• Journal of Korean Society of Transportation
• /
• v.26 no.5
• /
• pp.153-162
• /
• 2008

This study deals with the traffic accidents at the 4-legged signalized intersections in Cheong-ju. The purpose is to comparatively analyze the characteristics and models by the accident type using the data of 143 intersections. In pursuing the above, this study gives particular emphasis to modeling such the accidents as head on collision, rear end collision, side swipe, side right angle collision, and others. The main results are the followings. First, the overdispersion tests show that the negative binomial regression models are appropriate to the traffic accident data in the above contexts. Second, five accident models are developed, which are all analyzed to be statistically significant. Finally, the models are comparatively evaluated using the common variable(ADT) and type-specific variables.

• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.207-215
• /
• 2009

Generally, traffic accidents can be influenced by variables driving conditions including geometric, roadside design, and traffic conditions. Under the circumstance, homogeneous roadway segments were firstly identified using typical geometric variables obtained from field data collections in this study. These field data collections were conducted at highways located in several areas having various regional conditions for examples, outside metropolitan city; level and rolling rural areas. Due to many zero cells in crash database, a Zero Inflated Poisson model was used to develop crash prediction model to overestimated results in this study. It was found that EXPO, radius, grade, guardrail, mountainous terrain, crosswalk and bus-stop have statistically significant influence on vehicle to vehicle crashes at rural multi-lane roadway segments.

• Journal of the Society of Disaster Information
• /
• v.9 no.1
• /
• pp.30-49
• /
• 2013

In this research we developed a new traffic accident forecasting model on the basis of land use. A new traffic accident forecasting model by type was developed based on market segmentation and further introduction of variables that may reflect characteristics of various regions using Classification and Regression Tree Method. From the results of analysis, activities variables such as the registered population, commuters as well as road size, traffic accidents causing facilities being the subjects of activities were derived as variables explaining traffic accidents.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.99-110
• /
• 2008

It is commonly estimated that there is a much higher potential for accidents at a crossroads than along a single road due to its plethora of conflicting points. According to the 2006 figures by the National Police Agency, the number of traffic accidents at crossroads is greatly increasing compared to that along single roads. Among others, crossroads installed with traffic signals have more varied influential factors for traffic accidents and leave much more room for improvement than ones without traffic signals; thus, it is expected that a noticeable effect could be achieved in safety if proper counter-measures against the hazards at a crossroads were taken together with an estimate of causes for accidents This research managed to develop models for accident forecasts and accident intensity by applying data on accident history and site inspection of crossroads, targeting four selected downtown crossroads installed with traffic signals. The research was done by roughly dividing the process into four stages: first, analyze the accident model examined before; second, select variables affecting traffic accidents; third, develop a model for traffic accident forecasting by using a statistics-based methodology; and fourth, carry out the verification process of the models.

• International Journal of Highway Engineering
• /
• v.11 no.2
• /
• pp.17-25
• /
• 2009

The goal of this study is to develop Logistic regression model by accident location(entry section, exit section, inside intersection and pedestrian crossing section). Based on the accident data of Chungbuk Provincial Police Agency(2004$\sim$2005) and the field survey data, the geometric elements, environmental factor and others related to traffic accidents were analyzed. Developed models are all analyzed to be statistically significant(chi-square p=0.000, Nagelkerke $R^2$=0.363$\sim$0.819). The models show that the common factors of accidents are the traffic volume(ADT), distant of crossing and exclusive left turn lane, and the specific factors are the minor traffic volume(inside intersection model) and U-turn of main road(pedestrian crossing model). Hosmer & Loineshow tests are evaluated to be statistically significant(p$\geqq$0.05) except the entry section model. The correct classification rates are also analyzed to be very predictable(more than 73.9% to all models).

