• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.167-173
• /
• 2009

It is important to study on the traffic accident severity reduction because traffic accident is an issue that is directly related to human life. Therefore, this research developed countermeasure to reduce traffic accident severity considering various factors that affect the accident severity. This research developed the Accident Severity Prediction Model using the collected accident data from Seohaean Expressway in 2004~2006. Through this model, we can find the influence factors and methodology to reduce accident severity. The results show that speed limit violation, vehicle defects, vehicle to vehicle accident, vehicle to person accident, traffic volume, curve radius CV(Coefficient of variation) and vertical slope CV were selected to compose the accident severity model. These are certain causes of the severe accident. The accidents by these certain causes present specific sections of Seohaean Expressway. The results indicate that we can prevent severe accidents by providing selected traffic information and facilities to drivers at specific sections of the Expressway.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.12-28
• /
• 2019

Road geometry is one of the many factors that cause crashes, but the effect on traffic accident depends on weather conditions even under the same road geometry. This study identifies the variables affecting the crash severity by matching the highway accident data and weather data for 14 years from 2001 to 2014. A hierarchical ordered Logit model is used to reflect the effects of road geometry and weather condition interactions on crash severity, as well as the correlation between individual crashes in a region. Among the hierarchical models, we apply a random intercept model including interaction variables between road geometry and weather condition and a random coefficient model including regional weather characteristics as upper-level variables. As a result, it is confirmed that the effects of toll, ramp, downhill slope of 3% or more, and concrete barrier on the crash severity vary depending on weather conditions. It also shows that the combined effects of road geometry and weather conditions may not be linear depending on rainfall or snowfall levels. Finally, we suggest safety improvement measures based on the results of this study, which are expected to reduce the severity of traffic accidents in the future.

• International Journal of Highway Engineering
• /
• v.10 no.4
• /
• pp.199-211
• /
• 2008

This study deals with the side right-angle collisions of 4-legged signalized intersections in Cheongju. The goals are to analyze the characteristics of accidents and to find out the accident factors that affect severity using ordered probit model. In pursuing the above, the study uses the data of 580 side right-angle collisions occurred at the 181 intersections(2004-2005). The analyses show that more accidents were occurred in the nighttime and in going straight. The main cause was analyzed to be the red-light violation. Also, the main results of modeling are the following, First, the likelihood ratio index is 0.094 and t-ratio values that explain goodness of fit are significant. Second, minor road traffic volumes, minor road lanes, major road left-turn lanes, major road left-turn signal, major road yellow signal time, cross angle, major and minor road speed limits are significant factors affecting crash severities at signalized intersections.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.1-12
• /
• 2017

Traffic accidents are caused by a combination of human factors, vehicle factors, and environmental factors. In the case of traffic accidents where rental cars are involved, the possibility and the severity of traffic accidents are expected to be different from those of other traffic accidents due to the unfamiliar environment of the driver. In this study, we developed a model to forecast the severity of rental car accidents by using Naive Bayes classifier for Busan, Gangneung, and Jeju city. In addition, we compared the prediction accuracy performance of two models where one model uses the variables of which statistical significance were verified in a prior study and another model uses the entire available variables. As a result of the comparison, it is shown that the prediction accuracy is higher when using the variables with statistical significance.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.2
• /
• pp.165-174
• /
• 2021

The construction industry causes the most accidents and fatalities among all industries. Although many efforts have been made to reduce safety accidents in construction, the study on the lost workdays that return to work place is insufficient. Therefore, this study proposes a model that classifies the lost workdays lost into moderate and severity, and derives the importance of variable and analyzes important factors through the trained random forest model. We analyze the learning process of the random forest which is a black box model, and extracted important variables that impact on the severity of the lost workdays through the extracted feature importance. The factors existing inside were analyzed through the extracted variables. The purpose of this study is to analyze the accident case data at the construction site through a random forest model and to review variables that have a high impact on the lost workdays. In the future, this sutdy can apply to improve construction safety management and reduce the accident of industrial accidents.

• Journal of Korean Society of Transportation
• /
• v.26 no.2
• /
• pp.17-24
• /
• 2008

Traffic accident forecasting model has been developed steadily to understand factors affecting traffic accidents and to reduce them. In Korea, the length of highways is over 3,000km, and it is within the top ten in the world. However, the number of accidents-per-one kilometer highway is higher than any other countries. The rapid increase of travel demand and transportation infrastructures since 1980's may influence on the high rates of traffic accident. Accident severity is one of the important indices as well as the rate of accident and factors such as road geometric conditions, driver characteristics and type of vehicles may be related to traffic accident severity. However, since all these factors are interacted complicatedly, the interactions are not easily identified. A structural equations model is adopted to capture the complex relationships among variables. In the model estimation, we use 2,880 accident data on highways in Korea. The SEM with several factors mentioned above as endogenous and exogenous variables shows that they have complex and strong relationships.

