• 대한전자공학회논문지TC
• /
• 제43권9호
• /
• pp.25-31
• /
• 2006

본 논문에서는 데이터 마이닝을 이용한 차량 사고 사망확률 모형을 제안하였다. 본 논문의 목표는 제안된 모델을 이용하여 기술적, 환경적 개선을 통해 교통사고를 줄이는 것으로 교통사고 데이터를 수집하여 데이터 마이닝 알고리즘을 적용하여 사망 원인에 대한 분석을 통해 사망확률 모형을 개발하였다. 이를 위해서 훈련 데이터와 테스트 데이터를 이용하여 최적의 모형을 개발하였다. 이모형을 통해 교통 사망사고에 대한 사망확률을 구할 수 있고 사망 사고의 원인이 되는 중요한 요인을 알아낼 수 있다. 교통사고의 원인이 되는 요인을 기술 개발과 교통 환경 개선에 활용한다면 향후 교통사고를 줄이는데 기여할 것이다.

• 대한교통학회지
• /
• 제24권2호
• /
• pp.139-145
• /
• 2006

본 논문에서는 보행-차량 충돌사고 시 보행자 사망 여부를 확률적으로 예측할 수 있는 모형을 개발하였다. 베이지안 신경망을 적용하여 보행자 사망확률모형을 개발하고, 로지스틱 회귀분석 기법 기반의 모형과 예측력을 비교하였다. 본 연구를 위하여 개별 교통사고 자료를 수집하였으며, 교통사고 재현을 통해 사고 당시의 충돌속도를 추정하여 보행자 연령, 차종과 함께 모형의 독립변수로 사용하였다. 보다 정확하고 신뢰성 있는 모형개발을 위해 반복적 샘플링기법을 적용하여, 다양한 학습자료 및 테스트 자료를 구성하고 모형의 성능을 평가하였다 본 연구를 통해 개발된 모형은 보행자 보호를 위한 첨단차량기술 개발, 제한속도의 설정 등 다양한 정책 및 관련기술의 개발을 지원하는 유용한 도구로 사용될 것으로 기대된다.

• 대한교통학회지
• /
• 제23권3호
• /
• pp.49-57
• /
• 2005

본 연구에서는 보행자와 차량의 충돌 시 보행자의 상해를 감소시키기 위한 충돌안전기준의 도입에 따른 보행자 사망자수 감소 효과를 추정하는 방법론을 개발하였다. 국내 교통환경 특성을 반영한 보행자 사망확률모형을 개발하고, 사망자 감소 효과 추정에 반영하였다. 사고재현을 통해 추정된 충돌속도를 보행자 사망확률모형의 주요 변수로 사용하였다. 모형의 개발을 위해서는 logistic regression 기법을 적용하였으며, 충돌안전기준의 주요 변수인 HIC(Head Injury Criterion)와 충돌속도의 변화에 따른 사망자수 감소효과를 계량화하여 제시하였다. 제안된 방법론은 향후 국내 실정에 부합되는 충돌안전기준의 개발, 보행자 보호를 위한 첨단 차량의 개발, 보행자 안전을 위한 정책 수립 등을 지원하는 중요한 역할을 수행할 것으로 기대된다.

• 대한안전경영과학회지
• /
• 제24권4호
• /
• pp.41-47
• /
• 2022

A reliable prediction model of national occupational accident fatality rate can be used to evaluate level of safety and health protection for workers in a country. Moreover, the socio-economic aspects of occupational accidents can be identified through interpretation of a well-organized prediction model. In this paper, we propose a machine learning based relative comparison methods to predict and interpret a national occupational accident fatality rate based on socio-economic indicators. First, we collected 29 years of the relevant data from 11 developed countries. Second, we applied 4 types of machine learning regression models and evaluate their performance. Third, we interpret the contribution of each input variable using Shapley Additive Explanations(SHAP). As a result, Gradient Boosting Regressor showed the best predictive performance. We found that different patterns exist across countries in accordance with different socio-economic variables and occupational accident fatality rate.

• 한국안전학회지
• /
• 제33권1호
• /
• pp.148-161
• /
• 2018

A traffic fatality by young people marked average annual decrease of 4.5% since 2011. Meanwhile, a traffic fatality by senior over 65 years old marked average annual increase of 7.9% for the last five years which means that the annual increase of traffic fatality by senior will be a serious problem. This study started questioning that senior drivers over 65 years old did not retain the same causal factor of fatal traffic accidents and thus extensively analyzed a risk of it by age group quantitatively, dividing the senior driver group into the early, middle and latter stages. Depending on the aging level, the risk of traffic fatality showed a wide difference in seven different types of traffic accidents generally, and happened to increase with latter and middle parts of the senior driver more than the early part. Therefore, this study proposes four policy suggestions: 1) The senior driver need to be offered customized driving educations and the improvement of road environment is also recommended. 2) Political assistance is needed to support and guide a safety related technology installation for the new or existing car. 3) Renewal of driving license and an aptitude test(physical examination, cognitive test) for drivers over 75 years old should take in a less than 3 years and an additional road test is needed as occasion demands. 4) Like the United States and Europe, development and extension of customized treatment guidebook for medical teams who examine senior drivers is needed and establishment of education and administration system that a supervisor of driving license renewal can impose safety restriction and American anonymity reporting system is considered to institutionalize in the medium to longer term.

