• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.144-145
• /
• 2023

육상, 철도, 항공 등 타 교통분야에서 지속적으로 사고와 인명피해가 줄어든 반면, 해양분야는 해양사고가 증가하며 실효적 해양교통안전관리에 대한 필요성이 대두되고 있다. 최근 3년간 국내 해상에서 발생한 충돌사고 중 어선을 포함한 충돌사고가 전체의 약 84%를 차지하며, 해상교통의 주요 변수인 어선을 포함한 국가의 해상교통량 파악은 반드시 필요한 실정이다. 본 연구에서는 현 정부 국정과제인 '디지털 해상 교통망 구축'과 더불어 해양교통안전관리체계 마련의 일환으로 국내 전체 선박위치발신장치(AIS, V-PASS) 데이터를 활용하여 해상교통량을 분석하고 예측 모델을 개발한다. 이를 위해 선박 밀집도를 통한 그리드별 공간가산분석과 항적 데이터 전처리 및 선형화, 선박 길이에 따른 점용면적 산정을 통한 단위 그리드별 해상교통량을 분석한다. 또한, 과거 교통량 데이터는 딥러닝 기반의 시계열 특성을 지닌 RNN과 LSTM 모델을 활용하여 교통량 예측 모형을 개발한다. 본 연구의 결과는 해상교통량과 해양사고의 연관성 분석 및 속력제한구역 등 해상정책 수립의 정량적 근거를 제공하며, 국민에게 해상교통정보 제공을 통해 교통복지 증진에 기여할 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.1-18
• /
• 2023

With the recent developments in big data and deep learning, a variety of traffic information is collected widely and used for traffic operations. In particular, long short-term memory (LSTM) is used in the field of traffic information prediction with time series characteristics. Since trends, seasons, and cycles differ due to the nature of time series data input for an LSTM, a trial-and-error method based on characteristics of the data is essential for prediction models based on time series data in order to find hyperparameters. If a methodology is established to find suitable hyperparameters, it is possible to reduce the time spent in constructing high-accuracy models. Therefore, in this study, a traffic information prediction model is developed based on highway vehicle detection system (VDS) data and LSTM, and an impact assessment is conducted through changes in the LSTM evaluation indicators for each hyperparameter. In addition, a methodology for finding hyperparameters suitable for predicting highway traffic information in the transportation field is presented.

• Journal of Korean Society of Transportation
• /
• v.27 no.6
• /
• pp.55-67
• /
• 2009

In Korea, previously implemented road construction project caused a big budget waste due to overestimation of transport demand. There could be reasons for such inaccuracy of transport demand estimation, but the main reasons are: (1) low reliability of used basic road transport data and (2) inadequate sharing of data among agencies/departments. The National Transport Database and the Household Travel Database in Seoul Metropolitan Area, two representing basic road transport database, will be used to the establishment of a road construction plan that will be promoted afterwards. However, these materials have problems such as low reliability and inadequateness, too. Hence, focusing on transport demand estimation related databases, this paper will make proposals for enhancing their reliability and data sharing.

• Journal of Korean Society of Transportation
• /
• v.22 no.4 s.75
• /
• pp.107-116
• /
• 2004

VMS를 통한 정보제공에는 과도반응과 통행집중의 위험부담이 따른다. 즉 대안경로간에 이루어져야 할 통행배분을 정확히 유도할 수 있는 VMS 메시지란 존재치 않는다. VMS 메시지에 의해 특정 경로가 교통상황이 타 경로에 비해 좋다고 정보가 주어질 때, 그 정보에 대한 과도반응과 그 특정경로에 대한 통행집중 문제가 발생하여 정보제공에 의해 오히려 상황이 악화될 수 있다. 본 연구에서는 대안경로간의 물리적 특성 측면에서 우열이 있는 가상 네트워크를 대상으로 하여, 과도반응과 통행집중 문제를 극복하고 대안경로간의 적절한 통행배분을 달성하기 위한 VMS 운영알고리즘을 개발하는 것을 목표로 한다. VMS정보제공 결과, 즉 VMS를 통해 상황이 좋다고 알려준 경로에 통행이 집중할 경우 문제가 될 것인가 여부를 미리 예측해 보고, 문제가 될 경우 정보제공 전략을 수정하도록 하는, 피드백 제어에 예측적 방식을 접목하였다. 본 연구에서 제안한 알고리즘의 주요 기능은 다음과 같다. 1. 교통량, 속도 등에 대한 실시간 모니터링 시스템이 구축되어 있음을 전제로 한다. 2. 실시간 제어에는 모니터링 결과와 이에 근거한 정보제공전략의 시행사이에는 시간차가 존재한다. 이러한 시간차이로 인하여 단기예측이 필요하고, 이를 수행하는 모듈이 있다. 3. 정보제공 결과로 특정 경로에 과부하가 걸리는지 여부를 예측하기 위하여, 그 판단기준으로 그 경로의 실제 용량 산정이 필요하다. 이에 혼잡의 시공간적 전개에 따라 변하는 동적 용량을 산정하는 모듈이 있다. 4. 대안 경로간 통행배분 목표치를 수리적으로 산정할 수는 있으나, 이를 자동적으로 이루어 주는 메시지는 존재하지 않는다. 아울러 현실적으로 예측 불가능한 외란을 모형에 의존하여 예측하기 보다는, 계속적인 피드백 레귤레이터(Regulator) 작동에 의해 보정하여 목표를 달성해 가는 자동제어 기능을 갖고 있다.

