• Journal of Hydrospace Technology
• /
• v.1 no.1
• /
• pp.41-56
• /
• 1995

Flew control devices, such as flow liners, are frequently introduced in a cavitation tunnel in order to reduce the tunnel blockage effect, when a three-dimensional wake distribution is simulated using a complete ship model or a dummy model. In order to estimate the tunnel wall effect and to evaluate the effect of flow liners on the simulated wake distribution, a surface panel method is adopted for the calculation of the flow around a ship model and flow liners installed in a rectangular test section off cavitation tunnel. Calculation results on the Sydney Express ship model show that the tunnel wall effect on the hull surface pressure distribution is negligible for less than 5% blockage and can be appreciable for more than 20% blockage. The flow liners accelerate the flow near the afterbody of the ship model, so that the pressure gradient there becomes more favorable and accordingly the boundary layer thickness would be reduced. Since the resulting wake distribution is assumed to resemble the full scale wake, flow liners can also be used to simulate an estimated full scale wake without modifying the ship model. Boundary taper calculation should be incorporated in order to correlate the calculated wake distribution with the measured one.

• Communications for Statistical Applications and Methods
• /
• v.1 no.1
• /
• pp.52-56
• /
• 1994

When we have an i.i.d. sample of size n from a continuous distribution, the distribution truncated on the left at the rth order statistic plays an important role in the theoretical analysis of the Type 2 censored data. The charaterization of distributions by the average of the conditional expectation and the average of the conditional information concerning the truncated distribution is studied here.

• Journal of the Korean Statistical Society
• /
• v.19 no.2
• /
• pp.139-144
• /
• 1990

For the first-order bilinear time series model $X_t = aX_{t-1} + e_i + be_{t-1}X_{t-1}$ where ${e_i}$ is a sequence of independent normal random variables with mean 0 and variance $\sigma^2$, the asymptotic distribution of sample autocarrelation function is obtained and shown to follow a normal distribution. The variance of the asymptotic distribution is of a complicated form and hence a bootstrap estimate of the variance is proposed for large sample inference. This result can be used to distinguish between different bilinear models.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.14 no.24
• /
• pp.149-154
• /
• 1991

The one of the important problems in the design of queueing systems is the decision of the order of service stations. The object of this problem is the decision of the order that minimizes the expected sojourn time per customer in the given arrival process and service time distributions. In this paper, the tandem queueing system in series is studied with the emphasis on the optimal order of the tandem queueing system which has three stations with single servers. In one system, customers arrive at the first station with Poisson process. This system is composed of service stations with a constant, a general distribution and a Exponential distribution is studied. To select the optimal order after the orders of each pair of two stations is decided, it is compared the two orders of system. With this results, total expected delay of the systems which has three stations is compared. The result is the best that service station with constant time is on the first place, then the service station with general distribution and the service station with Exponential distribution is followed. And the other system is consist of service stations with a constant and two probabilistic distributions. In this case, two probabilistic distributions has a non-overlapping feature. It is the optimal order that the service station with constant time is on the first place then the service station with longer service time and the service station with shorter service time is followed.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.11
• /
• pp.1417-1423
• /
• 1999

Distribution system can experience the diverse events instantly and permanently. Also, it can experience high impedance fault or line drop under unbalanced situation, Accordingly, it is difficulty to identify the fault location because that data collected from distribution SCADA system may include uncertainty. This paper proposes an expert system, which can infer the faulted location the quickly and exactly for the diverse events in the distribution system. The expert system utilizes distribution SCADA function and collected data, especially, the monitoring mechanism for the normal open position switches is adopted newly in order to recognize the fault type exactly. Also, automated fault location diagnosis strategy is developed in order to minimize the spreading effect of fault obtained from the error of the system operator. The proposed strategy is implemented in C language. Especially, in order to prove the effectiveness of proposed expert system, the several scenario is simulated for the given model system. The real feeders are selected as model system for the simulation.

