• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5D
• /
• pp.453-459
• /
• 2010

In the study of traffic safety, it is utmost important to obtain more reliable estimates of the expected crashes for a site (or a segment). The observed crashes have been mainly used as the estimate of the expected crashes in Korea, while the empirical Bayes (EB) estimates based on the Poisson-gamma mixture model have been used in the USA and several European countries. Although numerous studies have used the EB method for estimating the expected crashes and/or the effectiveness of the safety countermeasures, no past studies examine the difference in the estimation errors between the two estimates. Thus, this study compares the estimation errors of the two estimates using a Monte Carlo simulation study. By analyzing the crash dataset at 3,000,000 simulated sites, this study reveals that the estimation errors of the EB estimates are always less than those of the observed crashes. Hence, it is imperative to incorporate the EB method into the traffic safety research guideline in Korea. However, the results show that the differences in the estimation errors between the two estimates decrease as the uncertainty of the prior distribution increases. Consequently, it is recommended that the EB method be used with reliable hyper-parameter estimates after conducting a comprehensive examination on the estimated negative binomial model.

• Journal of Korean Society of Transportation
• /
• v.20 no.7
• /
• pp.197-204
• /
• 2002

교통사고예측 및 예방을 위해서는 실제적으로 도로설계과정에서 제어가 가능한 도로 기하구조요소에 대한 사고관계를 파악함이 타당하다. 즉, 도로의 설계자는 도로건설에 앞서 기하구조요소와 사고와의 관계를 현장자료를 통해 정확히 밝혀 도로설계에 반영해야 한다. 이를 위해, 교통사고의 빈도분포를 박히는 것은 가장 기본이 되는 일이며, 교통사고 예측모형개발에 선행되어야 한다. 일반적으로 교통사고건수의 경우 분산이 평균보다 큰 과분산(overdispersion)의 특징을 가지고 있어 음이항 분포를 따른다고 알려져 있다. 따라서 본 논문은 사고모형의 개발에 앞서, 사고발생지점에 대한 도로설계요소와 기타 잠재적인 사고발생 관련요인이 비교적 잘 파악되어있는 호남고속도로를 중심으로 평면 선형상 곡선부에 대하여 교통사고의 분포를 적합도 검정을 통해 알아보고자 하였다. 사고자료는 한국도로송사의 호남고속도로 5년(1996∼2000)간 자료를 분석에 맞게 정리하였으며, 강민욱과 송봉수(2002)에서 제시한 평면선형에 있어서의 구간분할법을 이용하여 배향곡선구간과 단일곡선구간에 대한 사고분석을 하였다. 적합도 분석결과, 예상대로 음이항분포가 사고건수를 설명하기에 가장 적합한 확률분포로 제시되었으며, 이를 통해 최우추정법을 이용한 음이항회귀모형을 개발하였다. 구간분할법을 적용한 음이항회귀모형의 경우, 기존의 확률회귀토형에 비하여 높은 결정계수를 갖았으며, 모형에서 적용된 기하구조요소로는 차량 노출계수, 곡선반경, 단위거리 당 편경사변화값 등이다.

• Journal of Korean Society of Transportation
• /
• v.25 no.2 s.95
• /
• pp.63-72
• /
• 2007

The purpose of this study is to develop a traffic characteristic analysis, a correlation analysis with the variables of traffic characteristics, and accident estimation models while recognizing the seriousness of the traffic accidents. The analyses deal with the 181 4-legged signalized intersections that accounted for 1,183 out of 3,115 accidents in Cheongju in 2004. After measuring ADT, intersection area, average lane width, elevation, and other items as independent variables and the number of traffic accidents, the traffic accident rate (accidents per million entering vehicles) and equivalent property damage only (EPDO) figures as dependent variables which are estimated as influencing signalized intersection accidents, the estimation models are developed using correlation analysis and multiple regression analysis. In the analysis of the number of traffic accidents, the model indicates an $R^2$ of 0.612, and five independent variables are taken as significant factors. In the analysis of traffic accident rates, the model indicates an $R^2$ of 0.304 and five significant factors, including intersection area and ADT. Also, for the analysis or the EPDO numbers, which coincides with understanding the seriousness of the traffic accidents and the traffic characteristic analysis, the model indicates an $R^2$ of 0.559, and four independent variables (ADT, main street average lane width, elevation, and speed limit) as significant factors.

