• Journal of Korean Society of Transportation
• /
• v.33 no.5
• /
• pp.497-507
• /
• 2015

Nonrecurrent congestion of freeway was primarily caused by incident. The main cause of incident was known as a traffic accident. Therefore, accurate prediction of traffic incident clearance time is very important in accident management. Traffic accident data on freeway during year 2008 to year 2014 period were analyzed for this study. KNN(K-Nearest Neighbor) algorithm was hired for developing incident clearance time prediction model with the historical traffic accident data. Analysis result of accident data explains the level of accident significantly affect on the incident clearance time. For this reason, incident clearance time was categorized by accident level. Data were sorted by classification of traffic volume, number of lanes and time periods to consider traffic conditions and roadway geometry. Factors affecting incident clearance time were analyzed from the extracted data for identifying similar types of accident. Lastly, weight of detail factors was calculated in order to measure distance metric. Weight was calculated with applying standard method of normal distribution, then incident clearance time was predicted. Prediction result of model showed a lower prediction error(MAPE) than models of previous studies. The improve model developed in this study is expected to contribute to the efficient highway operation management when incident occurs.

• IE interfaces
• /
• v.15 no.4
• /
• pp.426-431
• /
• 2002

In many cases, the result of a road traffic accident can be described with more than one response variables. Nonetheless, most of the existing road accident data analysis deal with only one response variable and try to explain why it occurs. In this paper, we train association rules for a set of more than two response variables conditional on personal, environmental and vehicular/behavioral aspects of accident. Association rules are derived at 8% support and 70% confidence from the 1996 data of three police stations in Korea. We expect that these rules can contribute to effective safety practice in Korea.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.2
• /
• pp.35-41
• /
• 2023

On December 19, 2015, as Article 29-3 (Installation of Accident Recording Devices and Provision of Information) of Motor Vehicle Management Act came into force, In Korea, the EDR (Event Data Recorder) reports are often used for the analysis of various traffic accident cases such as multiple collisions, traffic insurance crimes, and sudden unintended acceleration (SUA), and the others. So many investigators have analyzed the driver's behavior and vehicle situation by comparing the time zero in the EDR report to the actual crash time in dash-cam (or CCTV). Time zero (T0) is defined as the reference time for the record interval or time interval when recording an accident in Article 56-2, Enforcement rule of Performance and Standard for Automobile and Automotive parts. Also in the EDR report, time zero (T0) is defined as whichever of the following occurs first; 1. "wake-up" by an air-bag control system, 2. Continuously running algorithms (by monitoring of longitudinal or lateral delta-V), 3. Deployment of a non-reversible deployment restraint. We have already proposed the "Flowchart & Checklist" to adopt the EDR report for traffic accident investigation and the necessity of specialized institutions or courses to systematically educate or analyze the EDR data. Therefore, in this paper, we report to traffic accident investigators notable points and analysis methods based on some real-world traffic accidents that can be misjudged in specifying time zero (T0).

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.1
• /
• pp.127-136
• /
• 2008

In these days, frequency of constructions on e freeway are increasing according as growing of the importance of e road maintenance and the road management. Work zone on the freeway where vehicles pass with high speed needs control method of lane closure and construction equipment. Because there are seldom researches in domestic study about reflecting characteristics of domestic road, sometimes we have applied for foreign cases to our traffic circumstance but it is not proper to apply for standard of other countries in our cases. foreign nation has different country square, condition of road, and level of people mind. Therefore, this study shows traffic accident characteristics in freeway work zones in Korea. At first, this study collected traffic accident data which include for 3 years $2003{\sim}2005$ in the whole freeway in Korea and then divided the data to five parts - level of the accident, type of the construction work, type of the accident, reason of the accident, according to geometric. According to comparing with non-work zones accident, this study found traffic accident characteristics in freeway work zones in Korea and suggested some alternative ideas for safety of work zones.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.427-441
• /
• 2021

Purpose: This study proposes a method for developing a model that predicts the probability of traffic accidents in advance to prevent the most frequent traffic accidents in the military. Method: For this purpose, CRISP-DM (Cross Industry Standard Process for Data Mining) was applied in this study. The CRISP-DM process consists of 6 stages, and each stage is not unidirectional like the Waterfall Model, but improves the level of completeness through feedback between stages. Results: As a result of modeling the same data set as the previously constructed accident investigation data for the entire group, when the classification criterion was 0.5, Significant results were derived from the accuracy, specificity, sensitivity, and AUC of the model for predicting traffic accidents. Conclusion: In the process of designing the prediction model, it was confirmed that it was difficult to obtain a meaningful prediction value due to the lack of data. The methodology for designing a predictive model using the data set was proposed by reorganizing and expanding a data set capable of rational inference to solve the data shortage.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.75-85
• /
• 2018

