• 응용통계연구
• /
• 제7권2호
• /
• pp.323-333
• /
• 1994

본 논문에서는 주어진 n개의 적률을 갖는 최적의 확률 밀도 함수를 찾는 문제와 관련된 몇가지 근사 정리들을 제안하고 증명한다. 또한, 이 근사 정리들이 예를 통하여 수행될 것이다.

• 한국재료학회지
• /
• 제29권8호
• /
• pp.477-482
• /
• 2019

The magnetic properties and electronic structures of the B20 crystal structure MnGe and MnSi were investigated using the density functional theory with local density approximation. The low symmetry of the B20 crystal structure plays a very important role to make electromagnetic characteristics of these materials. The important result of the calculations is that it can be observed the appearance of a pair of gaps in the density of states near the Fermi level in both compounds. These features are results from d-band splitting by the low symmetry of the crystal field from B20 crystal structure. It can be seen that there is half-metallic characteristics from the density of states in both compounds. The calculation shows that the value of magnetic moment of MnGe is 5 times bigger than that of MnSi even though they have same crystal structure. The electronic structures of paramagnetic case have a very narrow indirect gap just above the Fermi level in both compounds. These gaps acquire some significance in establishing the stability of the ferromagnetic states within the local density approximation. Calculation shows that the Mn 3d character dominates the density of states near the Fermi level in both materials.

• 응용통계연구
• /
• 제22권6호
• /
• pp.1345-1353
• /
• 2009

We introduce a simple methodology, so-called generalized gamma-polynomial approximation, based on moment-matching technique to approximate survival and hazard functions in the context of parametric survival analysis. We use the generalized gamma-polynomial approximation to approximate the density and distribution functions of convolutions and finite mixtures of random variables, from which the approximated survival and hazard functions are obtained. This technique provides very accurate approximation to the target functions, in addition to their being computationally efficient and easy to implement. In addition, the generalized gamma-polynomial approximations are very stable in middle range of the target distributions, whereas saddlepoint approximations are often unstable in a neighborhood of the mean.

• Journal of Applied and Pure Mathematics
• /
• 제4권3_4호
• /
• pp.185-209
• /
• 2022

Here we exhibit multivariate quantitative approximations of Banach space valued continuous multivariate functions on a box or ℝ^N, N ∈ ℕ, by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature type neural network operators. We treat also the case of approximation by iterated operators of the last four types. These approximations are achieved by establishing multidimensional Jackson type inequalities involving the multivariate modulus of continuity of the engaged function or its high order Fréchet derivatives. Our multivariate operators are defined by using a multidimensional density function induced by the generalized symmetrical sigmoid function. The approximations are point-wise and uniform. The related feed-forward neural network is with one hidden layer.

• Journal of Radiation Protection and Research
• /
• 제34권4호
• /
• pp.155-164
• /
• 2009

In this paper, we used computerized glow curve deconvolution (CGCD) software with several models for the simulation of a TL glow curve which was used for analysis. By using the general approximation plus model, parameters values of the glow curve were analyzed and compared with the other models parameters (general approximation, mixed order kinetics, general order kinetics). The LiF:Mg,Cu,Si and the LiF:Mg,Cu,P material were used for the glow curve analysis. And we based on figure of merits (FOM) which was the goodness of the fitting that was monitored through the value between analysis model and TLD materials. The ideal value of FOM is 0 which represents a perfect fit. The main glow peak makes the most effect of radiation dose assessment of TLD materials. The main peak of the LiF:Mg,Cu,Si materials has a intensity rate 80.76% of the whole TL glow intensity, and that of LiF:Mg,Cu,P materials has a intensity rate 68.07% of the whole TL glow intensity. The activation energy of LiF:Mg,Cu,Si was analyzed as 2.39 eV by result of the general approximation plus(GAP) model. In the case of mixed order kinetics (MOK), the activation energy was analyzed as 2.29 eV. The activation energy was analyzed as 2.38 eV by the general order kinetics (GOK) model. In the case of LiF:Mg,Cu,P TLD, the activation energy was analyzed as 2.39 eV by result of the GAP model. In the case of MOK, the activation energy was analyzed as 2.55 eV. The activation energy was analyzed as 2.51 eV by the GOK model. The R value means different ratio of retrapping-recombination. The R value of LiF:Mg,Cu,Si TLD main peak analyzed as $1.12\times10^{-6}$ and $\alpha$ value analyzed as $1.0\times10^{-3}$. The R of LiF:Mg,Cu,P TLD analyzed as $7.91\times10^{-4}$, the $\alpha$ value means different ratio of initial thermally trapped electron density-initial trapped electron density (include thermally disconnected trap electrons density). The $\alpha$ value was analyzed as $9.17\times10^{-1}$ which was the difference from LiF:Mg,Cu,Si TLD. The deep trap electron density of LiF:Mg,Cu,Si was higher than the deep trap electron density of LiF:Mg,Cu,P.

