• Communications for Statistical Applications and Methods
• /
• 제24권1호
• /
• pp.81-96
• /
• 2017

Cumulative logit random effects models are typically used to analyze longitudinal ordinal data. The random effects covariance matrix is used in the models to demonstrate both subject-specific and time variations. The covariance matrix may also be homogeneous; however, the structure of the covariance matrix is assumed to be homoscedastic and restricted because the matrix is high-dimensional and should be positive definite. To satisfy these restrictions two Cholesky decomposition methods were proposed in linear (mixed) models for the random effects precision matrix and the random effects covariance matrix, respectively: modified Cholesky and moving average Cholesky decompositions. In this paper, we use these two methods to model the random effects precision matrix and the random effects covariance matrix in cumulative logit random effects models for longitudinal ordinal data. The methods are illustrated by a lung cancer data set.

• Journal of the Korean Data and Information Science Society
• /
• 제12권1호
• /
• pp.19-25
• /
• 2001

Random effects models which describe the dependence via random effects in various correlated data have recently received considerable attention in the biomedical literature. They include mixed linear models (MLMs), generatized linear mixed models (GLMMS) and hierarchical generalized linear models (HGLMs). For the inference Lee and Nelder (2000) proposed the first-and second-order REML (restricted maximum likelihood) methods based on hierarchical-likelihood of tee and Welder (1996). In this paper, for Poisson-gamma HGLMs the new methods are theoretically compared with marginal likelihood methods and both methods are illustrated by two practical examples.

• 대한기계학회논문집B
• /
• 제26권12호
• /
• pp.1729-1737
• /
• 2002

A mathematical model for the prediction of carbon-dioxide absorption rate during the transient state of rotary type absorber is developed. The rotary type absorber operates using a fast rotating porous structure and clean water. The model for the transient state rotary type absorbers is based on the steady state model of packed tower absorber. The paper manipulates the operating data of an arbitrary quasi-steady state condition of rotary type absorber for the determination of the coefficients involved in the model developed. The prediction accuracy is evaluated from the measured data of rotary type absorber operated under fast transient state. The measured data include the mole fraction of carbon dioxide in mixed gas and the pressure of absorber. The relative error in carbon dioxide prediction is estimated to be 20% at maximum. The model is successfully applied for the prediction of the behavior of a closed cycle diesel engine.

• 산업경영시스템학회지
• /
• 제33권1호
• /
• pp.114-120
• /
• 2010

데이터마이닝의 사전 단계에서 데이터의 차원(Dimensionality)을 줄이기 위한 단계로서 많은 요소선택(Feature Selection) 방법들이 개발되었다. 이 방법은 결과를 예측하거나 데이터를 설명하고자 할 때 어떤 요소들이 관련이 있는지를 결정하는 과정을 포함한다. 또한 이 방법은 데이터의 크기에 대한 확장성 (Scalability)를 향상시키며 학습 모델을 더욱 이해하기 쉽도록 줄 수 있다. 이 논문에서는 NP(Nested Partition) 방법을 사용한 최적화 기반의 새로운 요소선택 방법을 NP 구조의 기본적인 이론 근거와 함께 제안한다. 또 한 편으로 많은 요소선택 방법들이 다중 형태의 데이터를 처리하는데 한계를 가지고 있는데, NP 기반의 요소선택 방법에 다중 형태의 데이터를 처리할 수 있도록 하는 요소 성능 평가도구(Evaluators)를 도입하여 이를 극복하고자 한다. 또한 어떤 평가도구가 특정 데이터 형태에서 더욱 좋은 결과를 보이는지를 실험 결과와 함께 제시하였다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2012년도 제38회 춘계학술대회논문집
• /
• pp.592-596
• /
• 2012

항공기 성능해석을 하기 위해서는 엔진 상세 데이터가 필수적으로 요구된다. 하지만 이러한 엔진 상세 데이터는 항공회사의 경험으로 축적된 자산이기 때문에 엔진 성능 정보를 구하기 어렵다. 본 연구에서는 일반적으로 공개된 자료와 문헌정보를 이용하여 혼합흐름 터보팬 엔진 성능 모델을 구축하고 결과를 비교하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제35권7호
• /
• pp.899-906
• /
• 2011

Generally, load conditions of machine or structure in fatigue destruction is occurred not under single load conditions but under mixed load conditions. However, the experiment under mixing mode is insufficient because of no having test standard to the behavior of crack under mixing mode and variety of test methods, and many tests are required. In this paper measured crack direction path by created figure capture system when a experiment. Also, we studied by comparison the behavior of crack giving the change of stress ratio and inserting beach mark. Through the test under mixing mode, advancing path of crack is indicated that advancing inclined angle ${\Theta}$ (direction of specimen length) has increased depending on the increase of mixed mode impaction. It is indicated that according to the increase of mixed mode loading condition impaction under mixing mode, advancing speed of crack gets slow. Also, we found that inner crack(cross section of specimen) is progressed more rapidly than outer crack based on data through beach mark.

