PURPOSES : The purpose of this study is to compare applicability, explanation power, and flexibility of traffic accident models between estimating model using the statistical method and the machine learning method. METHODS: In order to compare and analyze traffic accident models between model estimated using the statistical method and machine learning method, data acquisition was conducted, and traffic accident models were estimated using statistical methods such as negative binomial regression model, and machine learning methods such as a generalized regression neural network (GRNN). Then, the fitness of model as R2, root mean square error (RMSE), mean absolute percentage error (MAPE), accuracy, etc., were determined to compare the traffic accident models. RESULTS: The results showed that the annual average daily traffic (AADT), speed limits, number of lanes, land usage, exclusive right turn lanes, and front signals were significant for both traffic accident models. The GRNN model of total traffic accidents had been better statistical significant with R2: 0.829, RMSE: 2.495, MAPE: 32.158, and Accuracy: 66.761 compared with the negative binomial regression model with R2: 0.363, RMSE: 9.033, MAPE: 68.987, and Accuracy: 8.807. The GRNN model of injury traffic accidents also showed similar results of model’s statistical significance. CONCLUSIONS: Traffic accident models estimated with GRNN had better statistical significance compared with models estimated with statistical methods such as negative binomial regression model.

PURPOSES: The purpose of this study is to develop a crash prediction model at signalized intersections, which can capture the randomness and uncertainty of traffic accident forecasting in order to provide more precise results. METHODS: The authors propose a random parameter (RP) approach to overcome the limitation of the Count model that cannot consider the heterogeneity of the assigned locations or road sections. For the model’s development, 55 intersections located in the Daejeon metropolitan area were selected as the scope of the study, and panel data such as the number of crashes, traffic volume, and intersection geometry at each intersection were collected for the analysis. RESULTS: Based on the results of the RP negative binomial crash prediction model developed in this study, it was found that the independent variables such as the log form of average annual traffic volume, presence or absence of left-turn lanes on major roads, presence or absence of right-turn lanes on minor roads, and the number of crosswalks were statistically significant random parameters, and this showed that the variables have a heterogeneous influence on individual intersections. CONCLUSIONS : It was found that the RP model had a better fit to the data than the fixed parameters (FP) model since the RP model reflects the heterogeneity of the individual observations and captures the inconsistent and biased effects.

PURPOSES :This study deals with traffic accidents involving trucks. The objective of this study is to develop a traffic accident model for trucks at roundabouts.METHODS :To achieve its objective, this study gives particular attention to develop appropriate models using Poisson and negative binomial regression models. Traffic accident data from 2007 to 2014 were collected from TAAS data set of road traffic authority. Thirteen explanatory variables such as geometry and traffic volume were used.RESULTS :The main results can be summarized as follows: (1) two statistically significant Poisson models (ρ2 = 0.398 and 0.435) were developed, and (2) the analysis revealed the common variables to be traffic volume, number of exit lanes, speed breakers, and truck apron width.CONCLUSIONS :Our modeling reveals that increasing the number of speed breakers and speed limit signs, and widening the truck apron width are important for reducing the number of truck accidents at roundabouts.

PURPOSES: This study deals with the traffic accidents classified by the traffic analysis zone. The purpose is to develop the accident density models by using zonal traffic and socioeconomic data. METHODS : The traffic accident density models are developed through multiple linear regression analysis. In this study, three multiple linear models were developed. The dependent variable was traffic accident density, which is a measure of the relative distribution of traffic accidents. The independent variables were various traffic and socioeconomic variables. CONCLUSIONS : Three traffic accident density models were developed, and all models were statistically significant. Road length, trip production volume, intersections, van ratio, and number of vehicles per person in the transportation-based model were analyzed to be positive to the accident. Residential and commercial area ratio and transportation vulnerability ratio obtained using the socioeconomic-based model were found to affect the accident. The major arterial road ratio, trip production volume, intersection, van ratio, commercial ratio, and number of companies in the integrated model were also found to be related to the accident.

