• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2672-2679
• /
• 2012

The study was done to provide basic data of medical quality evaluation after developing the comorbidity disease mortality measurement modeled on the severity-adjustment method of AMI. This study analyzed 699,701 cases of Hospital Discharge Injury Data of 2005 and 2008, provided by the Korea Centers for Disease Control and Prevention. We used logistic regression to compare the risk-adjustment model of the Charlson Comorbidity Index with the predictability and compatibility of our severity score model that is newly developed for calibration. The models severity method included age, sex, hospitalization path, PCI presence, CABG, and 12 variables of the comorbidity disease. Predictability of the newly developed severity models, which has statistical C level of 0.796(95%CI=0.771-0.821) is higher than Charlson Comorbidity Index. This proves that there are differences of mortality, prevalence rate by method of mortality model calibration. In the future, this study outcome should be utilized more to achieve an improvement of medical quality evaluation, and also models will be developed that are considered for clinical significance and statistical compatibility.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.271-282
• /
• 2021

This study was conducted to develop a model for predicting the length of stay for premature infants through machine learning. For the development of this model, 6,149 cases of premature infants discharged from the hospital from 2011 to 2016 of the discharge injury in-depth survey data collected by the Korea Centers for Disease Control and Prevention were used. The neural network model of the initial hospitalization was superior to other models with an explanatory power (R²) of 0.75. In the model added by converting the clinical diagnosis to CCS(Clinical class ification software), the explanatory power (R²) of the cubist model was 0.81, which was superior to the random forest, gradient boost, neural network, and penalty regression models. In this study, using national data, a model for predicting the length of stay for premature infants was presented through machine learning and its applicability was confirmed. However, due to the lack of clinical information and parental information, additional research is needed to improve future performance.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.4
• /
• pp.1-8
• /
• 2012

The aim of this study is to evaluate fire-induced damage for shield tunnel linings. Full-scale fire test was conducted to evaluate fire-induced damage. Residual compressive strength was measured on the core samples of shield tunnel lining subjected to high temperatures. Heating temperature was predicted by XRD and TG analysis. As a result, Strength degradation of concrete with temperatures can be evaluated by residual compressive strength of core samples. In addition, residual compressive strength can be estimated by previous studies if heating temperature is exactly predicted. It is possible that heating temperature is predicted by XRD and TG analysis at $450^{\circ}C$. For more accurate prediction of heating temperature it should be performed both instrumental analysis and analytical methods with temperatures ranging from $400{\sim}600^{\circ}C$.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.1
• /
• pp.83-90
• /
• 2008

A vibration-based monitoring system is newly proposed to predict the loss of prestress forces in prestressed concrete (PSC) girder bridges. Firstly, a global damage alarming algorithm is newly proposed to monitor the occurrence of prestress-loss by using the change in frequency responses. Secondly, a prestress-loss prediction algorithm is selected to estimate the extent of prestress-loss by using the change in natural frequencies. Finally, the feasibility of the proposed system is experimentally evaluated on a scaled PSC girder model for which acceleration responses were measured for several damage scenarios of prestress-loss.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.103-108
• /
• 2018

The fragility curves for CFRD dams are derived in this study for probabilistic damage estimation as a function of a ground motion intensity. The dam crest settlement, which is a widely used damage index, is used for minor, moderate, and extensive damage states. The settlement is calculated from nonlinear dynamic numerical simulations. The accuracy of the numerical model is validated through comparison with a centrifuge test. The fragility curve is represented as a log normal distribution function and presented as a function of the peak ground acceleration. The fragility curves developed in this study can be utilized for real time assessment of the damage of dams.

• Composites Research
• /
• v.14 no.3
• /
• pp.1-9
• /
• 2001

A new non-destructive fatigue prediction model of the composite laminates is developed. The natural frequencies of fatigue-damaged laminates under extensional loading are related to the fatigue life of the laminates by establishing the equivalent flexural stiffness reduction as a function of the elastic properties of sublaminates. The flexural stiffness is derived by relating the 90-ply elastic modulus reduction, and using the laminate plate theory to the degraded elastic modulus and the intact elastic modulus of other laminates. The natural frequency reduction model, in which the dominant fatigue mode can be identified from the sensitivity scale factors of sublaminate elastic properties, provides natural frequency vs. fatigue cycle curves for the composite laminates. Vibration tests were also conducted on $[{90}_2/0_2]_s$ carbon/epoxy laminates to verify the natural frequency reduction model. Correlations between the predictions of the model and experimental results are good.

