• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1059-1065
• /
• 2020

In hospitals, nurses are subjectively determining the urine status to check the kidneys and circulatory system of patients whose statuses are related to patients with kidney disease, critically ill patients, and nursing homes before and after surgery. To improve this problem, this paper proposes a urine spectrum analysis system which clusters urine test results based on a hybrid machine learning model consists of unsupervised learning and supervised learning. The proposed system clusters the spectral data using unsupervised learning in the first part, and classifies them using supervised learning in the second part. The results of the proposed urine spectrum analysis system using a mixed model are evaluated with the results of pure supervised learning. This paper is expected to provide better services than existing medical services to patients by solving the shortage of nurses, shortening of examination time, and subjective evaluation in hospitals.

• 한국항공운항학회지
• /
• 제20권4호
• /
• pp.76-83
• /
• 2012

Korean aviation Turbulenc Guidance (KTG) system is developed using the operational unified model (UM) of the Korea Meteorological Administration (KMA) and pilot reports (PIREPs) over East Asia. The KTG system comprised of twenty turbulence diagnostics that represent various turbulence potentials and have the best forecasting skills, which are combined into a single ensemble-averaged index, namely KTG, at upper-(above FL250) and mid-(below FL250) levels. It is found that the overall performance of the KTG is higher than those produced from the one single best index, and satisfies the minimum criteria (80% accuracy) that the system is operationally useful in aviation industry.

• Bulletin of the Korean Chemical Society
• /
• 제34권12호
• /
• pp.3800-3804
• /
• 2013

In this study, molecular dynamics simulations of SPC/E (extended simple point charge) model have been carried out in the canonical NVT ensemble over the range of temperatures 300 to 550 K with and without Ewald summation. The quaternion method was used for the rotational motion of the rigid water molecule. Radial distribution functions $g_{OO}(r)$, $g_{OH}(r)$, and $g_{HH}(r)$ and self-diffusion coefficients D for SPC/E water were determined at 300-550 K and compared to experimental data. The temperature dependence on the structural and diffusion properties of SPC/E water was discussed.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.413-417
• /
• 2005

A lattice model of a typical bridge column section is analyzed, and results are presented. The lattice is built as an ensemble of line elements and masses, that can capture strain rate dependency of concrete material. The research mainly breaks up into two parts: First, a micro level analysis of the material is executed, and control parameters of the governing equations are derived by matching the results with the common macroscopic properties of concrete material. Then, the properties exhibited by the micro model, which extends the classical material properties are applied to the mesoscale model. Hence, the analysis of the target structure can be performed. In the mesoscale analysis, ramp-like impulse loads are applied at different velocity, so that the contribution of the material level rate dependency to the global behavior of the structure can be tracked.

• 응용통계연구
• /
• 제24권4호
• /
• pp.587-595
• /
• 2011

Credit scoring is an objective and automatic system to assess the credit risk of each customer. The logistic regression model is one of the popular methods of credit scoring to predict the default probability; however, it may not detect possible nonlinear features of predictors despite the advantages of interpretability and low computation cost. In this paper, we propose to use a generalized partially linear model as an alternative to logistic regression. We also introduce modern ensemble technologies such as bagging, boosting and random forests. We compare these methods via a simulation study and illustrate them through a German credit dataset.

• East Asian Economic Review
• /
• 제25권4호
• /
• pp.403-424
• /
• 2021

AdaBoost tweaks the sample weight for each training set used in the iterative process, however, it is demonstrated that it provides more correlated errors as the boosting iteration proceeds if models' accuracy is high enough. Therefore, in this study, we propose a novel way to improve the performance of the existing AdaBoost algorithm by employing heterogeneous models and a stochastic twist. By employing the heterogeneous ensemble, it ensures different models that have a different initial assumption about the data are used to improve on diversity. Also, by using a stochastic algorithm with a decaying convergence rate, the model is designed to balance out the trade-off between model prediction performance and model convergence. The result showed that the stochastic algorithm with decaying convergence rate's did have a improving effect and outperformed other existing boosting techniques.

• 시스템엔지니어링학술지
• /
• 제17권2호
• /
• pp.98-105
• /
• 2021

As the average life expectancy is rising, the population is aging and the number of chronic diseases is increasing. This has increased the importance of healthy life and health management, and interest in mobile health services is on the rise thanks to the development of ICT(Information and communication technologies) and the smartphone use expansion. In order to meet these interests, many mobile services related to daily health are being launched in the market. Therefore, in this study, the characteristics of users who actually use mobile health services were analyzed and a predictive model applied with machine learning modeling was developed. As a result of the study, we developed a prediction model to which the decision tree and ensemble methods were applied. And it was found that the mobile health service users' continued use can be induced by providing features that require frequent visit, suggesting achievable activity missions, and guiding the sensor connection for user's activity measurement.

