• Journal of Mechanical Science and Technology
• /
• v.14 no.10
• /
• pp.1041-1050
• /
• 2000

In this paper the effect of specimen thickness on fatigue crack growth with the spatial distribution of material properties is presented. Basically, the material resistance to fatigue crack growth is treated as a spatial stochastic process, which varies randomly on the crack surface. The theoretical autocorrelation functions of fatigue crack growth resistance with specimen thickness are discussed for several correlation lengths. Constant ${\Delta}K$ fatigue crack growth tests were also performed on CT type specimens with three different thicknesses of BS 4360 steel. Applying the proposed stochastic model and statistical analysis procedure, the experimental data were analyzed for different specimen thicknesses for determining the autocorrelation functions and probability distributions of the fatigue crack growth resistance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.238-243
• /
• 2006

베이지안 네트워크는 주어진 변수들 사이의 확률적 의존성을 분석하는 데에 널리 사용되어지고 있는 모델이다. 이러한 베이지안 네트워크의 활용에 있어서 베이지안 네트워크의 확실성을 분석하는 방법의 필요성이 대두되어지고 있다. 특히 규모가 큰 베이지안 네트워크 모델을 특정하는 상황에서 주어질 수 있는 학습 데이터의 수가 제한되는 경우나, 주된 관심사가 베이지안 네트워크의 일부 부분에 한정되는 경우에 베이지안 네트워크의 확실성에 대한 분석은 유용하게 사용될 수 있다. 본 논문에서는, 베이지안 네트워크에 존재할 수 있는 불확실성을 언급한 후, 베이지안 네트워크 내의 변수들이 갖는 확률분포의 분산을 이용해 베이지안 네트워크의 불확실성을 정의하는 방법을 제안한다. 간단한 베이지안 네트워크의 예시 모델을 이용하여 제안된 베이지안 네트워크의 불확실성 분석 방법이 유용할 수 있음을 보인다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.278-278
• /
• 2000

In this paper, we introduce a new genetic reordering operator based on the concept of schema to solve optimization problems such as the Traveling Salesman Problem(TSP) and maximizing or minimizing functions. In particular, because TSP is a well-known combinational optimization problem andbelongs to a NP-complete problem, there is huge solution space to be searched. For robustness to local minima, the operator separates selected strings into two parts to reduce the destructive probability of good building blocks. And it applies inversion to the schema part to prevent the premature convergence. At the same time, it searches new spaces of solutions. Additionally, the non-schema part is applied to inversion for robustness to local minima. By doing so, we can preserve diversity of the distributions in population and make GA be adaptive to the dynamic environment.

• Communications for Statistical Applications and Methods
• /
• v.20 no.6
• /
• pp.439-454
• /
• 2013

This study presents a Bayesian multiple change-point detection approach to segment and classify the observations that no longer come from an initial population after a certain time. Inferences are based on the multiple change-points in a sequence of random variables where the probability distribution changes. Bayesian multiple change-point estimation is classifies each observation into a segment. We use a truncated Poisson distribution for the number of change-points and conjugate prior for the exponential family distributions. The Bayesian method can lead the unsupervised classification of discrete, continuous variables and multivariate vectors based on latent class models; therefore, the solution for change-points corresponds to the stochastic partitions of observed data. We demonstrate segmentation with real data.

• Journal of Hydrogen and New Energy
• /
• v.12 no.1
• /
• pp.51-63
• /
• 2001

In this paper molecular dynamics simulations were employed to investigate the structural and dynamic properties of hydrogen ions impacted on the Ni (100) surface with the $45^{\circ}$ incident angle. The initial kinetic energies of the hydrogen ion range from 100 to 1,600 eV. Together with the trajectory visualization of hydrogen ions, we computed scattering and penetration yields, mean energies and angles, and probability and energy distributions as a function of longitudinal and azimuthal directions. In the case of lower energy scattering ions, the multiple collision effects were found to be important to the third layers or lower. For higher energy penetrating ions, compared with the normal incident angle, it was significant the effective channeling effects through the Ni layers and the angle dependencies were indicated both in the longitudinal and the azimuthal angle directions.

• The Korean Journal of Applied Statistics
• /
• v.9 no.1
• /
• pp.165-177
• /
• 1996

It is often needed to generate random numbers from truncated t-distributions to carry out Bayesian inferences, especially in Monte Carlo integration for estimation of posterior densities of constrained parameters. However, when the restricted area is an extreme tail area with a small probability most existing random generation methods are not efficient. In this paper, we propose an efficient acceptance-rejection method to generate random numbers from extreme tail areas of a t-distribution. Using some simulation results, we compare the proposed algorithm with other popular methods.

• The Korean Journal of Applied Statistics
• /
• v.9 no.1
• /
• pp.153-164
• /
• 1996

We discussed estimation of parameters using Gibbs sampler under order restriction on the parameters. Two well-knwon probability models, ordered exponential family and binomial distribution, are considered. We derived full conditional distributions(FCD) and also used one-for-one sampling algorithm to sample from the FCD's under order restrictions. Finally through two real data sets we compared three kinds of estimators; isotonic regression estimator, isotonic Bayesian estimator and the estimator using Gibbs sampler.

• Earthquakes and Structures
• /
• v.10 no.6
• /
• pp.1291-1314
• /
• 2016

The paper presents the development of experimental fragility functions for exterior RC beam-column connections based on results obtained from extensive testing carried out in the present study. Three typical types of seismically deficient beam-column connections, which are commonly prevalent in Indian sub-continent, were considered. These specimens were tested under cyclic displacement histories with different characteristics to induce different damage states. Rehabilitation specific fragility functions for damaged specimens were developed considering drift angle as a demand parameter. Four probability distributions were fit to the data and suitability of each distribution was evaluated using standard statistical method. Specimens with different damage states were rehabilitated appropriately and rehabilitated specimens were tested under similar displacement histories. Fragility functions for rehabilitated specimens have also been developed following similar procedure. Comparison of fragility functions for both original and rehabilitated specimens for each rehabilitation method showed close agreement, which establishes the effectiveness of the adopted rehabilitation strategies and hence would provide confidence in field application.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.34
• /
• pp.61-67
• /
• 1995

Through the model presented in this paper, we study on the depletion of stock taking place due to random loss of items as well as random demand, under the assumption that the distributions of demand are independent of those of loss, and both of them are identical, and that life time distribution of each item is negative exponential. The steady state probability distribution of the stock level assuming instantaneous delivery of order under (s, S) inventory policy. Also we have derived total expected cost expression with loss cost. The results of sensitive analysis show that the effect of loss rate is substantial on the total cost and optimal value of inventory level.

• Kyungpook Mathematical Journal
• /
• v.53 no.1
• /
• pp.105-116
• /
• 2013

Based on the concept of the folding, the folding in X-direction and in Y-direction are defined and denoted by the X-Folding and the Y-Folding respectively. We consider a random variable X which follows a rectangular distribution "R(a, b) distribution" with two parameters a, b. This paper aims to apply the folding on the unit area P($a{\leq}X{\leq}b$) and also to study the proposed folding in each direction for R(a, b) distribution and the generated family of the corresponding constructed rectangular probability distributions. Some main properties of this family are reviewed. According to the proposed folding, we derive and discuss some important corresponding functions in closed forms.