• 한국재난정보학회 논문집
• /
• 제13권4호
• /
• pp.570-576
• /
• 2017

고속도로에서 화물차는 승용차에 비해 도로의 많은 부분을 점유한다. 이로 인해 도로의 용량은 상대적으로 감소하며, 국소적으로 주변 운전자에게 위협적인 요소로 작용한다. 화물차 사고는 일반적인 사고와 달리 사고 특성이 다르므로 분석 방법 또한 일반적인 사고와 다르게 적용해야 한다. 사고 분석 방법 중 사고예측모형은 특정 구간에 대한 사고건수를 예측하며 교통계획을 수립할 때 사고 예방을 위한 대책 수립과 도로의 위험성을 진단할 때 활용된다. 이에 본 연구는 고속도로의 화물차 간 사고 비율을 적용하여 사고예측모형에 투입될 수 있는 보정계수를 산출하는 것을 목적으로 한다. 연구를 위해 고속도로를 대상으로 사고 자료를 수집하였으며 2014~2016년까지 3개 년도의 교통량 및 사고 자료를 활용하였다. 연간 사고건수를 토대로 사고예측모형을 개발하였으며, 본 연구를 통해 화물차 간 사고 비율에 따른 사고예측모형을 비교함으로써 실질적인 고속도로 사고예측모형을 확인하고 그에 대한 대책을 제시하고자 한다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2018년도 추계 학술논문 발표대회
• /
• pp.59-60
• /
• 2018

The purpose of this study is to predict and classify the accident types based on the KOSHA (Korea Occupational Safety & Health Agency) and weather data. We also have an effort to suggest an important management method according to accident types by deriving feature importance. We designed two models based on accident data and weather data (model(a)) and only weather data (model(b)). As a result of random forest method, the model(b) showed a lack of accuracy in prediction. However, the model(a) presented more accurate prediction results than the model(b). Thus we presented safety management plan based on the results. In the future, this study will continue to carry out real time prediction to occurrence types to prevent safety accidents by supplementing the real time accident data and weather data.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2016년도 추계 학술논문 발표대회
• /
• pp.73-74
• /
• 2016

Although various research is being carried out to prevent the construction accidents, the number of victims of construction site is increasing continuously. Therefore, the purpose of this study is construction accidents prediction applying the boosting algorithm to the construction domains. Boosting algorithm was applied to construct construction accident prediction model and application of the model was examined using actual accident cases. It is possible to support safety manager to manage and prevent accidents in priority using the model.

• 한국도로학회논문집
• /
• 제18권4호
• /
• pp.93-102
• /
• 2016

PURPOSES : There are many recently constructed roundabouts in Jeollabuk-do province. This study analyzed how roundabouts reduce the risk of accidents and improve safety in the province. METHODS : This study analyzed safety improvement at roundabouts by using an accident prediction model that uses an Empirical Bayes method based on negative binomial distribution. RESULTS : The results of our analysis model showed that the total number of accidents decreased from 130 to 51. Roundabouts also decreased casualties; the number of casualties decreased from 7 to 0 and the seriously wounded from 87 to 16. The effectiveness of accident reduction as analyzed by the accident prediction model with the Empirical Bayes method was 60%. CONCLUSIONS : The construction of roundabouts can bring about a reduction in the number of accidents and casualties, and make intersections safer.

• 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.

• 산업경영시스템학회지
• /
• 제45권2호
• /
• pp.20-29
• /
• 2022

This study intends to present a traffic node-based and link-based accident prediction models using XGBoost which is very excellent in performance among machine learning models, and to develop those models with sustainability and scalability. Also, we intend to present those models which predict the number of annual traffic accidents based on road types, weather conditions, and traffic information using XGBoost. To this end, data sets were constructed by collecting and preprocessing traffic accident information, road information, weather information, and traffic information. The SHAP method was used to identify the variables affecting the number of traffic accidents. The five main variables of the traffic node-based accident prediction model were snow cover, precipitation, the number of entering lanes and connected links, and slow speed. Otherwise, those of the traffic link-based accident prediction model were snow cover, precipitation, the number of lanes, road length, and slow speed. As the evaluation results of those models, the RMSE values of those models were each 0.2035 and 0.2107. In this study, only data from Sejong City were used to our models, but ours can be applied to all regions where traffic nodes and links are constructed. Therefore, our prediction models can be extended to a wider range.