• Journal of KIISE:Software and Applications
• /
• v.27 no.8
• /
• pp.855-863
• /
• 2000

Although Behavior-Knowledge Space (BKS) method, one of well known decision combination methods, does not need any assumptions in combining the multiple experts, it should theoretically build exponential storage spaces for storing and managing jointly observed K decisions from K experts. That is, combining K experts needs a (K+1)st-order probability distribution. However, it is well known that the distribution becomes unmanageable in storing and estimating, even for a small K. In order to overcome such weakness, it has been studied to decompose a probability distribution into a number of component distributions and to approximate the distribution with a product of the component distributions. One of such previous works is to apply a conditional independence assumption to the distribution. Another work is to approximate the distribution with a product of only first-order tree dependencies or second-order distributions as shown in [1]. In this paper, higher order dependency than the first-order is considered in approximating the distribution and a dependency-based framework is proposed to optimally approximate the (K+1)st-order probability distribution with a product set of dth-order dependencies where ($1{\le}d{\le}K$), and to combine multiple experts based on the product set using the Bayesian formalism. This framework was experimented and evaluated with a standardized CENPARMI data base.

• Journal of Distribution Research
• /
• v.1 no.1
• /
• pp.239-258
• /
• 1996

This study deals with the measurement of relational norms, a safeguard for sustained exchange relationshipsim marketing channel systems. Here, the relational norm items are hypothesized to have a second-order factor model, in which mine observed items originate from the three first-order factors and the first order factors in turn originate from a second-order factor. The three first order construe comprising a higher order norm are mutuality(equity in the distribution of benefits and burdens over the course of the exchange on a long term basis), flexibility(expectation of friendly adaption for possible circumstance changes), and solidarity (the degree to which the preservation of the unique and continuing relationship is internalized by the exchange partners as being important in and of itself). 113 research questionnaires are obtained from four industries such as construction, telecommunication, iron, and electric ＆ electronic industries, Reliability and nomological. discriminant validity are tested, and in using the confirmatory factor analysis of Lisrel 7.16, and the chi-square difference test it is tested which has a better satisfactory fit to the data, the first-order model or the second-order one. The results of this study indicates that relational norms have a second order construct. In the electric and electronic industry the model as a while has a satisfactory fit to the data and the relevant first- and second-order factor loading to the mutuality is not significant. Same Results are happened to the flexibility in the telecommunication industry and to the mutuality and flexibility in the inn industry. In sum, the model lends support to our construct, but it is difficult to apply the measurement model to all kinds of industries.

• Wind and Structures
• /
• v.19 no.4
• /
• pp.371-387
• /
• 2014

Probability plotting positions are popular and used as the basis for distribution fitting and for inspecting the quality of the fit because of its simplicity. The plotting positions that lead to excellent approximation to the mean of the order statistics should be used if the objective of the fitting is to estimate quantiles. Since the mean depends on the sample size and is not amenable for simple to use closed form solution, many plotting positions have been presented in the literature, including a new plotting position that is derived based on the weighted least-squares method. In this study, the accuracy of using the new plotting position to fit the Gumbel distribution for estimating quantiles is assessed. Also, plotting positions derived by fitting the mean of the order statistics for all ranks is proposed, and an approximation to the covariance of the order statistics for the Gumbel (and Weibull) variate is given. Relative bias and root-mean-square-error of the estimated quantiles by using the proposed plotting position are shown. The use of the proposed plotting position to estimate the quantiles of annual maximum wind speed is illustrated.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.171-178
• /
• 2013

In this paper, we develop noninformative priors for the generalized Pareto distribution when the parameter of interest is the shape parameter. We developed the first order and the second order matching priors.We revealed that the second order matching prior does not exist. It turns out that the reference prior satisfies a first order matching criterion, but Jeffrey's prior is not a first order matching prior. Some simulation study is performed and a real example is given.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 1999.10a
• /
• pp.212-219
• /
• 1999

In this paper we investigated an applicability of earthquake regulations for seismic-isolated building structures which has been used currently and propose an efficient method for vertical distribution of seismic loads. The distribution of force is revised in UBC-94 as vertical distribution of force of UBC(Uniform Building Code)-91 is not sufficient safety but its distribution is inefficient expensive because of similar expression to fixed-based structures. In order to overcome this difficulties improved vertical distribution to fixed-based structures. In order to overcome this difficulties improved vertical distribution of seismic load is proposed using two degrees-of-freedom isolated structures and mode shape of fixed-based structures. Efficiency and accuracy of the proposed method are verified through analysis of an example structures with moment resisting frame and shear walls so this study approximate to dynamic analysis results in each case.