• 대한기계학회논문집B
• /
• 제24권11호
• /
• pp.1513-1522
• /
• 2000

In this study, the burning velocities of LFG and LFG mixed fuels have been numerically determined. C3 reaction mechanism involving 92 species and 621 reactions was adopted in the calculation. The computed burning velocities using C3 mechanism show good agreements with experimental data. Based on numerical results, the maximum burning velocities of LFG and LFG mixed fuels were correlated as a function of CH$_4$ and LFG component percentage at stoichiometric conditions. In addition, the correlations of burning velocities of LFG and LFG mixed fuels were obtained over a wide range of the equivalence ratio. The numerical results are well agreed with the burning velocity correlations. The burning velocity correlations for LFG and LFG mixed fuels suggested in this study can be applied to the practical utilization of LFG.

• 펄프종이기술
• /
• 제35권1호
• /
• pp.19-26
• /
• 2003

In recent years, numerous studies have been carried out to find out the possible substitution of PE-coated paperboards used in packaging of watery or oily foods. Accordingly, this study was carried out to obtain the basic data for producing higher functional coating agents for pulp mold by evaluating various kinds of mixed coating agents. At that time, two kinds of synthetic coating agents(AKD, PYA) and three kinds of natural coating agent(CMC, corn starch, oxidized starch) were used for making the mixed coating agents respectively. Physical properties of coated paperboards were tested. Conclusions obtained from this study were as follows. Based on concentrations, the proper mixture ratios were 10:90(AKD:CMC), 10:90(AKD:corn starch), 10:90(AKD:oxidized starch), 40:60(PVA:CMC), 20:80(PVA:corn starch) and 20:80(PYA:oxidized starch). The mixed coating agent of PYA:corn starch(20:80) was the most efficient coating agent. Consequently, water and oil resistance were improved even with much addition of natural coating agents. We consider that they can be suitable for the packaging used in the storage of higher moisture vegetables and other food, and also can be suitable for oily fried food.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2011년 춘계학술대회논문집
• /
• pp.556-560
• /
• 2011

The seawater lift pump system is responsible for maintaining the open canal level to provide the suction flow of circulating water pump at the set point. The objective of this paper is to design a 2-stage mixed flow pump(for seawater lifting) by inverse design and to evaluate the overall performance and the local flow fields of the pump by using a commercial CFD code. Rotating speed of the impeller is 1,750 rpm with the flow rate of 2,700 $m^3/h$. Finite volume method with structured mesh and Realizable ${\kappa}-{\varepsilon}$ turbulent model is used to guaranty more accurate prediction of turbulent flow in the pump impeller. The numerical results such as static head brake horse power and efficiency of the mixed flow pump are compared with the reference data. Also, the periodic condition calculation method for the mixed flow pump was carried out in order to investigate the pump performance characteristics with the modification of impeller geometry.

• 응용통계연구
• /
• 제28권2호
• /
• pp.295-308
• /
• 2015

지난 수십 년 동안 유전형 기술(genotyping technology)의 발달로 개인별 유전자 정보를 얻기 위해 필요한 비용이 감소함에 따라, 다양한 인간 질병의 원인 유전자를 규명하기 위한 많은 유전역학 연구들이 진행되어 왔다. 예를 들어 전장유전체관련분석(genome-wide association studies)은 수백 개에 이르는 표현형(phenotypes)에 대하여 수천 개에 이르는 원인유전자를 규명하였다. 유전체 자료의 홍수로 인하여 대규모 유전체 자료를 분석할 수 있는 다양한 분석 알고리즘에 개발되었으며, 특별히 선형혼합모형은 유전율의 추정부터 관련분석(association studies)에 이르기까지 유전역학 연구에서 광범위하게 활용되고 방법론이었다. 본 논문에서는 유전역학 연구에 있어 빈번하게 활용되는 선형혼합모형의 활용 사례를 나열하고, 각 분석 모형 별 추정치들의 생물학적 의미를 논하고자 한다.