• Smart Structures and Systems
• /
• 제32권3호
• /
• pp.167-177
• /
• 2023

A probabilistic micromechanical framework is proposed to quantify numerically the self-healing capabilities of polymers containing microcapsules. A two-step self-healing process is designed in this study: A probabilistic micromechanical framework based on the ensemble volume-averaging method is derived for the polymers, and a hitting probability model combined with a crack nucleation model is then utilized for encountering microcapsules and microcracks. Using this framework, a series of parametric investigations are performed to examine the influence of various model parameters (e.g., the volume fraction of microcapsules, microcapsule radius, radius ratio of microcracks to microcapsules, microcrack aspect ratio, and scale parameter) on the self-healing capabilities of the polymers. The proposed framework is also implemented into a finite element code to solve the self-healing behavior of tapered double cantilever beam specimens.

• 한국수자원학회논문집
• /
• 제42권10호
• /
• pp.773-783
• /
• 2009

강우유출모형의 입력 자료로 사용되는 강우 관측 자료의 불확실성이 유량예측에 미치는 영향을 분석하기 위하여 모형변수 검정의 불확실성 연구에서 사용하는 GLUE (Generalized Likelihood Uncertainty Estimation)방법을 입력 자료 부분으로 확장하여 적용 하였다. 독일의 Weida 유역의 강우 관측 자료를 바탕으로 구조적 및 비구조적인 불확실성 부분을 각각 구조적인 오차 수정 과정과 DUE (Data Uncertainty Engine)을 통하여 강우자료를 구성하였다. 이를 유역의 수문학적 작용을 고려하기 위해 선정한 집중형 강우유출모형, PDM (Probability Distribution Model)에 MC (Monte Carlo)와 GLUE 방법을 활용하여 적용하였다. MC검정변수들의 검정 후 반응 표면(Posterior response surface)을 검토하고 GLUE 의 반응검정 모형변수(Behavioural model parameter set)를 선택, 간략한 GLUE 유량곡선들을 계산하였다. 계산된 GLUE 유량곡선들을 모두 합하여 앙상블 유량을 산정하고, 이 유량의 90 분위를 강우량자료 및 모형변수 검정의 불확실성을 고려한 신뢰구간으로 제시하였다. PDM 모형의 결과는 유량곡선의 전구간에서 안정적인 모의 능력을 보여주고 있으나, 첨두유량 부분이 적게 산정되는 문제점을 보이고 있다. 본 연구에서 상대적으로 적은 수의 강우 시나리오 및 반응검정 모형변수의 적용이라는 한계에도 불구하고, GLUE 방법을 강우관측자료의 불확실성 부분으로 확장하여 강우자료 및 변수 검정의 불확실성을 고려한 모의된 유량예측의 신뢰구간의 적용가능성을 보여주고 있다.

• Journal of Ecology and Environment
• /
• 제41권11호
• /
• pp.310-317
• /
• 2017

Background: Many studies about climate-related range shift of plants have focused on understanding the relationship between climatic factors and plant distributions. However, consideration of adaptation factors, such as dispersal and plant physiological processes, is necessary for a more accurate prediction. This study predicted the future distribution of marlberry (Ardisia japonica), a warm-adapted evergreen broadleaved shrub, under climate change in relation to the dispersal ability that is determined by elapsed time for the first seed production. Results: We introduced climate change data under four representative concentration pathway (RCP 2.6, 4.5, 6.0, and 8.5) scenarios from five different global circulation models (GCMs) to simulate the future distributions (2041~2060) of marlberry. Using these 20 different climate data, ensemble forecasts were produced by averaging the future distributions of marlberry in order to minimize the model uncertainties. Then, a dispersal-limited function was applied to the ensemble forecast in order to exam the impact of dispersal capacity on future marlberry distributions. In the dispersal-limited function, elapsed time for the first seed production and possible dispersal distances define the dispersal capacity. The results showed that the current suitable habitats of marlberry expanded toward central coast and southern inland area from the current southern and mid-eastern coast area in Korea. However, given the dispersal-limited function, this experiment showed lower expansions to the central coast area and southern inland area. Conclusions: This study well explains the importance of dispersal capacity in the prediction of future marlberry distribution and can be used as basic information in understanding the climate change effects on the future distributions of Ardisia japonica.