• 해양환경안전학회지
• /
• 제21권3호
• /
• pp.253-258
• /
• 2015

The purpose of this study is to find suitable probability distribution function of complex distribution data like multimodal. Normal distribution is broadly used to assume probability distribution function. However, complex distribution data like multimodal are very hard to be estimated by using normal distribution function only, and there might be errors when other distribution functions including normal distribution function are used. In this study, we experimented to find fit probability distribution function in multimodal area, by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. By using chi-squared statistic, gaussian mixture model(GMM) is the fittest model rather than other distribution functions, such as extreme value, generalized extreme value, logistic, and normal distribution. GMM was found to the fit model regard to multimodal data of maritime traffic flow distribution. Probability density function for collision probability and traffic flow distribution will be calculated much precisely in the future.

• 한국재난정보학회 논문집
• /
• 제16권3호
• /
• pp.602-610
• /
• 2020

연구목적: 영하의 조건에서도 균열발생을 억제하고, 구조적으로 안정된 성능과 방수기능을 동시에 발휘하는 아스팔트 포장시스템을 개발하고자 한다. 연구방법: SIS 폴리머 아스팔트, 일반 아스팔트 및 구스아스팔트를 대상으로 다양한 온도조건에 따른 유제의 부착실험 및 혼합물의 변형강도 실험을 실시하여 그 특성을 비교, 분석하였다. 연구결과: 아스팔트 유제의 부착강도는 SIS 폴리머 아스팔트가 일반 아스팔트 및 구스아스팔트에 비해 높은 것으로 나타났다. 아스팔트 혼합물의 변형강도는 SIS 폴리머 아스팔트와 일반 아스팔트가 거의 동일하게 나타났다. SIS 폴리머 아스팔트 혼합물은 일반 아스팔트 혼합물 및 구스아스팔트 혼합물에 비해 에너지흡수량이 상대적으로 높게 나타났다. 결론: SIS 폴리머 아스팔트 혼합물의 최대하중은 구스아스팔트 혼합물에 비해 낮게 나타났지만, 열악한 온도조건에서도 최대하중 이후에 안정적인 하중감소로 충분한 에너지흡수량을 확보하고 있고, 안정적인 파괴거동으로 미세균열 발생 등을 감소시켜 아스팔트 포장의 내구성 향상에 기여할 수 있을 것으로 판단된다.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.251-260
• /
• 2017

Black와 Scholes (1973)와 Merton (1973)의 옵션 가격결정이론에 대한 논문이 발표 된 이후 다양한 실증 분석 결과에 의하여 시간의 흐름에 따라 변동성이 불변한다고 가정하는 Black-Scholes 모형이 시장의 옵션 가격을 적절히 설명하지 못하고 있다는 것이 밝혀지면서 많은 대안적인 연구들이 진행되어 왔다. 예를 들어, Duan (1995)은 위험중립측도 하에서의 몬테카를로 시뮬레이션을 통해 GARCH 모형을 따르는 기초 자산의 옵션가격을 도출하는 방법을 제시하였다. 그러나 실제 주식이나 환율 등의 금융자료에 수익률분포는 정규분포에 비해 꼬리가 두껍고, 급첨의 형태를 보이는 데 Duan (1995)의 옵션가격 결정 방법은 이를 적절히 반영하지 못하고 있다. 이를 해결하기 위해 본 논문에서는 정규혼합모형의 오차를 갖는 GARCH 모형을 이용한 옵션가격 결정 방법을 제안하고자 한다. KOSPI200 옵션가격 자료를 이용하여 본 논문에서 제시된 옵션가격과 정규분포를 가정한 GARCH 모형에 의해 결정된 옵션가격과 비교한 결과, 금융 자료의 급첨의 성질이 뚜렷한 불안정한 시기인 경우에 오차가 정규혼합모형이라고 가정한 GARCH 모형에 의한 옵션가격 결정의 성과가 월등히 좋아지는 것을 확인할 수 있었다.

• Journal of Nutrition and Health
• /
• 제36권4호
• /
• pp.368-375
• /
• 2003

Cancer cachexia, characterized by weight loss and progressive tissue wasting, has been postulated to be mediated by cytokines. This study was conducted to evaluate the effect of Korean Traditional Medicine (KTM ; mokhyang, jisil, osooyu) mixture on food intake, blood cytokines level and blood nutrients status of the cachexia induced-mice. Thirty male Balb/c mice aged 6-8 weets were blocked into 3 groups that were Normal (no colon26 cells) Control (colon 26 cells) and KTM (colon26 cells + KTM extract mixture) group. In Control and KTM groups, murine adenocarcinoma colon 26 cells were injected subcutaneously to induce cachexia. KTM mice were given 200 ul KTM extract mixture (7%) per day. Half of each groups were sacrificed at the 14 th day to see serum cytokines & nutrients and the others were fed until almost of control group died to see life span. food intake and body weight were decreased significantly in cachexia induced groups. Tumor weight of KTM group was significantly lower than control group. Serum cytokines (IL-1$\beta$ and TNF-$\alpha$) level of cachexia induced groups were increased than those of normal group, and those of KTM group were significantly lower than the level of control group. Total serum protein and serum albumin were higher in KTM group than other groups. TG and fatty acid were lower in cachexia induced groups than normal group. HDL-cholesterol in serum was increased in KTM group. Effect of oral administration of KTM extract mixture on survival time of colon26 bearing mice showed extension of the life span. Overall, this study showed that KTM (mokhyang, jisil, osooyu) extract mixture inhibited the growth of cancer cell, changed the secretion of cytokines induced by colon26 adenocarcinoma in mice, and changed nutrition metabolism.