• Journal of Korean Society of Transportation
• /
• v.35 no.2
• /
• pp.160-168
• /
• 2017

In the past 10 years, the accidents caused by drowsy driving have occupied about 23% of all traffic accidents in Korea expressway network and this rate is the highest one among all accident causes. Unlike other types of accidents caused by speeding and distraction to the road, the accidents by drowsy driving should be managed differently because the drowsiness might not be controlled by human's will. To reduce the number of accidents caused by drowsy driving, researchers previously focused on the spot based analysis. However, what we actually need is a segment (link) and occurring time based analysis, rather than spot based analysis. Hence, this research performs initial effort by adapting link concept in terms of drowsy driving on highway. First of all, we analyze the accidents caused by drowsy in historical accident data along with their road environments. Then, links associate with driving time are analyzed using digital tachograph (DTG) data. To carry this out, negative binomial regression models, which are broadly used in the field, including highway safety manual, are used to define the relationship between the number of traffic accidents on expressway and drivers' behavior derived from DTG. From the results, empirical Bayes (EB) and potential for safety improvement (PSI) analysis are performed for potential risk segments of accident caused by drowsy driving on the future. As the result of traffic accidents caused by drowsy driving, the number of the traffic accidents increases with increase in annual average daily traffic (AADT), the proportion of trucks, the amount of DTG data, the average proportion of speeding over 20km/h, the average proportion of deceleration, and the average proportion of sudden lane-changing.

• Journal of Korean Society of Transportation
• /
• v.27 no.3
• /
• pp.81-90
• /
• 2009

The safety management of a road network comprises four basic inter-related components：identification of sites(black spot) requiring safety investigation, diagnosis of safety problems, selection of feasible treatments for potential treatment candidates, and prioritization of treatments given limited budgets(Persaud, 2001). Identification process of selecting black spot is very important for efficient investigation of sites. In this study, the accident prediction model for EB method was developed by using accident data and geometric conditions of black spots selected from four-leg signalized intersections in In-cheon City for three years (2004-2006). In addition, by comparing the rank nomination technique using EB method to that by using accident counts, we managed to show the problems which the existing method have and the necessity for developing rational prediction model. As a result, in terms of total number of accidents, both the counts predicted by existing non-linear regression model and that by EB method have high good of fitness, but EB method, considering both the accident counts by sites and total number of accident, has better good of fitness than non-linear poison model. According to the result of the comparison of ranks nominated for treatment between two methods, the rank for treatment of almost sites does not change but SeoHae intersection and a few other intersections have significant changes in their rank. This shows that, with the technique proposed in the study, the RTM problem caused by using real accident counts can be overcome.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5585-5593
• /
• 2014

This study tested the hypothesis that the significance of the heterogeneous dispersion parameter in safety performance function (SPF) used to estimate the expected crashes is affected by the endogenous heterogeneous prior distributions, and analyzed the impacts of the mis-specified dispersion parameter on the evaluation results for traffic safety countermeasures. In particular, this study simulated the Poisson means based on the heterogeneous dispersion parameters and estimated the SPFs using both the negative binomial (NB) model and the heterogeneous negative binomial (HNB) model for analyzing the impacts of the model mis-specification on the mean and dispersion functions in SPF. In addition, this study analyzed the characteristics of errors in the crash reduction factors (CRFs) obtained when the two models are used to estimate the posterior means and variances, which are essentially estimated through the estimated hyper-parameters in the heterogeneous prior distributions. The simulation study results showed that a mis-estimation on the heterogeneous dispersion parameters through the NB model does not affect the coefficient of the mean functions, but the variances of the prior distribution are seriously mis-estimated when the NB model is used to develop SPFs without considering the heterogeneity in dispersion. Consequently, when the NB model is used erroneously to estimate the prior distributions with heterogeneous dispersion parameters, the mis-estimated posterior mean can produce large errors in CRFs up to 120%.

