• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권4호
• /
• pp.285-294
• /
• 2007

In this paper, we investigate a novel online estimation algorithm for dynamic Bayesian network(DBN) parameters, given as conditional probabilities. We sequentially update the parameter adjustment rule based on observation data. We apply our algorithm to two well known representations of DBNs: to a first-order Markov Chain(MC) model and to a Hidden Markov Model(HMM). A sliding window allows efficient adaptive computation in real time. We also examine the stochastic convergence and stability of the learning algorithm.

• 한국농공학회논문집
• /
• 제46권5호
• /
• pp.55-60
• /
• 2004

This study was performed to evaluate the early estimation of compressive strength of concrete using mineral admixture by refrigeration curing method. It was a method of early decision for the property of concrete after the curing age 28days through the refrigeration curing at $-18{\pm}3^{\circ}$ for five hours. The test result was fixed connection between the curing age 28days and 31hours by the compressive strength test through the standard curing and refrigeration curing. Accordingly, it can be reduced the mistake of construction work by forecasting the property of concrete through the refrigeration curing.

• 한국통신학회논문지
• /
• 제22권7호
• /
• pp.1534-1542
• /
• 1997

In this paper, we present a performance improvement method for the direction-of-arrival (DOA) estimation algorithm of the narrowband signals incident on a uniform circular array. It is very important to estimate the covariance matrix effectively because the performance of DOA algorithm mainly depends on the exactness of the sampel coveriance matrix which is computed from the received samples of signals. In case of uniform circular array with the even number sensors, the structure of the arrray has a useful geometrical property. Therefore we present the method which can estimate covariance matrix more effectively using this property. The simulation results are shown to demonstrate the superior perfodrmance obtained by the proposed covariance matrix estimation method relative to that of the conventional estimation method.

• Communications for Statistical Applications and Methods
• /
• 제28권3호
• /
• pp.281-294
• /
• 2021

In this paper, we propose an adaptive regression method based on the single-layer neural network structure. We adopt a symmetric activation function as units of the structure. The activation function has a flexibility of its form with a parametrization and has a localizing property that is useful to improve the quality of estimation. In order to provide a spatially adaptive estimator, we regularize coefficients of the activation functions via ℓ₁-penalization, through which the activation functions to be regarded as unnecessary are removed. In implementation, an efficient coordinate descent algorithm is applied for the proposed estimator. To obtain the stable results of estimation, we present an initialization scheme suited for our structure. Model selection procedure based on the Akaike information criterion is described. The simulation results show that the proposed estimator performs favorably in relation to existing methods and recovers the local structure of the underlying function based on the sample.

• Journal of the Korean Data and Information Science Society
• /
• 제16권3호
• /
• pp.657-663
• /
• 2005

Under the minimum risk point estimation formulation of Robbins(1959), we consider the sequential point estimation problem for normal population $N({\theta},\;{\theta})$ with unknown parameter ${\theta}$. In the case of completely unknown ${\theta}$, Stein's(1945) two-stage procedure is known to enjoy the consistency property, but it is not even first-order efficient. In the case when ${\theta}>{\theta}_L\;where\;{\theta}_L(>0)$ is known, the revised two-stage procedure is shown to enjoy all the usual second-order properties.

• Journal of the Korean Statistical Society
• /
• 제30권2호
• /
• pp.281-290
• /
• 2001

Symmetric estimation and recursive mean adjustment are considered to construct tests for the doble unit root hypothesis for both parametric and semiparametric time series models. It is shown that simultaneous application of symmetric estimation and recursive mean adjustment yields the most powerful test. Moreover, size property of the semiparametric test based on the simultaneous application is bet among all semiparametric tests.

• 기술혁신학회지
• /
• 제11권2호
• /
• pp.241-263
• /
• 2008

기술가치평가에서 적절한 할인율의 적용은 가치평가의 신뢰성을 확보하는데 중요한 요소이다. 개별 기술가치평가 할인율은 개별 지식자산에 내재된 위험과 기회를 반영하는 것이기 때문에, 기업가치평가 표준 할인율인 WACC 과 상당히 다르다고 판단된다. 본 연구의 목적은 기술가치평가 할인율 적산모형의 위험구조와 위험프리미엄 추정방법을 제안하는 것이다. 적산모형의 성분은 무위험이자율, 전반적 시장위험프리미엄과 베타, 지식자산위험프리미엄 등 세 가지로 구성하였다. 특히, 본 연구에서 할인율 구성의 핵심인 지식자산위험 수준을 평가할 수 있는 10개 항목을 제안하였고, 위험수준 결과를 위험프리미엄으로 변환하기 위한 추정함수인 선형함수, 자연로그함수, 지수함수 등을 적용하였다. 상기 논리와 결과는 기술가치평가 할인율 추정의 객관성을 개선할 수 있는 실무적 대안이 될 수 있을 것이다.

• 한국정밀공학회지
• /
• 제25권5호
• /
• pp.103-111
• /
• 2008

This study proposes a technique to estimate the material property of a paper by using an experimental methods and commercial CAE software. Under gravitation, if one side of the paper is attached to the ground, the opposite side of paper is largely deformed, and vibrates freely. Since the paper has an orthotropic characteristic due to its treatment, the deformations in two orthogonal directions of the dry paper are different. An experimental method to measure the static deformation of the paper introduces this phenomenon. And dynamic behavior, frequency of free vibration is measured. And then. virtual prototypes that can represent the static and dynamic behavior are modeled by using the commercial CAE software $RecurDyn^{MT}$/MTT3D, which has been widely used by the printer makers. While comparing the deformation and frequency from the experiment and simulation, a design optimization technique in the commercial CAE software of R-INOPL, $RecurDyn^{TM}$/AutoDesign is used to estimate the material property such as Young's modulus, shear modulus and density of the paper.

• Journal of the Korean Statistical Society
• /
• 제29권1호
• /
• pp.9-16
• /
• 2000

This article addresses the problem of maximum likelihood estimation in ARCH regression with lagged dependent variables. Some topics in asymptotics of the model such as uniform expansion of likelihood function and construction of a class of MLE are discussed, and the regularity property of MLE is obtained. The error process here is possibly non-Gaussian.

• 산업경영시스템학회지
• /
• 제32권1호
• /
• pp.130-136
• /
• 2009

Estimation of mortality behavior of a industrial property are useful for calculating depreciation and making management decisions relating to property. The common methods of computing depreciation require an estimation of service life, and some methods may require an estimate of life expectancy. Estimation of service life and life expectancy can be computed from a smoothed and extended life table of original life tables developed through life analysis techniques. Several actuarial techniques are available to construct a life table for depreciation application. Of these methods, the graphic approach and graduation by mathematical formula are the most widely used in the field of depreciation. A commonly used technique of smoothing and of extending the life table is to fit a lows type survivor curves to the observed retirement rate by the least square method. In this paper, estimates of depreciation rate based on directly observed data of the domestic petrochemical equipments are presented.