• Journal of the Korean Data and Information Science Society
• /
• 제27권4호
• /
• pp.1083-1090
• /
• 2016

In clinical studies, different types of outcomes (e.g. repeated measures data and time-to-event data) for the same subject tend to be observed, and these data can be correlated. For example, a response variable of interest can be measured repeatedly over time on the same subject and at the same time, an event time representing a terminating event is also obtained. Joint modelling using a shared random effect is useful for analyzing these data. Inferences based on marginal likelihood may involve the evaluation of analytically intractable integrations over the random-effect distributions. In this paper we propose a joint HGLM approach for analyzing such outcomes using the HGLM (hierarchical generalized linear model) method based on h-likelihood (i.e. hierarchical likelihood), which avoids these integration itself. The proposed method has been demonstrated using various numerical studies.

• 한국군사과학기술학회지
• /
• 제5권2호
• /
• pp.50-61
• /
• 2002

In this study, 3-dimensional virtual visualization was performed for a rapid and accurate analysis of sea bottom topography, The visualization was done through the extracted data using the developed program and the generated data using the gridding method. The data extraction program was developed with AutoLISP programming language and this program was able to extract the needed sample bathymetry data from the electronic sea chart systematically as well as effectively. The gridded bathymetry data were generated by the interpolation or extrapolation method from the spatially-irregular sample data. As the result of realization for the 3-dimensional virtual visualization, it was shown a proper feasibility in the analysis of the sea bottom topography to determine the route of submarine cable burial.

• 대한교통학회지
• /
• 제10권3호
• /
• pp.21-42
• /
• 1992

As for the travel demand analysis of the past, forcasting has been conducted by the use of revealed preference(RP) informations about actual or observed choices made by individuals. Forcasting method using RP data needs implicit assumptions that there will be no remarkable changes in existing transport conditions. However in case of occuring the great changes in existing conditions or adding a new choice-set of hypothetical options, it is very difficult to predict future travel demand. Fortunately in recent years, especially in the mode choice analysis, it has been perceived that the importance of individual performance data using stated preference(SP) experiments as well as RP data. But the research reports has not been reported sufficiently from models estimated using SP data. Under this background, we analyze the factors affecting the mode choice behavior as a fundamental study against the modelling task with SP choice data. For this analysis, we assumed subway operations in the secondary cities where there are no subway lines until now, and set up a choice-set of hypothetical options based on Experimental Design Method.

• Journal of the Korean Data and Information Science Society
• /
• 제27권3호
• /
• pp.803-814
• /
• 2016

Recent times have seen an exponential increase in the amount of spatial data, which is in many cases associated with temporal data. Recent advances in computer technology and computation of hierarchical Bayesian models have enabled to analyze complex spatio-temporal data. Our work aims at modeling data of daily average nitrogen dioxide (NO2) levels obtained from 25 air monitoring sites in Seoul between 2003 and 2010. We considered an independent Gaussian process model and an auto-regressive model and carried out estimation within a hierarchical Bayesian framework with Markov chain Monte Carlo techniques. A Gaussian predictive process approximation has shown the better prediction performance rather than a Hierarchical auto-regressive model for the illustrative NO2 concentration levels at any unmonitored location.

• KEPCO Journal on Electric Power and Energy
• /
• 제3권2호
• /
• pp.127-131
• /
• 2017

The present paper describes the slagging field data obtained with the one-dimensional process model for the 500 MW tangentially coal fired boiler in Korea. To obtain slagging field data in terms of thermal resistances [$m^2{\cdot}^{\circ}C/kW$], a number of plant data were collected and analyzed with the one-dimensional modelling software at 500 MW full load. The slagging field data for the primary superheater were obtained for six coal blends, and compared with two TMA (Thermo-Mechanical analyzer) slagging indices and the numerical slagging index, along with the conventional slagging indices which were modified with the ash loading. The advanced two TMA indices for six blended coals give a good slagging tendency when comparing them with the slagging field data, while the modified conventional slagging indices give a relatively poor agreement.

• Environmental Engineering Research
• /
• 제14권2호
• /
• pp.102-110
• /
• 2009

Application of artificial intelligence (AI) approaches in eco-environmental modeling has gradually increased for the last decade. Comprehensive understanding and evaluation on the applicability of this approach to eco-environmental modeling are needed. In this study, we reviewed the previous studies that used AI-techniques in eco-environmental modeling. Decision Tree (DT) and Artificial Neural Network (ANN) were found to be major AI algorithms preferred by researchers in ecological and environmental modeling areas. When the effect of the size of training data on model prediction accuracy was explored using the data from the previous studies, the prediction accuracy and the size of training data showed nonlinear correlation, which was best-described by hyperbolic saturation function among the tested nonlinear functions including power and logarithmic functions. The hyperbolic saturation equations were proposed to be used as a guideline for optimizing the size of training data set, which is critically important in designing the field experiments required for training AI-based eco-environmental modeling.