PURPOSES : This study aimed to analyze traffic accidents at circular intersections, and discuss accident reduction strategies based on land use and vehicle type. METHODS : Traffic accident data from 2010 to 2014 were collected from the "traffic accident analysis system" (TAAS) data set of the Road Traffic Authority. To develop the accident rate model, a multiple linear regression model was used. Explanatory variables such as geometry and traffic volume were used to develop the models. RESULTS : The main results of the study are as follows. First, it was found that the null hypotheses that land use and vehicle type do not affect the accident rate should be rejected. Second, 16 accident rate models, which are statistically significant (with high $R^2$ values), were developed. Finally, the area of the central island, number of speed humps, entry lane width, circulatory roadway width, bus stops, and pedestrian crossings were analyzed to determine their effect on accidents according to the type of land use and vehicle. CONCLUSIONS : Through the developed accident rate models, it was revealed that the accident factors at circular intersections changed depending on land use and vehicle type. Thus, selecting the appropriate location of bus stops for trucks, widening entry lanes for cars, and installing splitter islands and optimal lighting for motorcycles were determined to be important for reducing the accident rate. Additionally, the evaluation showed that commercial and mixed land use had a weaker effect on accidents than residential land use.

• International Journal of Highway Engineering
• /
• v.17 no.3
• /
• pp.133-141
• /
• 2015

PURPOSES : This study dealt with traffic accidents occurring within roundabouts. The objective of this study was to analyze safety effect by introduction of roundabouts. METHODS : In pursuing the above, traffic accident data on roundabouts are collected and compared. For the analysis, collected data were separated as all intersection points, turning lane accident, approach lane accident by geometric design. RESULTS : Through the study results, it was found that the total accidents decreased by 55 accidents/2 year with safety effect of roundabouts. Also the result shows that accidents by point of two-lane roundabout at turning lane(0.26) and approach lane(0.27) is risky than total accidents by point(0.09). Moreover, accidents by point shows high value as diameter of a roundabout is bigger. CONCLUSIONS : When a roundabout is introduced at the intersections there are safety effects by reduction of traffic accidents.

• Journal of Korean Society of Transportation
• /
• v.35 no.1
• /
• pp.25-36
• /
• 2017

The purpose of this study is to analyze traffic accident reduction effect of the introduction of motorcycle safety inspection. To analyze the effect of motorcycle inspection, we first estimate the number of defective motorcycles, and calculate the probability of accident occurrences caused by the defect using four year traffic accident data. Finally, we estimate the number of reduced accidents due to the introduction of the inspection and the total reduced accident cost. In this study, we analyzed three scenarios. It is analyzed that when the safety inspection system is applied to all motorcycles, 642 cases of traffic accidents and 325 million won per year of traffic accident costs are reduced. It is approximately 0.1% of 2014 total traffic accident cost of 26.5725 trillion won per year. It suggests that the cost of traffic accidents and traffic accidents due to vehicle factors are reduced when the safety inspection system is introduced.

• Journal of Korean Society of Transportation
• /
• v.19 no.6
• /
• pp.207-218
• /
• 2001

As a city and industries are developed rapidly, a traffic accident and congestion take places on the road link become serious and it can be a large problem of the society in the future. Especially, most of the traffic accidents on the signalized intersection are caused by the human factor, vehicle and environmental factor mutually. The relation of the traffic accident and volume is acting on the outbreak of the traffic accident and the mistake of driver altogether as a major cause. The purpose of this paper is to develop a model for the forecasting of the traffic accident and to use research data gained to predict many traffic accidents. The data of this study were used with real one of the 73 areas of the four-legged signalized intersection in Kwang-ju city from 1996 to 1998 for three years to develop a model for the forecasting of the traffic accident. The statistical methods used in this paper are the principal component, regression and correlation analysis. We studied accident models to find out useful data from the statistics method and applied the data to the different area of the Choun-La province for the verification of the model. So, the result of this paper showed a reasonable model for the forecasting or the traffic accident and possibility of the model for simulating on real case. Finally, This study would be made of a study continually for the safe design and plan for the four-legged signalized intersection.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.301-310
• /
• 2021

The TATI model is a Traffic Accident Text to RGB Image model, which is a methodology proposed in this paper for predicting the severity of traffic accidents. Traffic fatalities are decreasing every year, but they are among the low in the OECD members. Many studies have been conducted to reduce the death rate of traffic accidents, and among them, studies have been steadily conducted to reduce the incidence and mortality rate by predicting the severity of traffic accidents. In this regard, research has recently been active to predict the severity of traffic accidents by utilizing statistical models and deep learning models. In this paper, traffic accident dataset is converted to color images to predict the severity of traffic accidents, and this is done via CNN models. For performance comparison, we experiment that train the same data and compare the prediction results with the proposed model and other models. Through 10 experiments, we compare the accuracy and error range of four deep learning models. Experimental results show that the accuracy of the proposed model was the highest at 0.85, and the second lowest error range at 0.03 was shown to confirm the superiority of the performance.