• Communications for Statistical Applications and Methods
• /
• 제21권2호
• /
• pp.115-124
• /
• 2014

In this paper we derive a Berry-Esseen type bound for the kernel density estimator of a random left truncated model, in which each datum (Y) is randomly left truncated and is sampled if $Y{\geq}T$, where T is the truncation random variable with an unknown distribution. This unknown distribution is estimated with the Lynden-Bell estimator. In particular the normal approximation rate, by choice of the bandwidth, is shown to be close to $n^{-1/6}$ modulo logarithmic term. We have also investigated this normal approximation rate via a simulation study.

• Journal of the Korean Statistical Society
• /
• 제10권
• /
• pp.140-144
• /
• 1981

This paper approximates to a kernel density estimate by a truncated series of expansion involving Hermite polynomials, since this could ease the computing burden involved in the kernel-based density estimation. However, this truncated series may give a multimodal estimate when we are estiamting unimodal density. In this paper we will show a way to insure the truncated series to be positive and unimodal so that the approximation to a kernel density estimator would be maeningful.

• 한국통신학회논문지
• /
• 제31권4C호
• /
• pp.310-317
• /
• 2006

본 논문에서는 체크 노드 분할에 의한 low-density parity-check(LDPC) 부호의 새로운 직렬 메시지 전달 복호 알고리즘을 제안한다. 이 새로운 복호 알고리즘은 특히 적은 반복 횟수에 대하여 기존의 메시지 전달 복호 알고리즘의 비트 오율(BER) 성능보다 더 우수한 성능을 보인다. 체크 노드의 분할된 부분 집합의 개수가 증가함에 따라 비트 오율 성능이 보다 좋아진다는 사실을 분석적 결과로 확인할 수 있다. 또한 가우시안 근사화를 이용한 밀도 진화를 이용하여 변수 노드에서 메시지들의 평균값에 대한 재귀 방정식을 유도하고, 모의 실험을 이용하여 분석적인 결과를 검증하였다.

• Communications for Statistical Applications and Methods
• /
• 제17권3호
• /
• pp.367-376
• /
• 2010

최근 확산모형의 추정을 위한 매우 다양한 방법론들이 제시되고 연구 되어 왔다. 본 연구에서는 제안된 확산모형의 추정 방법 중에서, 안장점근사법을 이용한 확산모형의 모수 추정방법에 대하여 살펴보게 되고, 가장 단순한 형태의 안장점근사법인 단일항 안장점근사법의 사용을 제안하게 된다. 단일항 안장점근사법은 오일러근사법과 마찬가지로 계산속도가 빠르고, 다양한 모형에 적용이 가능하면서도 최대우도추정량과 마찬가지로 성능이 우수한 특성을 갖고 있음을 살펴보게 된다. OU 확산모형을 대상으로 한 시뮬레이션 연구를 통하여 단일항 안장점근사를 이용한 추정량과 다른 추정량들과의 성질을 비교한다.

• Journal of applied mathematics & informatics
• /
• 제27권5_6호
• /
• pp.1087-1095
• /
• 2009

In this paper, we study approximation method from scattered data to the derivatives of a function f by a radial basis function $\phi$. For a given function f, we define a nearly interpolating function and discuss its accuracy. In particular, we are interested in using smooth functions $\phi$ which are (conditionally) positive definite. We estimate accuracy of approximation for the Sobolev space while the classical radial basis function interpolation applies to the so-called native space. We observe that our approximant provides spectral convergence order, as the density of the given data is getting smaller.