• 디지털콘텐츠학회 논문지
• /
• 제19권4호
• /
• pp.685-692
• /
• 2018

본 연구는 통계분석을 이용한 중년 성인의 고혈압 예측모델 개발이 목적이다. 국민건강영양조사자료(2013년-2016년)를 사용하여 통계분석과 예측모델을 개발하였다. 이진 로지스틱 회귀분석으로 통계적 유의한 고혈압 위험인자를 제시하였으며, Wrapper 변수선택기법을 적용한 로지스틱회귀와 나이브베이즈 알고리즘을 이용하여 예측모델을 개발하였다. 통계분석에서 고혈압에 가장 높은 연관성을 갖는 인자는 남성에서 WHtR (p<0.0001, OR = 2.0242), 여성에서 AGE(p<0.0001, OR = 3.9185)로 나타났다. 예측모델의 성능평가에서, 로지스틱 회귀 모델이 남성(AUC = 0.782)과 여성(AUC = 0.858)에서 가장 좋은 예측력을 보였다. 우리의 연구 결과는 고혈압에 대한 대규모 스크리링 도구를 개발하는데 중요한 정보를 제공하며, 고혈압 연구에 대한 기반정보로 활용할 수 있다.

• Journal of Preventive Medicine and Public Health
• /
• 제43권4호
• /
• pp.283-291
• /
• 2010

Objectives: The purpose of this study was to develop a prediction model for future smoking intention among Korean adolescents aged 13 to 15 in order to identify the high risk group exposed to future smoking. Methods: The data was collected from a total of 5940 students who participated in a self-administrated questionnaire of a cross-sectional school-based survey, the 2004 Korea Global Youth Tobacco Survey. Chi-square tests and logistic regression analyses were carried out to identify the relevant determinants associated with intentions of adolescents’ future smoking. Receiver Operation Characteristic (ROC) assessment was applied to evaluate the explanation level of the developed prediction model. Results: 8.4% of male and 7.2% of female participants show their intentions of future smoking. Among non-smoking adolescents; who have past smoking experience [odds ratio (OR) 2.73; 95% confidence interval (CI) 1.92- 3.88]; who have intentions of smoking when close friends offer a cigarette (OR 31.47; 95% CI = 21.50 - 46.05); and who have friends that are mostly smokers (OR 5.27; 95% CI = 2.85 - 9.74) are more likely to be smokers in the future. The prediction model developed from this study consists of five determinants; past smoking experience; parents smoking status; friends smoking status; ownership of a product with a cigarette brand logo; and intentions of smoking from close friends’ cigarette offer. The area under the ROC curve was 0.8744 (95% CI=0.85 - 0.90) for current non-smokers. Conclusions: For efficiency, school-based smoking prevention programs need to be designed to target the high risk group exposed to future smoking through the prediction model developed by the study, instead of implementing the programs for all the students.

• 한국지반환경공학회 논문집
• /
• 제17권6호
• /
• pp.13-21
• /
• 2016

기존의 토사재해 위험지역 예측은 토질특성과 경사만으로 분석되기 때문에 지역적 특징이 반영되어 있지 않다. 따라서 보다 합리적인 위험지 예측 분석을 위하여 해당지역의 특징을 반영한 토사재해 위험지 예측을 할 필요가 있다. 토사재해 위험지의 특징 중 하나인 수목의 뿌리는 토사 내 점착력을 증가시키는 작용을 하는 것으로 연구되어 왔으며, 수목의 종류에 따라 그 영향이 다른 것으로 알려져 있다. 또한, 지역에 따라 수목의 밀집 정도(수관밀도)가 다양하기 때문에 실제 수목의 분포를 고려하여 토사재해 위험지역 예측을 한다면 보다 합리적인 위험지 예측이 가능할 것이다. 본 연구에서는 세종시 괴화산 일대를 중심으로 수목의 수관밀도를 고려한 뿌리점착력을 사용하여 토사재해 위험지역 예측을 하였으며, 뿌리점착력을 적용하지 않은 토사재해 위험지역 예측 결과와 비교하였다.

• 한국안전학회지
• /
• 제33권4호
• /
• pp.98-104
• /
• 2018

Macroscopic accident analyses have been conducted to incorporate transportation safety into long-term transportation planning. In macro-level accident prediction model, exposure variable(e.g. a settled population) have been used as fundamental explanatory variable under the concept that each trip will be subjected to a probable risk of accident. However, a settled population may be embedded error by exclusion of active population concept. The objective of this research study is to develop macro-level accident prediction model using floating population variable(concept of including a settled population and active population) collected from mobile phone data. The concept of accident prediction models is introduced utilizing exposure variable as explanatory variable in a generalized linear regression with assumption of a negative binomial error structure. The goodness of fit of model using floating population variable is compared with that of the each models using population and the number of household variables. Also, log transformation models are additionally developed to improve the goodness of fit. The results show that the log transformation model using floating population variable is useful for capturing the relationships between accident and exposure variable and generally perform better than the models using other existing exposure variables. The developed model using floating population variable can be used to guide transportation safety policy decision makers to allocate resources more efficiently for the regions(or zones) with higher risk and improve urban transportation safety in transportation planning step.