• 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.

• Journal of Korean Society of Transportation
• /
• v.21 no.3
• /
• pp.85-96
• /
• 2003

To build traffic information providing services by ITS technology should be carried out effect analysis in the first step for social and individual advantages. The propose on this study is to make clear what influences of highway network by traffic information are, and what differences between drivers who use traffic information and drivers who do not use that for route choice are. For these propose. travel time and forecast error of travel time on network and traffic information dependence of driver are analyzed by simulation. As a result of analysis travel time and forecast error of travel time is that the efficiency and reliability of travel time were increased when getting more drivers using traffic information in network. Drivers who using traffic information had advantage of decrease of travel time and forecast error in only definite situation. traffic information dependence analysis presented that drivers are dependent upon information and reliability of traffic information is also increased when drivers using traffic information become on increasing in network. In conclusion, considering the range of the traffic information user ratio in this simulation, this study presents that the traffic information service provides an advantage to the highway network and the drivers, and increases the dependence of information.

• Journal of Korean Society of Transportation
• /
• v.29 no.1
• /
• pp.71-79
• /
• 2011

Traditionally, a dynamic network model is considered as a tool for solving real-time traffic problems. One of useful and practical ways of using such models is to use it to produce and disseminate forecast travel time information so that the travelers can switch their routes from congested to less-congested or uncongested, which can enhance the performance of the network. This approach seems to be promising when the traffic congestion is severe, especially when sudden incidents happen. A consideration that should be given in implementing this method is that travel time information may affect the future traffic condition itself, creating undesirable side effects such as the over-reaction problem. Furthermore incorrect forecast travel time can make the information unreliable. In this paper, a network-wide travel time prediction model under incidents is developed. The model assumes that all drivers have access to detailed traffic information through personalized in-vehicle devices such as car navigation systems. Drivers are assumed to make their own travel choice based on the travel time information provided. A route-based stochastic variational inequality is formulated, which is used as a basic model for the travel time prediction. A diversion function is introduced to account for the motorists' willingness to divert. An inverse function of the diversion curve is derived to develop a variational inequality formulation for the travel time prediction model. Computational results illustrate the characteristics of the proposed model.

• Proceedings of the KOR-KST Conference
• /
• 2007.11a
• /
• pp.960-968
• /
• 2007

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.773-794
• /
• 2021

Prediction of vehicle traffic volume is very important in planning municipal administration. It may help promote social and economic interests and also prevent traffic congestion costs. Traffic volume as a time-varying trajectory is considered as functional data. In this paper we study three functional regression models that can be used to predict an unseen trajectory of traffic volume based on already observed trajectories. We apply the methods to highway tollgate traffic volume data collected at some tollgates in Seoul, Chuncheon and Gangneung. We compare the prediction errors of the three models to find the best one for each of the three tollgate traffic volumes.

• Journal of Korean Society of Transportation
• /
• v.27 no.2
• /
• pp.207-214
• /
• 2009

This study proposed an advanced warning information system based on real-time traffic conflict analysis. An algorithm to detect and analyze unsafe traffic events associated with car-following and lane-changes using individual vehicle trajectories was developed. A positive guidance procedure was adopted to provide warning information to alert drivers to hazardous traffic conditions derived from the outcomes of the algorithm. In addition, autoregressive integrated moving average (ARIMA) analyses were conducted to investigate the predictability of warning information for the enhancement of information reliability.