• Journal of Korean Society of Transportation
• /
• v.30 no.2
• /
• pp.101-116
• /
• 2012

Accident prediction models have been utilized to predict accident possibilities in existing or projected freeways and to evaluate programs or policies for improving safety. In this study, a traffic accident prediction model for freeways was developed for the above purposes. When selecting variables for the model, the highest priority was on the ease of both collecting data and applying them into the model. The dependent variable was set as the number of total accidents and the number of accidents including casualties in the unit of IC(or JCT). As a result, two models were developed; the overall accident model and the casualty-related accident model. The error structure adjusted to each model was the negative binomial distribution and the Poisson distribution, respectively. Among the two models, a more appropriate model was selected by statistical estimation. Major nine national freeways were selected and five-year dada of 2003~2007 were utilized. Explanatory variables should take on either a predictable value such as traffic volumes or a fixed value with respect to geometric conditions. As a result of the Maximum Likelihood estimation, significant variables of the overall accident model were found to be the link length between ICs(or JCTs), the daily volumes(AADT), and the ratio of bus volume to the number of curved segments between ICs(or JCTs). For the casualty-related accident model, the link length between ICs(or JCTs), the daily volumes(AADT), and the ratio of bus volumes had a significant impact on the accident. The likelihood ratio test was conducted to verify the spatial and temporal transferability for estimated parameters of each model. It was found that the overall accident model could be transferred only to the road with four or more than six lanes. On the other hand, the casualty-related accident model was transferrable to every road and every time period. In conclusion, the model developed in this study was able to be extended to various applications to establish future plans and evaluate policies.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.4
• /
• pp.1279-1287
• /
• 2014

The purpose of this study is to develop the U-turn accident model at signalized intersections in urban areas. The characteristics of the accidents which are associated with U-turn operation at 3 and 4-legged signalized intersections was analyzed and the U-turn accident model was developed by regression analysis in Changwon city. First, in order to analyze the effectiveness on traffic accidents by U-turn installation, the difference of mean of traffic accident number are measured between two groups which are composed by whether or not U-turn installation the groups by Mann-Whitney U test. The result of significance test showed that intergroup comparison on mean by accident types made difference except rear-end accident type and by accident locations exit section only showed difference in significance level at 4-legged intersections, so the accident number have more where the U-turn is permitted than not. Response measures about the number of accidents were classified by whether accidents occurred and accident model were constructed using binomial logistic regression analysis method. The developed models show that the variables of conflict traffic, number of opposing lane are adopted as independent variable for both intersections. The variables of longitudinal grade for 3-legged signalized intersection and number of crosswalk for 4-legged signalized intersection at which the U-turn is permitted is adopted as independent variable only. These study results suggest that U-turn would be permitted at the intersection where the number of opposing lane is more than 3.5 each, the longitudinal grade of opposing road is upward flow and there is need to establish the U-turn traffic sign at signalized intersections.

• Journal of Korean Society of Transportation
• /
• v.32 no.2
• /
• pp.170-178
• /
• 2014

Until now, several research on the relationship of traffic crash occurrences and geometric had been conducted and revealed that projects of road alignment, geometric improvement and hazardous segment selection reduced the number of accidents and accident severities. However, such variables did not consider the non-homogeneous characteristics of roadway segments due to the difficulty of data collection, which results in under-estimation of the standard error affecting the overall modeling goodness-of-fit. This study highlights the importance of non-homogeneity by looking at the effect of the non-homogeneous geometric variables through the modeling process. The model delivers meaningful results when using some geometric variables without relevant geometrics' variables.

• Journal of Korean Society of Transportation
• /
• v.30 no.5
• /
• pp.3-10
• /
• 2012

This study dealt with traffic accidents occurring within roundabouts. The objective was to develop roundabout accident models for different driving types by using simultaneous equations. In pursuing the above, this study used a statistical program SPSS 17.0 to accommodate data from 148 accidents occurred within 39 roundabouts of Korea. In addition, the 2SLS(2 stage least square) estimation method was adopted to calibrate the models. The main results are as follows. First, both the number of accidents and the EPDO were evaluated to have bilateral relationships. Second, all 6 different simultaneous equation models according to driving types were found to be statistically significant. Third, the developed models were compared to each other with respect to either common or specific variables. Finally, variables such as ADT, conflicting rate, heavy vehicle ratio, circulatory roadway width, number of circulatory roadway lane, approach lane width, average approach lanes, parking places, and bus stops were selected as independent variables for the models.