• 한국도로학회논문집
• /
• 제17권3호
• /
• pp.107-115
• /
• 2015

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.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.15-23
• /
• 2020

In this paper, we propose a new method to detect traffic accidents in video from vehicle-mounted cameras (vehicle black box). We use the distance between vehicles to determine whether an accident has occurred. To calculate the position of each vehicle, we use object detection and tracking method. By the way, in a crowded road environment, it is so difficult to decide an accident has occurred because of parked vehicles at the edge of the road. It is not easy to discriminate against accidents from non-accidents because a moving vehicle and a stopped vehicle are mixed on a regular downtown road. In this paper, we try to increase the accuracy of the vehicle accident detection by using not only the motion of the surrounding vehicle but also ego-motion as the input of the Recurrent Neural Network (RNN). We improved the accuracy of accident detection compared to the previous method.

• 한국안전학회지
• /
• 제32권3호
• /
• pp.74-82
• /
• 2017

This study was conducted to test the impacts of distractions caused by smartphones on pedestrians whilst walking alongside or across vehicular traffic in a high-density urban zone in South Korea. Through this study, we propose objective evidence for a link between the risk of traffic accidents and distractions from smartphones for pedestrians because of less likely notice activities surrounding road along their walking. This means that smartphones usage may cause inattentional blindness even during a simple activity that should require few cognitive resources. We conducted an experiment comparing pedestrian behavioral patterns of walking with smartphone distractions (such as listening to music with earphones or sending text messages) and normal walking without any distractions. In the experiment, participants walked along a pedestrian path prescribed by researchers and were observed at 8 points which were as follows: two observation points through which participants were instructed to listen to music whilst walking, two points where participants were instructed to send text messages, and four points through which participants were instructed not to use a smartphone at all. According to pedestrian behavior analysis, there is a trend for attention to be distributed amongst whatever other activities pedestrians are doing whilst walking. Therefore, this study proposes that pedestrians walking with such distractions are at a higher risk of traffic accidents compared to those who walk without such distractions. Thus, we advise for the South Korean government to consider ways to traffic policy that will enhance traffic safety for pedestrians.

• 한국ITS학회 논문지
• /
• 제19권6호
• /
• pp.49-60
• /
• 2020

교통사고 예방을 위해 설치되는 무인교통단속장비의 운영대수는 매년 경찰청과 지방자치단체의 지속적인 설치로 해마다 증가하고 있다. 하지만 공학적, 체계적인 분석결과가 아닌 민원 위주의 정성적인 판단을 기반으로 설치하고 있어 정량적인 설치기준이 필요한 실정이다. 따라서 본 논문에서는 도로 유형별 사고 심각도를 고려한 설치 판단기준을 제시하고 필요 설치대수를 산출하여 향후 추가 설치대수를 도출하는 것을 목표로 하였다. 사고건수와 KSI를 활용하여 교통사고 심각도를 나타낼 수 있는 ARI 지표를 개발하였으며, 일원배치 분산분석과 군집분석을 통해 도로유형을 4가지 유형으로 분류하고, 도로 유형별 사고 잦은 곳의 사고정보를 분석하여 교통사고 심각도가 높은 군집의 ARI를 도출하였다. 도로 유형별 단속장비의 설치 판단을 위한 ARI 값을 제시하였고, 사고 잦은 곳 중 교통단속장비가 기 설치된 구간을 제외하고 5,244대의 추가 설치가 필요한 것으로 분석되었다.

• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.65-78
• /
• 2017

Even though cars have a good effect on modern society, traffic accidents do not. There are traffic laws that define the regulations and aim to reduce accidents from happening; nevertheless, it is hard to determine all accident causes such as road and traffic conditions, and human related factors. If a traffic accident occurs, the traffic law classifies it as 'Negligence of Safe Driving' for cases that are not defined by specific regulations. Meanwhile, as Korea is already growing rapidly elderly population with more than 65 years, so are the number of traffic accidents caused by this group. Therefore, we studied predictive and comparative analysis of the number of traffic accidents caused by 'Negligence of Safe Driving' by dividing it into two groups : All-ages and Elderly. In this paper, we used empirical monthly data from 2007 to 2015 collected by TAAS (Traffic Accident Analysis System), identified the most suitable ARIMA forecasting model by using the four steps of the Box-Jenkins method : Identification, Estimation, Diagnostics, Forecasting. The results of this study indicate that ARIMA $(1, 1, 0)(0, 1, 1)_{12}$ is the most suitable forecasting model in the group of All-ages; and ARIMA $(0, 1, 1)(0, 1, 1)_{12}$ is the most suitable in the group of Elderly. Then, with this fitted model, we forecasted the number of traffic accidents for 2 years of both groups. There is no large fluctuation in the group of All-ages, but the group of Elderly shows a gradual increase trend. Finally, we compared two groups in terms of the forecast, suggested a countermeasure plan to reduce traffic accidents for both groups.

