• 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.

• 한국도로학회논문집
• /
• 제19권5호
• /
• pp.143-151
• /
• 2017

PURPOSES : The purpose of this study is to develop models of accidents occurring at circular intersections related to the time of day and night and driver gender, and to provide countermeasures for safer circular intersections. METHODS : Seventy intersections built before 2008 were surveyed for inclusion in the modeling. Traffic accident data from 2008 to 2014 were collected from the TAAS data set of the Road Traffic Authority. Sixteen variables explaining the accidents including geometry and traffic volume were selected from the literature and seven multiple linear regression models were developed using SPSS 20.0. RESULTS : First, the null hypotheses, that the number of traffic accidents are not related to driver gender or time of day, were rejected at a 5% level of significance. Second, seven statistically significant accident models with $R^2$ value of 0.643-0.890 were developed. Third, in daytime models by gender, when the right-turn-only lane was selected as the common variable, the number of lanes, presence of driveways and speed humps, diagrammatic exit destination sign, and total entering traffic volume were evaluated as specific variables. Finally, in nighttime models by gender, when the diagrammatic exit destination sign was selected as the common variable, total entering traffic volume, presence of right-turn-only lanes, number of circulatory road way lanes, and presence of splitter islands and driveways were identified as specific variables. CONCLUSIONS:This study developed seven accident models and analyzed the common and specific variables by time of day and gender. The results suggest approaches to providing countermeasures for safer circular intersections.

• 대한토목학회논문집
• /
• 제31권2D호
• /
• pp.203-208
• /
• 2011

우리나라 대부분의 도시는 지속적인 개발에 따라 교통 수요가 급속도로 증가하고 있다. 이에 따라 도로용량 증대를 위한 도로 확장 등이 이루어지고 있으나 동일 교통 특성을 지니는 구간 내에서 일부 구간만의 확장으로 전체적인 주행 차로 수 균형이 유지되고 있지 않아 차량 소통 및 교통안전 측면에서 문제가 발생하고 있다. 본 연구에서는 국도 32호선 대전광역시 통과 구간 중 직진 주행 차로 수가 일치하지 않는 구간을 중심으로 차로 수 불일치에 따른 문제점을 분석하고 차로 수를 일치하였을 경우의 효과에 대한 분석을 실시하였다. 분석 방법으로는 마이크로 시뮬레이션인 VISSIM을 활용하였으며 개선 전후의 평균 통행속도, 지체도, 상충 수 등을 비교 분석하였다. 분석결과 주행 차로 수 일치에 따라 지체도가 감소하고 평균 통행속도가 증가하였다. 본 연구결과는 주행 차로 수 일치의 중요성을 부각시켜 향후 도로확장 등 개선 공사 시행에서 병목현상 개선 및 차량 상충 감소에 기여할 것으로 판단된다.

• 한국도로학회논문집
• /
• 제14권2호
• /
• pp.145-155
• /
• 2012

현재 서울시는 대중교통 활성화 정책에 따라 버스전용차로제도를 실시하고 있다. 과거 가로변버스전용차로 설치를 시작으로 현재에는 중앙버스전용차로 설치구간도 증가하고 있다. 본 연구의 목적은 이 중앙버스전용차로와 가로변버스전용차로에서 버스사고에 영향을 미치는 요인을 분석하는데 있다. 분석방법으로 교통사고가 확률적으로 극히 드물게 일어난다는 점을 생각하여 포아송 회귀모형과 음이항 회귀모형을 선택하였으며, 과산포 존재여부에 따라 음이항 회귀모형으로 최종모형을 정립하였다. 중앙버스전용차로구간은 버스노선수, 중앙차로 진출입 유형수, 중앙차로 정지선 후퇴유무, 중앙차로 정지선과 횡단보도 이격거리, 교통량, 가변차로 정류장 정차노선수 6개의 변수에서 버스사고에 유의한 영향을 미치는 것으로 나타났다. 가로변버스전용 차로구간은 우회전 버스노선수, 상습 불법주정차 유무, 보행신호시간, 토지이용형태 4개의 변수에서 버스사고에 유의한 영향을 미치는 것으로 나타났다.