PURPOSES : This study tries to develop the accident models of 4-legged signalized intersections in Busan Metropolitan city with random parameter in count model to understanding the factors mainly influencing on accident frequencies. METHODS: To develop the traffic accidents modeling, this study uses RP(random parameter) negative binomial model which enables to take account of heterogeneity in data. By using RP model, each intersection’s specific geometry characteristics were considered. RESULTS : By comparing the both FP(fixed parameter) and RP modeling, it was confirmed the RP model has a little higher explanation power than the FP model. Out of 17 statistically significant variables, 4 variables including traffic volumes on minor roads, pedestrian crossing on major roads, and distance of pedestrian crossing on major/minor roads are derived as having random parameters. In addition, the marginal effect and elasticity of variables are analyzed to understand the variables’impact on the likelihood of accident occurrences. CONCLUSIONS :This study shows that the uses of RP is better fitted to the accident data since each observations’specific characteristics could be considered. Thus, the methods which could consider the heterogeneity of data is recommended to analyze the relationship between accidents and affecting factors(for example, traffic safety facilities or geometrics in signalized 4-legged intersections).

PURPOSES : The purposes of this study are to compare the day and night characteristics and to develop the models of traffic accidents. in Rural Signalized Intersections METHODS : To develop day and night traffic accident models using the Negative Binomial Model, which was constructed for 156 signalized intersections of rural areas, through field investigations and casualty data from the National Police Agency. RESULTS : Among a total of 17 variances, the daytime traffic accident estimate models identified a total of 9 influence factors of traffic accidents. In the case of nighttime traffic accident models, 11 influence factors of traffic accidents were identified. CONCLUSIONS: By comparing the two models, it was determined that the number of main roads was an independent factor for daytime accidents. For nighttime accidents, several factors were independently involved, including the number of entrances to sub-roads, whether left turn lanes existed in major roads, the distances of pedestrian crossings to main roads and sub-roads, lighting facilities, and others. It was apparent that if the same situation arises, the probability of an accident occurring at night is higher than during the day because the speed of travel through intersections in rural areas is somewhat higher at night than during the day.

이 연구는 청주시의 가로구간 교통사고를 다루고 있다. 연구의 목적은 가로구간의 기능별 사고모형을 개발하는 데 있다. 이를 위해서 이 연구는 전체 472개의 세부구간으로 분리된 주간선도로와 보조간선도로의 사고 자료를 이용하여 적합한 모형을 개발하는데 중점을 두고 있다. 연구의 주요 결과는 다음과 같다. 첫째, 주간선과 보조간선도로의 사고특성에 대한 t 검정은 두 도로의 사고건수와 EPDO에 차이가 있는 것으로 나타나 기능별 사고모형 개발이 적절한 것으로 분석된다. 둘째, 주간선도로의 EPDO와 사고건수는 모두 ZINB모형이 적합한 것으로 분석된다. 셋째, 보조간선도로 EPDO는 ZINB모형, 그리고 사고건수는 ZIP모형이 최적인 것으로 분석된다. 마지막으로 주간선도로 사고모형(ZINB)의 공통변수는 교통량과 굴곡점수, 보조간선도로의 EPDO모형(ZINB)과 사고건수모형(ZIP) 공통변수는 평균종단경사인 것으로 평가된다.

본 연구는 도로연장측면에서 본선에 비해 상대적으로 연결로에서 발생하는 사고빈도가 높고, 교통사고가 증가하는 추세인 고속도로 연결로의 교통사고 예측모형의 개발에 초점을 두었다. 연결로 유형별(직결, 준직결, 루프)로 통계적으로 유의한 사고인자를 선정하고, 사고율과의 관계가 비선형 임을 분석하여 변수를 변형(Variables Transformation)하여 All possible 방식으로 예측모형을 개발하고, 통계적 진단 및 검증을 거쳐 유의성을 확인하였으며 이에 기존 개발 모형에 비해 예측력이 더욱 우수한 결과를 보였다. 개발된 사고예측모형은 보다 비용면에서 효율적이고, 안전한 트럼펫형 IC 연결로의 설계와 연결로 교통사고 원인분석에 활용될 수 있을 것으로 기대된다.