• Journal of the Korean Data and Information Science Society
• /
• 제17권4호
• /
• pp.1397-1403
• /
• 2006

This paper considers the testing problem for scale changes in autoregressive processes with heavy-tailed innovations. For a test, we propose the CUSUM test statistic based on the trimmed residuals. We perform a simulation study for the mixture normal and Cauchy innovations.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 추계 학술논문 발표대회
• /
• pp.75-76
• /
• 2019

The purpose of this study is to achieving a sufficient fluidity without segregation for normal strength grade concrete mixture. therefore in this research, by analyzing the various superplasticizer dosages on the concrete mixture, the segregation range was analyzed to provide a proper concrete mix design with sufficient fluidity.

• 응용통계연구
• /
• 제24권6호
• /
• pp.987-994
• /
• 2011

모집단이 부도와 정상상태로 구분되는 신용평가 관점에서 부도와 정상 상태의 조건부 누적분포함수를 추정하는 방법으로 정규혼합 분포추정과 kernel density estimation을 이용하는 분포추정을 고려한다. 정규혼합 분포의 모수를 EM 알고리즘을 사용해 추정하고, KDE 방법에서는 많이 사용하는 다섯 종류의 커널 함수와 네가지의 띠폭을 이용한다. 그리고 추정한 분포로부터 구한 각각의 ROC 함수를 구한다. 추정한 분포들의 적합도를 비교 분석하고, 이를 바탕으로 구한 ROC 곡선의 성과를 비교 토론한다. 본 연구에서는 KDE 방법으로 추정한 분포함수가 더 적합하고, 추정한 정규혼합 분포를 이용한 ROC 함수가 더 좋은 성과를 나타내는 것을 발견하였다.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.625-637
• /
• 2015

We develop a Bayesian clustering procedure based on a Dirichlet process prior with cluster specific random effects. Gibbs sampling of a normal mixture of linear mixed regressions with a Dirichlet process was implemented to calculate posterior probabilities when the number of clusters was unknown. Our approach (unlike its counterparts) provides simultaneous partitioning and parameter estimation with the computation of the classification probabilities. A Monte Carlo study of curve estimation results showed that the model was useful for function estimation. We find that the proposed Dirichlet process mixture model with cluster specific random effects detects clusters sensitively by combining vague edges into different clusters. Examples are given to show how these models perform on real data.

• 대한전기학회논문지
• /
• 제40권1호
• /
• pp.1-9
• /
• 1991

This paper describes a new method of calculating expected energy generation and loss of load probability (L.O.L.P) for electric power system operation and expansion planning. The method represents an equivalent load duration curve (E.L.D.C) as a mixture of cumulants approximation (M.O.N.A). By regarding a load distribution as many normal distributions-rather than one normal distribution-and representing each of them in terms of Gram-Charlier expansion, we could improve the accuracy of results. We developed an algorithm which automatically determines the number of distribution and demarcation points. In modeling of a supply system, we made subsets of generators according to the number of generator outage: since the calculation of each subset's moment needs to be processed rapidly, we further developed specific recursive formulae. The method is applied to the test systems and the results are compared with those of cumulant, M.O.N.A. and Booth-Baleriaux method. It is verified that the M.O.C.A. method is faster and more accure than any other method.

• 음성과학
• /
• 제14권1호
• /
• pp.151-162
• /
• 2007

This study focuses on the classification of pathological voice using GMM (Gaussian Mixture Model) and compares the results to the previous work which was done by ANN (Artificial Neural Network). Speech data from normal people and patients were collected, then diagnosed and classified into two different categories. Six characteristic parameters (Jitter, Shimmer, NHR, SPI, APQ and RAP) were chosen. Then the classification method based on the artificial neural network and Gaussian mixture method was employed to discriminate the data into normal and pathological speech. The GMM method attained 98.4% average correct classification rate with training data and 95.2% average correct classification rate with test data. The different mixture number (3 to 15) of GMM was used in order to obtain an optimal condition for classification. We also compared the average classification rate based on GMM, ANN and HMM. The proper number of mixtures on Gaussian model needs to be investigated in our future work.