이들 곡선을 제어하는 조정점들이 기하학적 경계조건을 만족하도록 유전자 알고리즘으로 조정한다. 이 방법은 선형 생성시 순정 작업을 동시에 수행하므로 효율적인 선형 설계를 가능하게 한다.

• 한국음향학회지
• /
• 제24권1호
• /
• pp.1-10
• /
• 2005

본 논문에서는 이동하는 광대역 음원의 위치추정에 적합한 높은 분해능을 가지는 광대역LPA (local polynomial approximation) 빔형성기법을 제안한다. 제안한 기법은 여러 개의 데이터 단편으로부터 구하는 공분산행렬 대신, 하나의 데이터 단편의 여러 개 주파수 성분으로부터 얻은 조향 공분산행렬을 이용하는 STMV(steered minimum variance) 기법을 LPA 빔형성기법에 적용하였다. STMV 기법의 센서가중벡터를 이용하여 LPA 가격함수를 구성하였으며 이를 최대화 시키는 방위각과 각속도를 2차원 탐색을 통하여 추정함으로써 높은 방위각 분해능을 가지도록 하였다. 모의신호와 실제 해상 실험 데이터를 이용하여 제안한 기법의 성능을 기존의 기법과 비교, 분석 하였다

• 한국CDE학회논문집
• /
• 제10권5호
• /
• pp.314-327
• /
• 2005

This paper describes the volumetric data modeling and analysis methods that employ volumetric NURBS or VNURBS that represents heterogeneous objects or fields in multidimensional space. For volumetric data modeling, we formulate the construction algorithms involving the scattered data approximation and the curvilinear grid data interpolation. And then the computational algorithms are presented for the geometric and mathematical analysis of the volume data set with the VNURBS model. Finally, we apply the modeling and analysis methods to various field applications including grid generation, flow visualization, implicit surface modeling, and image morphing. Those application examples verify the usefulness and extensibility of our VNUBRS representation in the context of volume modeling and analysis.