• International Journal of Highway Engineering
• /
• v.11 no.1
• /
• pp.153-164
• /
• 2009

This Paper presents the severity analysis result of the year 2006 national pedestrian crashes using the data base of 37,589 records prepared for the National Police Bureau. A set of attributing factors considered to affect pedestrian crash patterns were selected, and their contributing effects were investigated by applying the Ordered Logit Model. This model was selected because this model has been able to afford satisfactory results when the dependent variable involved ordered severity levels; fatal, injury, and property- damage-only in this investigation. The investigation has unveiled the followings; First, the pedestrian crash patterns were dependent upon human -drivel and pedestrian- characteristics including gender, age, and drinking conditions. Second, other contributing factors included vehicle, roadway geometric, weather, and hour of day characteristics. Third, seasonal effect was not contributive to crash patterns. Finally, the application of the Ordered Logit Model facilitated the ordered severity level analysis of the pedestrian crash data. This paper concludes that conventional wisdom on the pedestrian crash characteristics is largely truthful. However, this conclusion is limited only to the data used in this analysis, and further research is required for its generalization.

• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.103-114
• /
• 2011

In this study, we discuss a fatal accident severity model obtained from the analysis of 112 crash sites collected since 2000, and the resulting relationship between fatal accidents and roadway geometry design. From the 720 times computer simulations for improving driving safety, we then reached the following conclusions:. First, the result of cross and frequency-analyses on the car accident sites showed that 43.7% of the accidents occurred on the curved roads, 60.7% on the vertical curve section, 57.2% on the roadways with radius of curvature of 0 to 24m, 83.9% on the roads with superelevation of 0.1 to 2.0% and 49.1% on the one-way 2-lane roads; vehicle types involved are passenger vehicles (33.0%), trucks (20.5%) and buses (14.3%) in order of frequency. The results also show that the superelevation is the most influencing factor for the fatal accidents. Second, employing the Ordered Probit Model (OPM), we developed a severity model for fatal accidents being a function of on various road conditions so as to the damages can be predicted. The proposed model possibly assists the practitioners to predict dangerous roadway segments, and to take appropriate measures in advance. Third, computer simulation runs show that providing adequate superelevation on the segment where a fatal accident occurred could reduce similar fatal accidents by at least 85%. This result indicates that the regulations specified in the Rule for Road Structure and Facility Standard (description and guidelines) should be enhanced to include more specific requirement for providing the superelevation.

• Journal of Korean Society of Transportation
• /
• v.16 no.4
• /
• pp.187-194
• /
• 1998

본 연구는 교통사고 심각도와 관련된 중요변수를 찾고 이들 변수를 바탕으로 신경망, Decision Tree, 로지스틱 회귀분석을 이용하여 사고 심각도 분류 예측모형을 추정하였다. 다수의 범주형 변수로 이루어진 교통사고 통계원표상의 설명변수 들로부터 사고 심각도 변화에 영향력 있는 변수 선택을 위하여 독립성 검정을 위한 $x^2$ test와 Decision Tree를 이용하였고, 선택된 변수들은 신경망과 로지스틱 회귀분석의 기초로 이용되었다. 분석결과 세가지기법간에 분류정확도에는 유의한 차이가 없는 것으로 나타났다. 그러나 Decision Tree가 설명변수 선택능력과 분석수행시간, 사고 심각도 결정요인 식별의 용이함 측면에서 범주형 종속변수인 사고 심각도의 분석에 적합한 것으로 보이며 사고 심각도에는 보호장구가 가장 큰 영향을 미치는 것으로 재입증되었다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.6
• /
• pp.133-144
• /
• 2012

This study focused on estimating influential factors of traffic accidents and analyzing traffic accident severity of elderly and non elderly using traffic accident data. In order to reclassify elderly and non elderly traffic accident by a statistical method from entire traffic accident data, multiple discriminant analysis was applied. Also ordered logit model was applied for analyzing traffic accident severities using traffic accident severities as an independent variable and transportation facilities, road conditions and human characteristics as dependent variables. As results of the comparison between elderly and non elderly traffic accident, the traffic accident severity was affected by the age, types of traffic accidents, human characteristics and road conditions as well. Also, transportation facilities and road conditions affected to more elderly traffic accident than non elderly. Therefore, traffic accident severity would be decreased with the improvement of transportation facilities and road conditions for the elderly.