• Journal of Korean Society of Transportation
• /
• v.22 no.6
• /
• pp.145-157
• /
• 2004

Microscopic freeway simulation models project the uncertain values of performance measures for subject traffic conditions by explaining drivers' driving behavior with lane changing and car-following models. However, the existing lane changing models are limited to gap acceptance oriented passive behavior of drivers and not able to capture more-or-less aggressive driving behavior(e.g. cut-in lane changing) ordinarily obseved in field. This paper suggests the definition of cut-inlane changing and presents its characteristics based on the findings from two different freeway on- and off-ramp sections. In addition, this paper proposes a new lane changing model capable of handling both passive and active drivers' driving behavior for better performance of simulations. The proposed lane changing model was tested with Hanyang Simulatin (HYTSIM), a microscopic freeway simulation program developed for this study. The HYTSIM simulation results reflecting the performance of the proposed lane changing model were compared against the field data. The test results showed that the distribution of gaps collected when vehicles change lanes were statistically identical to the field data at 95% confidence level.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.697-700
• /
• 2006

저수시 하천유량(Low Streamflow)의 추정은 하천의 수질관리, 용수공급계획, 댐 방류계획등의 수자원관리에 있어서 매우 중요한 부분이다. 이러한 중요성에 따라 Vogel과 Kroll (1989)은 저수시 하천유량을 추정하기 위한 여러 가지 확률분포함수를 제안하였다. 가장 흔히 제안되어지는 이변수 확률분포(Two-Parameter Distribution)로는 Lognormal 분포와 Weibull 분포가 있으며 이와 더불어 Three-Parameter Lognormal, Three-Parameter Weibull, Log Person Type Ⅲ 분포도 널리 사용되어진다. 그러나 이러한 여러 가지 확률 분포함수 중에서 가장 적절한 확률분포의 선택은 저수시 하천유량의 물리적인 측면과는 상관없이 주로 적합도(Gooness of Fit)에 기인된 통계치에 의해서만 결정되기도 하는데 이러한 경우 잘못된 가정을 받아들이는 확률이 높아짐에 따라 추정결과의 신뢰성(Reliability)을 감소시킬 수 있다. 이러한 문제점을 극복하기 위해서 Onoz와 Bayazit (2001)는 Recession Curve를 지수함수로 가정하고 최대 갈수 기간의 길이(Maximum Dry Period Length)의 확률에 대한 이론적인 결과치들을 사용하여 Weibull 분포의 특정한 경우에 해당되어지는 Power 분포를 유도하였으며 유도된 Power 분포의 매개변수를 추정하기 위하여 L-Moment 방법을 사용하였다. 또한 Onoz와 Bayazit (2001) 작은 유출량에서 확률분포와 잘 맞지 않는 경우 작은 유출량값에 작은 가중치를 부여하여 확률분포에 대한 영향을 줄이는 방법인 LL-Moment 방법을 제안하였다. 본 연구에서는 낙동강 유역의 1번부터 5번 소유역에 대해 SSARR 모형을 이용하여 모의한 유출량을 이용하여 Weibull 분포, L-Moment방법에 의해 추정된 매개변수를 사용한 Power 분포, LL-Moment 방법에 의해 추정된 매개변수를 사용한 Power 분포를 적용하였으며 이들 분포의 적합도를 PPCC Test를 사용하여 평가해봄으로써 낙동강 유역에서의 저수시의 유출량 추정에 대한 Power 분포의 적용성을 판단해 보았다.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.1
• /
• pp.51-59
• /
• 2001

We propose the Bayesian testing for the equality of two Lognormal population means. Specially we use the fractional Bayesian factors suggested by O'Hagan (1995) based on the noninformative priors for the parameters. In order to investigate the usefulness of the proposed Bayesian testing procedures, we compare it with classical tests via both real data analysis and simulations.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.3
• /
• pp.122-134
• /
• 1994

The objective of this study is to provide with the hydrometeological and probabilistic characteristics of the storms and winds of typhoons that have been passed through the Korea peninsula during the last twenty-three years since 1961. The paths and intensities of the typhoons were analyzed. Fifty weather stations were selected and the rainfall and wind data during typhoon periods were collected. Rainfall data were analyzed for the patterns and probabilistic distributions. The results were presented to describe the areal distributions of probabilistic characteristics. Wind data were also analysed for their probabilistic distributions. The results obtained from this study can be summarized as follows: 1. The most frequent typhoon path that have passed through the Korean peninsula was type E, which was followed by types CWE, W, WE, and S. The most frequent typhoon intensity was type B, that was followed by A, super A, and C types, respectively. 2. The third quartile typhoon rainfall patterns appear most frequently followed by the second, first, and quartiles, respectively, in Seoul, Pusan, Taegu, Kwangju and Taejon. The single typhoon rainfalls with long rainfall durations tended to show delayed type rainfall patterns predominantly compared to the single rainfalls with short rainfall durations. 3. The most frequent probabilistic distribution for typhoon rainfall event is Pearson type-III, followed by Two-parameter lognormal distribution, and Type-I extremal distribution. 4. The most frequent probability distribution model of seashore location was Pearson type-III distribution. The most frequent probability distribution model of inland location was two parameter lognormal distribution. 5. The most frequent probabilistic distribution for typhoon wind events was Type-I xtremal distribution, followed by Two-parameter lognormal distribution, and Normal distribution.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.16 no.3
• /
• pp.130-141
• /
• 2004