• Nuclear Engineering and Technology
• /
• 제46권3호
• /
• pp.373-380
• /
• 2014

Safety-related parameters are very important for confirming the status of a nuclear power plant. In particular, the reactor vessel water level has a direct impact on the safety fortress by confirming reactor core cooling. In this study, the reactor vessel water level under the condition of a severe accident, where the water level could not be measured, was predicted using a fuzzy neural network (FNN). The prediction model was developed using training data, and validated using independent test data. The data was generated from simulations of the optimized power reactor 1000 (OPR1000) using MAAP4 code. The informative data for training the FNN model was selected using the subtractive clustering method. The prediction performance of the reactor vessel water level was quite satisfactory, but a few large errors were occasionally observed. To check the effect of instrument errors, the prediction model was verified using data containing artificially added errors. The developed FNN model was sufficiently accurate to be used to predict the reactor vessel water level in severe accident situations where the integrity of the reactor vessel water level sensor is compromised. Furthermore, if the developed FNN model can be optimized using a variety of data, it should be possible to predict the reactor vessel water level precisely.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 추계학술대회 논문집
• /
• pp.429-434
• /
• 2001

Rail crossings pose special safety concerns for modern railroad operation with faster trains. More than ninety percent of train operation-related accidents occurs on at-grade crossings. Surest countermeasure for this safety hazard is to eliminate at-grade crossings by constructing over/under pass or by closing them. These eliminations usually require substantial amount of investment and/or heavy public protest from those affected by them. Thorough and objective analysis are usually required, and valid accident prediction models are essential to the process. This paper developed an accident prediction model for Korean at-grade crossings. The model utilized many important factors such as guide personnel, highway traffic, train frequency, train sight distance, and number of tracks. Developed model was validated with actual accident data.

• 한국철도학회논문집
• /
• 제20권4호
• /
• pp.482-490
• /
• 2017

본 연구는 사고심각도 분류 및 예측을 위한 철도사고조사 통계기법에 관한 연구이다. 그동안의 선형 회귀분석은 사고 심각도 분석에 어려움이 있었으나 로지스틱회귀분석은 이를 보완할 수 있었다. 데이터마이닝 기법인 로지스틱회귀분석을 활용, 서울지하철(5~8호선) 역사 내 전도사고 중 에스컬레이터 전도사고 발생에 영향을 주는 사고예측 모형 변수는 사고자 연령, 음주여부, 사고 당시상황 및 행동, 핸드레일 잡음 여부였다. 분석의 정확도는 76.7%로 설명되었고 분석방법 결과에 따르면 정확도와 유의수준 측에서 로지스틱회귀분석 방법이 도시철도 사상사고 예측모형을 개발하는데 유용한 데이터마이닝 기법으로 판단된다.

• 한국도로학회논문집
• /
• 제10권1호
• /
• pp.31-39
• /
• 2008

본 연구는 도로기하구조 요인과 교통사고간의 관계를 규명하기 위하여 CART분석을 이용하여 전국의 4차로 국도를 대상으로 교통사고예측모형을 개발하고, 다중회귀모형, 확률회귀모형과 CART분석모형을 비교 분석하여 개발한 모형의 적합도를 검증하였다. 연구결과로는 첫째, 변수간의 복합적인 상호관계를 설명할 수 있는 CART분석을 이용하여 국도의 교통사고 예측모형을 개발하고 도로기하구조 요인에 따라 표준교통사고율을 의미하는 교통사고발생도표를 제시하였다. 둘째, CART분석모형에 근거하여 교통사고 발생률에 큰 영향을 미치는 도로기하구조 요인이 구간거리(km), 횡단보도폭(m), 횡단길어깨(m), 교통량 순으로 나타났다. 셋째, CART분석모형의 적합도 검증결과, CART분석모형이 실제교통사고율을 타 모형에 비해 전반적으로 잘 묘사하고 있었으나, 각 모형별로 교통사고율의 크기에 따라 교통사고율이 비교적 낮은 구간에서는 다중회귀모형이, 평균이상의 교통사고율을 나타내는 구간에서는 포아송 회귀모형의 예측력이 높았으며, CART분석모형은 교통사고율의 크기와 상관없이 우수한 예측력을 보였다. 넷째, 도출된 교통사고발생도표는 도로기하구조 조건에 따른 표준교통사고율을 제시해주기 때문에 도로설계 시에 안전한 기하구조 설계요소 선정기준을 제시 할 뿐만 아니라, 교통사고 잦은 지점개선사업추진 시 사업의 우선순위를 판단할 수 있는 기준을 제시하는 등 정책적 활용도가 매우 높을 것으로 판단된다.