• 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 electronic communication sciences
• /
• v.15 no.6
• /
• pp.1123-1130
• /
• 2020

This study aims to classify the severity in car crashes using five classification learning models. The dataset used in this study contains 21,013 vehicle crashes, obtained from Korea Expressway Corporation, between the year of 2015-2017 and the LightGBM(Light Gradient Boosting Model) performed well with the highest accuracy. LightGBM, the number of involved vehicles, type of accident, incident location, incident lane type, types of accidents, types of vehicles involved in accidents were shown as priority factors. Based on the results of this model, the establishment of a management strategy for response of highway traffic accident should be presented through a consistent prediction process of accident severity level. This study identifies applicability of Machine Learning Models for Predicting of the Severity of Car Traffic Accidents on a Highway and suggests that various machine learning techniques based on big data that can be used in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.106-106
• /
• 2017

우리나라는 현재 재난의 유형을 자연재난과 사회재난으로 구분하여 관리하고 있다. 하지만 최근 재난 사고 사례를 살펴보면 단일재난으로 인한 피해보다 자연재난이 발생한 이후 사회재난으로 재난이 전파되는 복합재난의 형태가 종종 나타나고 있다. 복합재난은 단일 재난에 의한 피해(인적, 물적) 보다 크게 나타나고 복합재난의 발생원인 및 전파과정을 분석하기 어려워 이에 대한 다각적인 분석과 동시에 재난상호간의 연관성을 도출하는 연구가 필요한 시점이다. 과거 재난사고정보를 분석하는 연구는 일반적인 통계기법을 활용한 분석에 머물러 있으며 수집된 재난사고사례가 많지 않아 분석에 신뢰성을 보장할 수 없었다. 이에 본 연구에서는 복잡하게 나타나는 재난 사고를 분석하기 위하여 최근 각광받고 있는 인공지능 분석기법을 연구에 고려하였다. 본 연구의 과정은, 첫째로 재난사고정보 분석에 인공지능을 활용한 사례를 조사하고 여타 연구분야에서 적용되고 있는 인공지능 분석기술을 재난사고정보 분석에 활용할 수 있는 방안을 모색하였다. 둘째로 수집가능 한 재난사고정보를 수집하고 인공지능 모형에 적용가능 한 형태로 변환하는 과정을 수행하였다. 셋째로 변환된 재난사고정보를 대표적인 인공지능 알고리즘을 활용하여 다양한 질문(목적)에 부합하는 재난사고정보 분석모형을 구축하고자 하였다. 마지막으로 다양한 인공지능 알고리즘을 적용한 모형의 신뢰성을 비교하였으며 이를 통하여 재난사고정보 분석에 적용가능 하며 질문(목적)에 부합하는 최적 인공지능 알고리즘을 도출하고자 하였다.

• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.151-159
• /
• 2010

This paper presents a research result that was performed to develop a more accurate freeway crash prediction model than existing models. While the existing crash models only focus on developing crash relationships associated with highway geometric conditions found on a short section of a crash site, this research applies a different approach considering the upstream highway geometric conditions as well. Theoretically, crashes occur while motorists are in motion, and particularly at freeways vehicle speed at one specific point is very sensitive to upstream geometric conditions. Therefore, this is a reasonable approach. To form the analysis data base, this research gathers the geometric conditions of the West Seaside Freeway 269.3 km and six years crash data ranging 2003-2008 for these freeway sections. As a result, it is found that crashes fit well into Negative Binomial Distribution, and, based on the developed model, total number of crashes is inversely proportional to highway curve length and radius. Contrarily, crash occurrences are proportional to tangent length. This result is different from existing crash study results, and it seems to be resulted from this research assumption that a crash is influenced greatly by upstream geometric conditions. Also, this research provides the expected effects on crash occurrences of the length of downgrade sections, speed camera placements, and the on- and off- ramp presences. It is expected that this research result is useful for doing more reasonable highway designs and safety audit analysis, and applying the same research approach to national roads and other major roads in urban areas is recommended.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.49-57
• /
• 2011

This study deals with the traffic accident of arterial link sections in the case of Cheongju. The purpose of the study is to develop the traffic accident model by the function of arterial links. In pursuing the above, this study gives particular attentions to developing the appropriate models using the accident data of main and minor arterial roads divided by 472 small link sections. The main results analyzed are as follows. First, as the t test on the accident characteristics of main and minor arterial roads shows that there are differences in the number of accident and EPDO(equivalent property damage only) between two roads, the development of models by function is analyzed to be appropriate. Second, it is analyzed that ZINB models are all statistically suitable to the number of accident and EPDO of main arterial roads. Third, the analysis shows that EPDOs of minor arterial roads fit to ZINB, and the number of the accident fit to ZIP model. Finally, the common variables of main arterial roads are evaluated to be the traffic volume and the number of inflection point, and those of minor be the average grade.