• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• 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.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.98-104
• /
• 2018

Macroscopic accident analyses have been conducted to incorporate transportation safety into long-term transportation planning. In macro-level accident prediction model, exposure variable(e.g. a settled population) have been used as fundamental explanatory variable under the concept that each trip will be subjected to a probable risk of accident. However, a settled population may be embedded error by exclusion of active population concept. The objective of this research study is to develop macro-level accident prediction model using floating population variable(concept of including a settled population and active population) collected from mobile phone data. The concept of accident prediction models is introduced utilizing exposure variable as explanatory variable in a generalized linear regression with assumption of a negative binomial error structure. The goodness of fit of model using floating population variable is compared with that of the each models using population and the number of household variables. Also, log transformation models are additionally developed to improve the goodness of fit. The results show that the log transformation model using floating population variable is useful for capturing the relationships between accident and exposure variable and generally perform better than the models using other existing exposure variables. The developed model using floating population variable can be used to guide transportation safety policy decision makers to allocate resources more efficiently for the regions(or zones) with higher risk and improve urban transportation safety in transportation planning step.

• International Journal of Highway Engineering
• /
• v.14 no.5
• /
• pp.101-111
• /
• 2012

PURPOSES: Because expressway ramps are very complex segments where diverse roadway design elements dynamically change within relatively short length, drivers on ramps are required to drive their cars carefully for safety. Especially, ramps on expressways are designed to guarantee driving at high speed so that the risk and severity of traffic accidents on expressway ramps may be higher and more deadly than other facilities on expressways. Safe deceleration maneuvers are required on off-ramps, whereas safe acceleration maneuvers are necessary on onramps. This difference in required maneuvers may contribute to dissimilar patterns and severity of traffic accidents by ramp types. Therefore, this study was aimed at developing prediction models of the severity of traffic accidents on expressway on- and off-ramps separately in order to consider dissimilar patterns and severity of traffic accidents according to types of ramps. METHODS: Four-year-long traffic accident data between 2007 and 2010 were utilized to distinguish contributing design elements in conjunction with AADT and ramp length. The prediction models were built using the negative binomial regression model consisting of the severity of traffic accident as a dependent variable and contributing design elements as in independent variables. RESULTS: The developed regression models were evaluated using the traffic accident data of the ramps which was not used in building the models by comparing actual and estimated severity of traffic accidents. Conclusively, the average prediction error rates of on-ramps and offramps were 30.5% and 30.8% respectively. CONCLUSIONS: The prediction models for the severity of traffic accidents on expressway on- and off-ramps will be useful in enhancing the safety on expressway ramps as well as developing design guidelines for expressway ramps.

• Journal of the Korean Society for Railway
• /
• v.20 no.4
• /
• pp.482-490
• /
• 2017

This study is a railway accident investigation statistic study with the purpose of prediction and classification of accident severity. Linear regression models have some difficulties in classifying accident severity, but a logistic regression model can be used to overcome the weaknesses of linear regression models. The logistic regression model is applied to escalator (E/S) accidents in all stations on 5~8 lines of the Seoul Metro, using data mining techniques such as logistic regression analysis. The forecasting variables of E/S accidents in urban railway stations are considered, such as passenger age, drinking, overall situation, behavior, and handrail grip. In the overall accuracy analysis, the logistic regression accuracy is explained 76.7%. According to the results of this analysis, it has been confirmed that the accuracy and the level of significance of the logistic regression analysis make it a useful data mining technique to establish an accident severity prediction model for urban railway casualty accidents.

• Journal of Korean Society of Transportation
• /
• v.27 no.3
• /
• pp.91-102
• /
• 2009

A traffic accident prediction model developed using various design variables(road design variables, geometric variables, and traffic environmental variables) is one of the most important factors to safety design evaluation system for roads. However, statistical accident models have a crucial problem not applicable for all intersections. To make up this problem, this study developed AMFs(Accident Modification Factors) through statistical modeling methods, historical accident databases, judgment from traffic experts, and literature review by considering design variable's characteristics, traffic accident rates, and traffic accident frequency. AMFs developed in this study include exclusive left-turn lane, exclusive right-turn lane, sight distance, and intersection angle. Predictabilities of the developed AMFs and the existing accident prediction models are compared with real accident historical data. The results showed that performances of the developed AMFs are superior to the existing statistical accident prediction models. These findings show that AMFs should be considered as a important process to develop safety design evaluation algorithms. Additionally, AMFs could be used as an index that can judge the impact of corresponding design variables on accidents in rural intersections.

