• 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 Industrial and Systems Engineering
• /
• v.40 no.1
• /
• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.3
• /
• pp.59-73
• /
• 2021

There are many lives lost due traffic accidents, and which have not decreased despite advances in technology. In order to prevent traffic accidents, it is necessary to accurately forecast how they will change in the future. Until now, traffic accident-frequency forecasting has not been a major research field, but has been analyzed microscopically by traditional methods, mainly based on statistics over a previous period of time. Despite the recent introduction of AI to the traffic accident field, the focus is mainly on forecasting traffic flow. This study converts into time series data the records from 1,339,587 traffic accidents that occurred in Korea from 2014 to 2019, and uses the AI algorithm to forecast the frequency of traffic accidents based on driver's age and time of day. In addition, the forecast values and the actual values were compared and verified based on changes in the traffic environment due to COVID-19. In the future, these research results are expected to lead to improvements in policies that prevent traffic accidents.

• KDI Journal of Economic Policy
• /
• v.35 no.4
• /
• pp.31-61
• /
• 2013

The purpose of this study is to calculate the economic value of transport demand forecasting risks in the road PPP project. Under the assumption that volatility of the road PPP project value occurs only in regard with uncertainty of traffic volume forecasting, this study calculates the economic value of the traffic forecasting risks in the case of the road PPP project. To that end, forecasted traffic volume is assumed to be a stochastic variable and to follow the Geometric Brownian motion as time passes. In particular, this study attempts to differentiate itself from existing studies that simply use an arbitrary assumption by presenting the application of different traffic volume growth volatility and the rates before and after the ramp-up period. Analysis of the case projects reveals that the risk premium related to traffic volume forecast of the project turns out as 7.39~8.30%, without considering option value-such as minimum revenue guarantee-while the project value volatility caused by transport demand forecasting risks is 17.11%. As the discount rate grows higher, the project value volatility tends to decrease and volatility in project value is always suggested to be larger than that in transport volume influenced by leverage effect due to fixed expenditure. The market value of transport demand forecasting risk-calculated using the project value volatility and risk premium-is analyzed to be between 0.42~0.50, implying that a 1% increase or decrease in the transport amount volatility would lead to a 0.42~0.50% increase or decrease in risk premium of the project.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.1
• /
• pp.92-101
• /
• 2009

In this paper, we propose a dynamic bandwidth provisioning method based on traffic forecasting in IEEE 802.16e packet core network. The traffic is categorized as 4-different classes and the traffic amount of each class is forecasted by the Box-Jenkins method. To increase the service provider's revenue we provision the bandwidth of 4-different classes dynamically using greedy algorithm. The simulation results show that the number of packet drops is reduced and the level of QoS is improved compared with two different the methods - no priority considering and static provisioning.

• Journal of Korean Society of Transportation
• /
• v.18 no.3
• /
• pp.55-76
• /
• 2000

We propose a general solution methodology for identifying the optimal aggregation interval sizes as a function of the traffic dynamics and frequency of observations for four cases : i) link travel time estimation, ii) corridor/route travel time estimation, iii) link travel time forecasting. and iv) corridor/route travel time forecasting. We first develop statistical models which define Mean Square Error (MSE) for four different cases and interpret the models from a traffic flow perspective. The emphasis is on i) the tradeoff between the Precision and bias, 2) the difference between estimation and forecasting, and 3) the implication of the correlation between links on the corridor/route travel time estimation and forecasting, We then demonstrate the Proposed models to the real-world travel time data from Houston, Texas which were collected as Part of the Automatic Vehicle Identification (AVI) system of the Houston Transtar system. The best aggregation interval sizes for the link travel time estimation and forecasting were different and the function of the traffic dynamics. For the best aggregation interval sizes for the corridor/route travel time estimation and forecasting, the covariance between links had an important effect.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.795-797
• /
• 2005

During the past few years, various traffic-flow forecasting models, i.e. an ARIMA, an ANN, and so on, have been developed to predict more accurate traffic flow. However, these models analyze historical data in an attempt to predict future value of a variable of interest. They make use of the following basic strategy. Past data are analyzed in order to identify a pattern that can be used to describe them. Then this pattern is extrapolated, or extended, into the future in order to make forecasts. This strategy rests on the assumption that the pattern that has been identified will continue into the future. So ARIMA or ANN models with its traditional architecture cannot be expected to give good predictions unless this assumption is valid; The statistical models in particular, the time series models are deficient in the sense that they merely extrapolate past patterns in the data without reflecting the expected irregular and infrequent future events Also forecasting power of a single model is limited to its accurate. In this paper, we compared with an ANN model and ARIMA model and tried to combine an ARIMA model and ANN model for obtaining a better forecasting performance. In addition to combining two models, we also introduced judgmental adjustment technique. Our approach can improve the forecasting power in traffic flow. To validate our model, we have compared the performance with other models. Finally we prove that the proposed model, i.e. ARIMA + ANN + Judgmental Adjustment, is superior to the other model.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.219-227
• /
• 2007

The time series models have been used to analyze and predict the network traffic. In this paper, we compare the performance of the time series models for prediction of network traffic. The feasibility study showed that a class of nonlinear time series models can be outperformed than the linear time series models to predict the network traffic.

• Journal of Korean Society of Transportation
• /
• v.7 no.2
• /
• pp.29-43
• /
• 1989

The purpose of this study is to construct a forecasting model involved in a diverted traffic volume of the 2nd intra-urban expressway in construction presently, in the case of the future prediction of traffic demand for the intra-urban expressway in Pusan. In this study, the model involved in a diverted traffic volume is constructed trustworthy. And the future traffic demand of intra-urban expressway by this model was forecasted 114,005 volume/daily in 1996 and 147,090 volume/daily in 2001. However, it will made a study more and more concretely for practicality and limitation as well as construction of the forecasting model considered an intrinsic problem of an observational error and necessity of survey for much more socio-economic data, the traffic volume on all orad and OD pairs in Pusan.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.362-364
• /
• 2018

Predicting network traffic volume has become a popular topic recently due to its support in many situations such as detecting abnormal network activities and provisioning network services. Especially, predicting the volume of the next upcoming traffic from the series of observed recent traffic volume is an interesting and challenging problem. In past, various techniques are researched by using time series forecasting methods such as moving averaging and exponential smoothing. In this paper, we propose a long short-term memory neural network (LSTM) based network traffic volume prediction method. The proposed method employs the changing rate of observed traffic volume, the corresponding time window index, and a seasonality factor indicating the changing trend as input features, and predicts the upcoming network traffic. The experiment results with real datasets proves that our proposed method works better than other time series forecasting methods in predicting upcoming network traffic.