• 한국안전학회지
• /
• 제36권3호
• /
• pp.31-39
• /
• 2021

In Korea, more than half of work-related fatalities have occurred on construction sites. To reduce such occupational accidents, safety inspection by government agencies is essential in construction sites that present a high risk of serious accidents. To address this issue, this study developed risk prediction models of serious accidents in construction sites using five machine learning methods: support vector machine, random forest, XGBoost, LightGBM, and AutoML. To this end, 15 proactive information (e.g., number of stories and period of construction) that are usually available prior to construction were considered and two over-sampling techniques (SMOTE and ADASYN) were used to address the problem of class-imbalanced data. The results showed that all machine learning methods achieved 0.876~0.941 in the F1-score with the adoption of over-sampling techniques. LightGBM with ADASYN yielded the best prediction performance in both the F1-score (0.941) and the area under the ROC curve (0.941). The prediction models revealed four major features: number of stories, period of construction, excavation depth, and height. The prediction models developed in this study can be useful both for government agencies in prioritizing construction sites for safety inspection and for construction companies in establishing pre-construction preventive measures.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 봄 학술발표회 논문집
• /
• pp.493-500
• /
• 2001

The construction of bored tunnels in soft ground inevitably causes ground movements. In the urban environment these may be of particular significance, because of their influence on buildings, other tunnels and services. The prediction of ground movements and the assessment of the potential effects on the structures is therefore an essential aspect of planning, design and construction of a tunnelling project in the urban environment. In this study, to minimize the effect of tunnelling-Induced ground movements on the adjacent structures, a system for tile settlement risk management was developed. The GIS based risk assessment system for adjacent structures developed in this study consists of several modules such as building information module, settlement evaluation module, potential risk assessment module for adjacent structures, and analysis module for monitoring data. This system focuses on controlling and managing construction processes that may lead to settlement In the surrounding buildings and can contribute to producing the optimum technical and economic design.

• 한국방재안전학회논문집
• /
• 제10권1호
• /
• pp.29-34
• /
• 2017

This Analyzed case study of measuring displacement, implemented laboratory investigation, and in-situ testing in order to interpret ground subsidence risk rating by excavation work. Since geological features of each country are different, it is necessary to objectify or classify quantitatively ground subsidence risk evaluation in accordance with Korean ground character. Induced main factor that could be evaluated and used to predicted ground subsidence risk through literature investigation and analysis study on research trend related to the ground subsidence. Major factors of ground subsidence might be classified by geological features as overburden, boundary surface of ground, soil, rock and water. These factors affect each other differently in accordance with type of ground that's classified soil, rock, or complex. Then rock could be classified including limestone element or not, also in case of the latter it might be classified whether brittle shear zone or not.

• 한국가스학회지
• /
• 제20권3호
• /
• pp.59-65
• /
• 2016

가스 사용 시설에서 폭발 위험성 평가 등급에 따라 적합한 방폭용 설비를 사용하는 것은 매우 중요하다. 가스 관련 법에서 가스 사용시설의 방폭 기준은 제시하고 있으나 폭발 위험장소 구분을 위한 기술 기준은 별도로 제시되어 있지 않다. 본 연구에서 한국산업표준 KS를 이용하여 저압 도시가스 배관시설에 대해 합리적인 폭발위험성 예측 방법을 제시하고자 한다. 누출공 크기, 누출압력에 따른 가상체적, 환기 유효성 등의 중요변수를 적용하여 폭발위험성이 예측되었다. 자연 환기 조건을 만족하는 실험 설비가 제작되어 도시 가스 누출 실험 결과와 KS 표준에 의해 예측된 폭발 위험성 예측 결과가 비교되었다.

• 한국안전학회지
• /
• 제21권6호
• /
• pp.74-81
• /
• 2006

Probabilistic Risk Assessment considering statistically random variables is performed for the preliminary design of a Arch Bridge. Component reliabilities of girders have been evaluated using the response surfaces of the design variables at the selected critical sections based on the maximum shear and negative moment locations. Response Surface Method(RSM) is successfully applied for reliability analyses for this relatively small probability of failure of the complex structure, which is hard to be obtained by Monte-Carlo Simulations or by First Order Second Moment Method that can not easily calculate the derivative terms of implicit limit state functions. For the analysis of system reliability, parallel resistance system composed of girders is changed into parallel series connection system. The upper and lower probabilities of failure for the structural system have been evaluated and compared with the suggested prediction method for the combination of failure modes. The suggested prediction method for the combination of failure modes reveals the unexpected combinations of element failures in significantly reduced time and efforts compared with the previous permutation method or system reliability analysis method.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.295-300
• /
• 2007

Probabilistic Risk Assessment considering statistically random variables is performed for the preliminary design of a Arch Bridge. Component reliabilities of girders have been evaluated using the response surfaces of the design variables at the selected critical sections based on the maximum shear and negative moment locations. Response Surface Method (RSM) is successfully applied for reliability analyses for this relatively small probability of failure of the complex structure, which is hard to be obtained by Monte-Carlo Simulations or by First Order Second Moment Method that can not easily calculate the derivative terms of implicit limit state functions. For the analysis of system reliability, parallel resistance system composed of girders is changed into parallel series connection system. The upper and lower probabilities of failure for the structural system have been evaluated and compared with the suggested prediction method for the combination of failure modes. The suggested prediction method for the combination of failure modes reveals the unexpected combinations of element failures in significant]y reduced time and efforts compared with the previous permutation method or system reliability analysis method.