• 한국기록관리학회지
• /
• 제11권1호
• /
• pp.161-181
• /
• 2011

본 연구는 디지털 연구데이터의 보존을 통해 얻을 수 있는 편익을 확인하기 위한 것이다. 경제학적 측면에서 디지털 연구데이터의 보존을 바라보고 있는 연구 사례를 살펴봄으로써 양적인 측면과 질적인 측면에서 디지털 연구데이터 보존을 통해 얻을 수 있는 광범위한 혜택을 분석한다. 이를 통해 국내의 디지털 연구데이터를 체계적으로 보존 관리하기 위한 시작점으로, 보존활동에의 투자를 이끌어낼 수 있는 편익을 확인하고 산출하기 위한 방안을 제시하고자 한다.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.271-275
• /
• 2015

A variety of evaluation application and initiatives on the adoption of Building Information Modelling (BIM) have been introduced in recent years. Most of which however, focused mainly on evaluating design to construction phase-processes, or BIM utilization performances. Through studying existing publications, it is found that continuous utilization of BIM data throughout the building's life cycle is comparatively less explored or documented. Therefore, this study looks at improving this incomplete life cycle condition with the concept that accumulated BIM data should be carried forward and statistically quantified for cross comparison, in order to facilitate practitioners to better improve the projects the future. Based on this conceptual theory of moving towards a closedloop BIM building life cycle, this study explores, through existing literature, the use of cloud based computing as the means to quantify and adaptively utilize BIM data. Categorization of BIM data relations in adaptive utilization of BIM data is then suggested as a initial step for enhancing cross comparison of BIM data in a cloud environment.

• 한국지반공학회지:지반
• /
• 제12권5호
• /
• pp.127-136
• /
• 1996

초 경량재인 E.P.S(20~30kg/m3)를 성토재로 사용하여 부족한 지지력과 침하에 대한 안정 성을 확보하는 방법이 최근 많이 사용되고 있다. 국내에서는 1993년 인천의 연약지반상 교대 됫채움재로 이 공법이 처음 사용된 이래 점차 활용이 늘어나고 있는 실정이다. 그러나 아직까지 EPS를 성토 재료로 사용한 지반에서 EPS의 거동을 예측하기 위한 합리적인 수치해석 모델이 제시되어 있지 않고 일축압축강도 및 크리프시험 결과에 따른 설계강도만이 제안되어 있는 실정이다. 따라서 본 연구에서는 성토재료로 사용된 EPS의 수치해석 모델을 제시하기 위하여 성토재로 사용되는 여러 종류 밀도의 EPS에 대해 구속압을 변화시키면서 삼축압축시험을 실시하였다. 삼축압축시험 결과를 분석하여 EPS의 축방향 변형률-응력 관계와 이의 도함수 그리고 포아송비를 밀도와 구속압에 의한 함수식으로 나타낼 수 있었다. 이 관계로부터 EPS의 거동을 예측하기 위한 비선형모델을 제안하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제34권8호
• /
• pp.1195-1202
• /
• 2010

2회로정수 등가회로에 의한 3상유도전동기 모델링 방식은 정격제원만으로 모의운전 특성을 효과적으로 재현하는 장점이 있으나 여자전류의 생략으로 역률 지시에서의 오차가 커지는 문제가 있다. 본 논문에서는 이러한 오차를 해소하기 위한 방안으로 정격 역률이 실제 전동기와 일치되는 조건에서 부하 크기와 관련이 없는 보상전류의 직교 성분을 해석한 후 이를 2회로정수의 부하 전류에 합성하는 방식을 제시하였다. 또한 정격제원으로부터 보상전류와 보정된 값의 전동기 전류, 토크 및 역률을 출력하는 전체적인 과정을 계산하는 연산모듈을 구성하였으며 실제 전동기의 제원을 모듈에 입력하여 나타나는 시뮬레이션 결과를 확인하였다. 이로부터 정격 운전점에서 주요 운전값이 실제 전동기와 일치할 뿐 아니라 슬립에 따른 전체 운전 영역에서 제시된 모듈의 출력 결과가 2회로정수의 경우보다 개선된 모의 특성을 나타내었다.