• 한국심리학회지 : 문화 및 사회문제
• /
• 제13권4호
• /
• pp.101-112
• /
• 2007

본 연구는 운전확신수준을 구성하는 '상황둔감성', '불안전운전', '주의집중소홀', '운전자신감'이 교통사고에 미치는 영향을 살펴보았다. 총 1055명의 운전자를 대상으로 운전확신수준 질문지를 실시하였으며, 이들의 과속·음주 운전과 같은 위험한 운전행동 및 교통사고 경험을 조사하였다. 이 가운데 결측치를 확인하여 998명의 자료가 분석에 사용되었다. 그 결과, 운전확신수준의 구성요소가 교통사고에 이르는 경로를 통해 운전확신수준과 교통사고가 유의한 관련이 있음을 알 수 있었다. 운전확신수준 가운데 '상황둔감성'과 '불안전운전'이 교통사고에 유의한 영향을 미치고 있는 것으로 나타났는데 '상황둔감성'이 교통사고에 부적인 영향을 미치고 있는데 반해, '불안전운전'은 교통사고에 정적인 영향을 미치는 것으로 나타났다. 이러한 결과 운전확신수준을 구성하는 각각의 요인에 따라서 교통사고에 미치는 영향에 차이가 있음을 의미한다. 비록 본 연구에서 '주의집중소홀'과 '운전자신감'은 교통사고와 유의한 관계를 가지고 있음을 밝혀낼 수는 없었지만, 추후 이 두 요인이 운전에 어떤 영향을 미치는지 살펴보아야 할 것이다.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.841-854
• /
• 2020

The paper explains the method to process, analyze and predict traffic patterns in Los Angeles county using Big Data and Machine Learning. The dataset is used from a popular navigating platform in the USA, which tracks information on the road using connected users' devices and also collects reports shared by the users through the app. The dataset mainly consists of information about traffic jams and traffic incidents reported by users, such as road closure, hazards, accidents. The major contribution of this paper is to give a clear view of how the large-scale road traffic data can be stored and processed using the Big Data system - Hadoop and its ecosystem (Hive). In addition, analysis is explained with the help of visuals using Business Intelligence and prediction with classification machine learning model on the sampled traffic data is presented using Azure ML. The process of modeling, as well as results, are interpreted using metrics: accuracy, precision and recall.

• 대한교통학회지
• /
• 제25권3호
• /
• pp.123-135
• /
• 2007

본 연구에서는 고속도로 트럼펫 인터체인지상에서 연결로 형식별로 일어나는 교통사고와 도로 기하구조 및 교통량등의 교통사고 요인들과의 관계를 분석하기 위해 교통사고의 분포의 특성을 분석하여 적합도 검증을 통해 모형추정시 가장 적절한 분포를 찾은 결과 음이항분포(Negative binomial distribution)가 선택되었다. 선택된 분포에 기반하여 트럼펫 인터체인지 연결로 전체, 연결로 형식별(직결, 준직결, 루프연결로) 각각의 음이항회귀모형 (Negative binomial regression model)을 개발하였다. 총 4개의 모형을 개발하고 그것의 적합도를 판단하는 여러 가지 통계값과 모형에서 예측한 값과 실제 관측값과의 차이를 분석한 결과 예측모형이 적합하게 구축되었음을 보였다. 추정된 모형의 통계적으로 유의한 변수들을 분석하여 교통사고를 설명하는데 유의한 변수들을 판단하고 이러한 변수들을 도로의 설계자가 도로 설계 및 운영에 적용하거나 교통안전계획 수립시 해당도로의 교통특성을 반영한 교통사고 절감 대책 등에 이용할 수 있을 것이다.

• 대한교통학회지
• /
• 제34권1호
• /
• pp.15-28
• /
• 2016

본 연구는 최근 이슈가 되는 난폭운전과 보복운전의 발생 메커니즘을 운전행동 결정요인(대인분노와 공격성)과 위험운전 행동요인(난폭운전행동과 과속위험행동, 음주운전행동, 주의산만, 대처미숙)을 통해 분석하고, 예방 대책을 마련하는 것을 목표로 진행하였다. 본 연구의 결과를 정리하면, 첫째, 도로교통공단 7개 지부에서 교통법규 위반자와 교통사고 야기자 351명을 대상으로 실시한 설문결과를 통해 운전 중 난폭운전과 보복운전의 심각성과 맞춤형 교육의 형태, 적정 시간, 교육내용 등 요구사항을 파악할 수 있다. 둘째, 난폭운전과 보복운전에 운전행동 결정요인과 위험운전 행동요인의 세부 항목 관련성 유무와 메커니즘을 Figure 3과 Table 8을 통해 명확히 파악할 수 있다. 이를 통해, 난폭운전과 보복운전 대책의 우선순위와 가중치 등을 요인별, 항목별로 선정할 수 있다. 셋째, 난폭운전과 보복운전 메커니즘 분석모형을 통해 예방 대책을 Table 9 - Table 10과 같이 공통대책과 각 요인별 맞춤형 대책으로 구분하여 제시할 수 있었다.