• Journal of Digital Convergence
• /
• v.16 no.1
• /
• pp.231-242
• /
• 2018

The efficient management of the Length of Stay(LOS) is important in hospital. It is import to reduce medical cost for patients and increase profitability for hospitals. In order to efficiently manage LOS, it is necessary to develop an artificial intelligence-based prediction model that supports hospitals in benchmarking and reduction ways of LOS. In order to develop a predictive model of LOS for acute stroke patients, acute stroke patients were extracted from 2013 and 2014 discharge injury patient data. The data for analysis was classified as 60% for training and 40% for evaluation. In the model development, we used traditional regression technique such as multiple regression analysis method, artificial intelligence technique such as interactive decision tree, neural network technique, and ensemble technique which integrate all. Model evaluation used Root ASE (Absolute error) index. They were 23.7 by multiple regression, 23.7 by interactive decision tree, 22.7 by neural network and 22.7 by esemble technique. As a result of model evaluation, neural network technique which is artificial intelligence technique was found to be superior. Through this, the utility of artificial intelligence has been proved in the development of the prediction LOS model. In the future, it is necessary to continue research on how to utilize artificial intelligence techniques more effectively in the development of LOS prediction model.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.11a
• /
• pp.212-213
• /
• 2018

청항선은 해상 부유물을 수거하는 배로서 청소과정에서 특성상 해상부유물로 인한 선체손상 또는 프로펠러 유입으로 사고의 위험이 있다. 따라서, 건조 시 이를 고려한 설계를 하거나 반영하여야 한다. 그러나 모형시험에서 구현의 문제와 많은 Case로 인해 시간과 비용에 많은 어려움이 있다. 따라서, 이를 예측하기 위해 최근 발전하고 있는 수치해석을 통해 해상 부유물을 구현하였다. 그 후 속도에 따라 부유물을 흘려 프로펠러 주변 유입여부를 확인하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.105-105
• /
• 2020

전 세계적으로 기후변화에 따른 기온상승 및 강수량 증가, 호우일수 증가 등 이상기후로 인해 다양한 형태의 자연재해가 발생하고 있으며, 이로 인해 우리나라에서도 폭우, 풍랑, 가뭄, 대설 등으로 인한 자연재해 발생이 증가하고 있다. 특히 우리나라는 연평균 강수량 1,300mm의 대부분의 강우가 하절기인 6 ~ 9월에 태풍 및 집중호우를 동반하여 발생하기 때문에 연강수량의 60%이상이 여름철에 집중된다. 이러한 여름철에 집중된 강우로 인해 홍수 및 범람 피해가 여름철에 급증하고 있으며, 2차 피해인 산사태 및 토석류 피해 또한 급증하고 있는 추세이다. 토석류는 집중호우 시 자연산지의 취약한 사면이 붕괴되어 유출수와 함께 급경사의 계류로 붕괴된 토석이 유출되면서 토석류로 전이 및 발전하여 계류하부의 주택 및 농경지를 매몰하여 피해를 발생시킨다. 특히 토석류는 유출수와 함께 토석이 급경사의 계류를 따라 빠른 속도로 이동하고 퇴적 시작점에서 높이의 6배까지 이동하여 인명피해 등 큰 피해를 발생시키는 특성이 있다. 이러한 토석류 피해로 인한 피해와 손실을 최소화하기 위해서는 토석류 발생 시 피해 규모를 예측하여야하며, 또한 하부 구조물의 손실을 정량적으로 해석하여 방재정책의 우선순위를 수립하여야 한다. 따라서 본 논문에서는 강우로 인한 토석류 발생시 하부 구조물의 손실을 정량적으로 해석하기 위하여 토사재해 손실·손상함수를 개발하여, 함수를 탑재한 토사재해 피해액 산정모형인 DELET(DEbris flow Loss Estimation Tool) 모형을 개발하였다. DELET를 이용하여 실제 토석류 피해가 발생한 피해지역에 적용하여 토사재해 피해 구조물의 손실을 평가하였다.

• Journal of the Korean GEO-environmental Society
• /
• v.9 no.5
• /
• pp.21-27
• /
• 2008

The Sediment deposits in rivers and reservoirs are major components interfering with the useful function of the reservoirs, and clogging the inlet port at water intakes in rivers and erosion of pump impellers. Therefore, an accurate estimation method of sediment deposition is requisite to the efficient water resources investigation, planning and management. The objective of this paper is to forecast of reservoir sediment deposition using two dimensional model (SMS) to UnMun reservoir in GyeongSangBukDo. The RUSLE model showed that reservoirs volume was decreased $2,084.09{\times}10^6m^3$ after 50 years and $2,196.65{\times}10^6m^3$ after 100 years, which is plan flood level elevation (EL.152.12 m) reservoir. The two dimensional model showed that reservoirs volume was decreased $2,227.41{\times}10^6m^3$ after 50 years and $2,121.47{\times}10^6m^3$ after 100 years, which is plan flood level elevation (EL.152.12 m) reservoir. The results of this application showed that the use of two dimensional model was very effective for the estimation sediment deposits throughout the reservoir.