• 한국도로학회논문집
• /
• 제20권1호
• /
• pp.117-126
• /
• 2018

PURPOSES : The purpose of this paper is to analyze the change in lane reflection performance through lane washing and sweeping on highway lanes. METHODS : This paper compared and analyzed the changes in lane reflection performance before and after lane washing and sweeping. The research method was as follows. First, we selected four research sites on the Gyeong-bu Highway. Second, the parameters affecting lane reflection performance are classified into luminance, brightness, and number of glass beads. Third, the change in reflection performance was measured after washing /sweeping at the same place after studying 60m of the unwashed/unswept area. Fourth, the measurement results were compared and analyzed before and after lane washing/sweeping. RESULTS : The results of this study are as follows. First, lane washing improved the luminance and brightness by 4.2~21.4% and 1.4~5.1%, respectively, and reduced the number of glass beads per wash by 0.2~1.2%. Second, lane sweeping improved the luminance and brightness by 2.3~8.5% and 0.8~2.3%, respectively, and reduced the number of glass beads per sweep by 0.8~4.9%. CONCLUSIONS : By comparing the results of lane washing and sweeping, it was found that compared to lane sweeping, lane washing improved the luminance and fewer glass beads were dropped.

• 한국ITS학회 논문지
• /
• 제8권3호
• /
• pp.42-51
• /
• 2009

우리나라는 고속도로 차로 수에 따라 차종별로 통행차로를 지정하는 제도를 운영하고 있으며, 그 동안 제도의 유효성 논란 속에 폐지와 운영을 반복하며 시행되고 있다. 본 논문에서는 제도의 유효성을 검증하기 위해 고속도로 10개 구간을 대상으로 차로통행방법 위반율과 교통사고와의 연관성을 분석하였다. 그 결과 양(+)의 상관관계가 있는 것으로 나타나 위반차량에 대한 적극적인 단속이 요구되며, 본 논문에서는 차량번호판의 영상인식에 기반한 자동단속시스템 구축 방안을 제시하였다.

• 교육녹색환경연구
• /
• 제16권1호
• /
• pp.20-29
• /
• 2017

5개 신도시내 초등학교별 장기(24년간) 학생수 증감추세를 9개 계획요소(개발밀도, 다양한 사설학원의 입지 가능 여부, 학교 위치, 통학구역 형태, 인근 학교와의 거리 공동통학구역 운영 여부, 보행자전용가로 조성, 접도조건, 통학로상 입체보차분리시설 유무 등)별 가설을 설정하고, 이를 바탕으로 장기 학생수 증감추세와의 연관성 판단기준에 따라 분석한 결과는 다음과 같다. 첫째, 개발밀도, 학교 위치, 통학구역 형태, 인근 학교 거리, 입체보차분리시설 설치 등의 계획요소는 뚜렷한 연관성이 뚜렷하게 나타났다. 둘째, 사설학원 입지와 인근학교 거리 보행자전용가로 설치의 계획요소는 약간의 연관성을 보였다. 셋째, 접도 차선수와 공동통학구역 계획요소는 연관성이 없었다. 본 연구는 수도권 1기 5개 신도시 89개 초등학교만을 조사 분석한 결과이기 때문에 이를 일반화하는데 한계가 있고, 분석요소 및 평가기준을 더욱 정교화할 필요가 있어 이에 대한 후속연구가 필요하다.

• 자동차안전학회지
• /
• 제16권1호
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• 한국도로학회논문집
• /
• 제20권2호
• /
• pp.119-126
• /
• 2018

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.

• 한국도로학회논문집
• /
• 제18권6호
• /
• pp.153-160
• /
• 2016

OBJECTIVES : The objective of this study is to develop a traffic accident model of a roundabout based on the type of land use. METHODS : The traffic accident data from 2010 to 2014 were collected from the "traffic accident analysis system (TAAS)" data set of the Road Traffic Authority. A multiple linear regression model was utilized in this study to analyze the accidents based on the type of land use. Variables such as geometry and traffic volume were used to develop the accident models based on the type of land use. RESULTS : The main results are as follows. First, the null hypothesis that the type of land use does not affect the number of accidents is rejected. Second, four accident models based on the type of land use have been developed, which are statistically significant (high $R^2$ values). Finally, the total entering and circulating volumes, area of the central island, number of speed breakers, mean number of entry lanes, diameter of the inscribed circle, mean width of the entry lane, area of the roundabout, bus stops, and number of circulatory roadways are analyzed to see how they affect the accident for each type of land use. CONCLUSIONS : The development of the accident models based on the type of land use has revealed that the accident factors at a roundabout are different for each case. Thus, more speed breakers in commercial areas and an inscribed circle of proper diameter in commercial and residential areas are determined to be important for reducing the number of accidents. Additionally, expanding the width of the entry lanes, decreasing the area of the roundabouts in residential areas, and reducing the conflict factors such as bus stops in green spaces are determined to be important.