• International Journal of Highway Engineering
• /
• v.10 no.1
• /
• pp.19-29
• /
• 2008

The main purpose of this study is to introduce Hauer's(2004) approach that overcomes current accident prediction models' limitation and to apply this approach to Korean situation using fatal accident data on motorways. After developing accident prediction models according to this approach, it is found that AADT and vertical grade could improve fitness of the model, whereas a radius of roads is not related to the number of accidents. The advantage of Hauer's approach is to reduce possibility to eliminate critical variables and to keep uncritical variables when we consider many variables to develop accident prediction models.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.11a
• /
• pp.59-60
• /
• 2018

The purpose of this study is to predict and classify the accident types based on the KOSHA (Korea Occupational Safety & Health Agency) and weather data. We also have an effort to suggest an important management method according to accident types by deriving feature importance. We designed two models based on accident data and weather data (model(a)) and only weather data (model(b)). As a result of random forest method, the model(b) showed a lack of accuracy in prediction. However, the model(a) presented more accurate prediction results than the model(b). Thus we presented safety management plan based on the results. In the future, this study will continue to carry out real time prediction to occurrence types to prevent safety accidents by supplementing the real time accident data and weather data.

• Journal of the Society of Disaster Information
• /
• v.13 no.4
• /
• pp.570-576
• /
• 2017

Trucks take up more portions than cars on highways. Due to this, road use relatively diminish and it serves locally as a threatening factor to nearby drivers. Baggage car accident has distinct characteristics so that it needs the application of different analysis opposed to ordinary accidents. Accident prediction model, one of accident analyses, is used to predict the numbers of accident in certain parts, establish traffic plans as well as accident prevention methods, and diagnose the danger of roads. Thus, this study aims to apply the accident rate of baggage car on highways and calculate the correction factor to be put in the accident prediction models. Accident data based on highway was collected and traffic amounts and accident documents between 2014 and 2016 were utilized. The author developed an accident prediction model based on numbers of annual accidents and set mean annual and daily traffic amounts. This study intends to identify the practical accident prediction model on highway and present an appropriate solution by comparing the prediction model in accords with the accident rate between baggage cars.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.393-404
• /
• 2012

After the Fukushima nuclear accident in 2011, there has been increasing concern regarding severe accidents in nuclear facilities. Severe accident scenarios are difficult for operators to monitor and identify. Therefore, accurate prediction of a severe accident is important in order to manage it appropriately in the unfavorable conditions. In this study, artificial intelligence (AI) techniques, such as support vector classification (SVC), probabilistic neural network (PNN), group method of data handling (GMDH), and fuzzy neural network (FNN), were used to monitor the major transient scenarios of a severe accident caused by three different initiating events, the hot-leg loss of coolant accident (LOCA), the cold-leg LOCA, and the steam generator tube rupture in pressurized water reactors (PWRs). The SVC and PNN models were used for the event classification. The GMDH and FNN models were employed to accurately predict the important timing representing severe accident scenarios. In addition, in order to verify the proposed algorithm, data from a number of numerical simulations were required in order to train the AI techniques due to the shortage of real LOCA data. The data was acquired by performing simulations using the MAAP4 code. The prediction accuracy of the three types of initiating events was sufficiently high to predict severe accident scenarios. Therefore, the AI techniques can be applied successfully in the identification and monitoring of severe accident scenarios in real PWRs.

• International Journal of Highway Engineering
• /
• v.15 no.6
• /
• pp.113-123
• /
• 2013

PURPOSES : Although numerous researches have been studied to reveal accident causations for road intersections, there are still many research gaps for road segments. It is mainly because of difficulty of data and lack of analytical method. This study aims to study accident causations for rural road segments and develop accident modification factors for safety evaluation. The accident modification factors can be used to improve road safety. METHODS : Methods for developing AMF are diverse. This study developed AMFs using accident prediction models and selected explanatory variables from the accident models. In order to select final AMFs, three different methods were applied in the study. RESULTS : As a result of the study, many AMFs such as horizontal curves or vertical curves were developed and explained the meanings of the results. CONCLUSIONS : This study introduced meaningful methods for developing significant AMFs and also showed several AMFs. It is expected that traffic or road engineers will be able to use the AMFs to improve road segment safety.