For a coastal or harbor structure design, one of the most important environmental factors is the appropriate design wave condition. Especially, the information of deepwater wave height distribution is essential for reliability design. In this paper, a set of deep water wave data obtained from KORDI(2003) were analyzed for extreme wave heights. These wave data at 67 stations off the Korean coast from 1979 to 1998 were arranged in the 16 directions. The probability distributions considered in this research were the Weibull, the Gumbel, the Log-pearson Type-III, and Lognormal distribution. For each of these distributions, three parameter estimation methods, i.e. the method of moments, maximum likelihood and probability weighted moments, were applied. Chi-square and Kolmogorov-Smirnov goodness-of-fit tests were performed, and the assumed distribution was accepted at the confidence level 95%. Gumbel distribution which best fits to the 67 station was selected as the most probable parent distribution, and optimally estimated parameters and 50 year design wave heights were presented.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.3-9
• /
• 2001

In this paper, a random number generator for simulation of speech-waveform coders was designed. A random number generator having a desired probability density function and a desired power spectral density is discussed and experimental results are presented. The technique is based on Sondhi algorithm which consists of a linear filter and a memoryless nonlinearity. Several methods of obtaining memoryless nonlinearities for some typical continuous distributions are discussed. Sondhi algorithm is analyzed in the time domain using the diagonal expansion of the bivariate Gaussian probability density function. It is shown that the Sondhi algorithm gives satisfactory results when the memoryless nonlinearity is given in an antisymmetric form as in uniform, Cauchy, binary and gamma distribution. It is shown that the Sondhi algorithm does not perform well when the corresponding memoryless nonlinearity cannot be obtained analytically as in Student-t and F distributions, and when the memoryless nonlinearity can not be expressed in an antisymmetric form as in chi-squared and lognormal distributions.

• International Journal of Highway Engineering
• /
• v.12 no.1
• /
• pp.61-69
• /
• 2010

In this paper, we present the methodology about an optimal probability distribution selection as well as survival rate estimation with the national highway database from 1999 to 2008. Probability paper methods are adopted to estimate the parameters of each hazard model. The goodness-of-fit test, such as the Anderson-Darling statistics, was performed. As a result, we found that Lognormal distributionan is an appropriate distribution of newly constructed sections as well as overlayed sections. We also ascertained that the results of survival rate for pavement life between the proposed method and observed data are similar. Such a selection methodology and measures based on reliability theory can provide useful information for maintenance plans in pavement management systems as long as additional life data on pavement sections are accumulated.

• Water for future
• /
• v.29 no.1
• /
• pp.129-139
• /
• 1996

It is very important to select appropriate distributions for hydrological data in planning and designing hydraulic structures. Also, it is necessary to check whether the selected distribution reproduces the statistical characteristics of the real data. In this study, the parameters of the two- and three-parameter gamma, two- and three-parameter lognormal, Gumbel, two- and three-parameter log-Gumbel, GEV, log-Pearsonn type III, two- and three-parameter Weibull, four- and five-parameter Wakeby distributions were estimated for the rainfall data of 22 sites in Korea with 7 different durations based on the methods of moments, probability weighted moments, and maximum likelihood. And the validity conditions were checked for the estimated parameters. The separation effect for each distribution was examined throught 10,000 simulations using the estimated parameters. As results, the separation effect was the smallest: log-Pearson type III for moment method, log-Pearson type III and GEV for probability weighted moment method, and GEV for maximum likelihood method. However, it is large for the two-parameter distributions.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.6
• /
• pp.781-787
• /
• 2010

Forecasting possible failure characteristics is very important in maintenance planning because it helps in predicting any future failures and determining the optimum replacement interval. This paper examines the time.to-failure distribution of the transfer gearbox of a J79 engine by using a probability plotting technique which is one of the most convenient techniques for reliability analysis. Various probability distributions are evaluated for determining the suitable probability distribution of the failure data of the transfer gearbox, and the resulting correlation coefficient indicates that failure data have a lognormal distribution. The expected number of unscheduled maintenance actions and the optimum replacement interval for various values of cost ratios are determined.

• The Korean Journal of Applied Statistics
• /
• v.13 no.1
• /
• pp.189-196
• /
• 2000

Conjugate prior density families were motivated by considerations of tractability in implementing the Bayesian paradigm. But we consider problem that the conjugate prior p($\Theta$) cannot be used in restriction of the parameter $\Theta$. This article considers the nonconjugate prior problem of hierarchical Poisson model. We demonstrate the use of latent variables for sampling non-standard densities which arise in the context of the Bayesian analysis of non-conjugate by using a Gibbs sampler.