• Nuclear Engineering and Technology
• /
• 제44권7호
• /
• pp.745-754
• /
• 2012

The correlations between Large Early Release Frequency (LERF) and Early Fatality need to be investigated for risk-informed application and regulation. In Regulatory Guide (RG) -1.174, while there are decision-making criteria using the measures of Core Damage Frequency (CDF) and LERF, there are no specific criteria on LERF. Since there are both huge uncertainties and large costs needed in off-site consequence calculation, a LERF assessment methodology needs to be developed, and its correlation factor needs to be identified, for risk-informed decision-making. A new method for estimating off-site consequence has been presented and performed for assessing health effects caused by radioisotopes released from severe accidents of nuclear power plants in this study. The MACCS2 code is used for validating the source term quantitatively regarding health effects, depending on the release characteristics of radioisotopes during severe accidents. This study developed a method for identifying correlations between LERF and Early Fatality and validates the results of the model using the MACCS2 code. The results of this study may contribute to defining LERF and finding a measure for risk-informed regulations and risk-informed decision-making.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2011년도 춘계학술대회
• /
• pp.177-183
• /
• 2011

Korea has performed strategies for the third industrial accident prevention in order to minimize industrial accident. However, the occupational fatality rate and industrial accident rate appears to be stagnated for 11 years. Therefore, this paper forecasts the occupational fatality rate and industrial accident rate for 10 years. Also, this paper applies regression method (RA), exponential smoothing method (ESM), double exponential smoothing method (DESM), autoregressive integrated moving average (ARIMA) model and proposed analytical function method (PAFM) for trend of industrial accident. Finally, this paper suggests fundamental strategies for industrial accident prevention by forecasting of industrial accident rate in the long term.

• Nuclear Engineering and Technology
• /
• 제37권3호
• /
• pp.245-258
• /
• 2005

This paper addresses two types of uncertainty: stochastic uncertainty and subjective uncertainty in probabilistic accident consequence assessments. The off-site consequence assessment code OSCAAR has been applied to uncertainty and sensitivity analyses on the individual risks of early fatality and latent cancer fatality in the population outside the plant boundary due to a severe accident. A new stratified meteorological sampling scheme was successfully implemented into the trajectory model for atmospheric dispersion and the statistical variability of the probability distributions of the consequence was examined. A total of 65 uncertain input parameters was considered and 128 runs of OSCAAR with 144 meteorological sequences were performed in the parameter uncertainty analysis. The study provided the range of uncertainty for the expected values of individual risks of early and latent cancer fatality close to the site. In the sensitivity analyses, the correlation/regression measures were useful for identifying those input parameters whose uncertainty makes an important contribution to the overall uncertainty for the consequence. This could provide valuable insights into areas for further research aiming at reducing the uncertainties.

• 한국자동차공학회논문집
• /
• 제18권3호
• /
• pp.104-109
• /
• 2010

The fatality of pedestrian accounts for about 21.2% of all fatality at 2007 year in Korea. In car to pedestrian accident it is very important to inspect the throw distance of pedestrian after collision for exact reconstructing of the accident. The variables that influence on the throw distance of pedestrian can be classified into the factors of vehicle and pedestrian, and road condition. It was simulated by PC-CRASH, a kinetic analysis program for a traffic accident in sedan type vehicle and SPSS program was used for regression analysis. From the results, the throw distance of pedestrian increased with the increasing of vehicle velocity, and decreased with the increasing of impact offset. Also it decreased with the increasing of velocity of pedestrian at accident, and throw distance at the road condition of wet was longer than that at dry condition. Finally, the regression model of sedan type vehicle on the throw distance of pedestrian was as follows; $$dist_i=2.39-0.11offset_i+0.59speed_i-545height_i-0.25walk_i+2.78wet_i+{\epsilon}_i$$.

• 한국자동차공학회논문집
• /
• 제23권5호
• /
• pp.553-563
• /
• 2015

Reportedly the fatality rate from secondary collision is six times higher than the average fatality rate from all traffic accidents. So prevention of the secondary collision is attracting significant attention from automotive industries. However, the secondary collision prevention systems that have been developed are not considering possibility of brake actuator failure that can occur by the impact during the initial collision. In this paper, a new system has been developed that could prevent secondary collision even in case of brake actuator failure by taking advantage of still operating actuators. In this system, a steering control is performed for maintaining a lane by using linear quadratic regulator. Additionally, the system attempts differential brake control with the remaining braking capability to stop the vehicle in the shortest distance. Through simulation in various collision scenarios, the system has demonstrated significant potential of preventing secondary collision that could otherwise have resulted in severe fatality.