• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.5
• /
• pp.988-995
• /
• 2009

One of the most popular services of Telematics is a shortest path finding from a starting point to a destination. In this paper, a dynamic shortest path finding system with forecasting result of traffic flow in the future was developed and various experiments to verify the performance of our system using real-time traffic information has been conducted. Traffic forecasting has been done by a prediction system using Bayesian network. It searched a dynamic shortest path, a static shortest path and an accumulated shortest path for the same starting point and destination and calculated their travel time to compare with one of its real shortest path. From the experiment, over 75%, the travel time of dynamic shortest paths is the closest to one of their real shortest paths than one of static shortest paths and accumulated shortest paths. Therefore, it is proved that finding a dynamic shortest path by applying traffic flows in the future for intermediated intersections can give more accurate traffic information and improve the quality of services of Telematics than finding a static shortest path applying by traffic flows of the starting time for intermediated intersections.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.2
• /
• pp.186-192
• /
• 2014

In this paper, we analysed vessel traffic volume and patterns of traffic flow for ships using areas where included wind farm site and adjacent waters of Daejeong Offshore Wind Farm, and estimated traffic volume by classified navigational routes according to suggestion of rational routeing measures on the basis of classified patterns after installation of offshore wind facilities. Also, we assessed vessel traffic safety for each designed routeing measures on the basis of estimated traffic volume and proposed requisite countermeasures for the safe navigation of ships. With a result of analysing patterns of traffic flow, the current traffic flow was classified by 8 patterns and the annual traffic volume was predicted to 8,975 ships. On the basis of these, expected the vessel traffic volume according to designed four routeing mesaures after installation of wind farm. As result of assessing vessel traffic safety by using powered-vessel collision model of SSPA on the basis of the estimated traffic volume, the value of collision probability was less than safe criteria $10^{-4}$. Thereby we made sure usability of the designed routeing measures for the safe navigation of ships.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.4
• /
• pp.179-188
• /
• 2017

It is very challenging to analyze the traffic flow in the city because there are lots of traffic accidents, intersections, and pedestrians etc. Now, even in mid-size cities Bus Information Systems(BIS) have been deployed, which have offered the forecast of arriving times at the stations to passengers. BIS also provides more informations such as the current locations, departure-arrival times of buses. In this paper, we perform the time-series analysis of the traffic flow using the data of the average trvel time and the average speed between stations extracted from the BIS. In the mid size cities, the data from BIS will have a important role on prediction and analysis of the traffic flow. We used the Dynamic Linear Model(DLM) for how to make the time series forecasting model to analyze and predict the average speeds at the given locations, which seem to show the representative of traffics in the city. Especially, we analysis travel times for weekdays and weekends separately. We think this study can help forecast the traffic jams, congestion areas and more accurate arrival times of buses.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.44-57
• /
• 2019

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.241-241
• /
• 2022

우리나라의 자연하천은 대부분 사행하천으로 이루어져 있다. 특히 사행하천의 만곡부에서는 2차류가 발생할 수 있으며, 이는 만곡부의 흐름에 비선형적인 영향을 미치게 되어 흐름과 유사이송에 대해 복잡한 상호작용을 하게 된다. 하천에 서식하고 있는 식생 또한 흐름에 영향을 줄 수 있다. 더군다나, 댐으로 인한 유사의 차단과 방류량 통제는 댐 하류 구간에 영향을 주게 되어 식생활착을 야기할 수 있으며 활착 이후에는 통제가 어려울 정도로 식생밀도가 증가하며 번성하기도 한다. 이러한 현상이 지속되면 식생으로 인해 통수능이 저하되기도 하며, 홍수범람이 발생할 수 있다. 따라서 만곡부 하도식생에 의한 흐름변화를 연구하는 것은 치수적인 측면에서 중요하다. 본 연구에서는 이러한 필요성을 고려하여, 2차원 흐름모형인 Nays2D를 활용하여 식생대의 밀도변화에 따른 흐름변화 예측모의를 위한 수치실험을 수행하였다. 연구지역은 사행하천으로서 식생대가 발달한 대청댐 하류 구간이다. 본 연구에서는 현장조사를 통해 구축한 식생특성을 반영하여 예측모의를 수행하였으며, 이를 위해 부등류를 기반으로 식생밀도에 따라 2021년의 식생현황, 전체벌채(식생없음), 솎아베기(2021년 식생밀도의 0.5배), 존치(2021년 식생밀도의 2배)로 가정하여 모형을 구축하였다. 모의결과, 전체벌채의 경우, 2차류에 의해 흐름이 만곡부 외측으로 집중되었기 때문에 만곡부 외측에서 수심과 유속이 증가하였다. 2021년 식생현황과 솎아베기, 그리고 존치의 경우, 공통적으로 만곡부 외측에 식생이 존재하고 있기 때문에 전체벌채보다 수심이 증가하고 유속이 감소하였으며 식생대 주변과 하도중앙으로 흐름이 집중되는 경향을 나타났다. 이를 통해, 전체벌채의 경우 치수적으로 만곡부 외측에서 2차류의 발달로 세굴을 야기할 가능성을 확인할 수 있었으며 식생이 존재하는 경우에는 만곡부 외측에 퇴적이 발생할 수 있을 것으로 판단된다. 본 연구에서는 식생과 흐름만을 고려하여 수치모의를 수행하였으나 추후 연구에서는 흐름과 하상변동을 모두 고려하여 수치모의를 수행한다면 보다 세부적으로 식생밀도가 하천환경에 미치는 영향 이해할 수 있을 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.480-480
• /
• 2023

본 연구에서는 섬진강 하류에서 2차원 흐름 모형인 Nays2DH 활용하여 섬진강댐 하류, 송정 구간의 식생밀도를 고려한 부등류 계산을 통해 하도의 수위 및 유속을 예측 모의하는 방법론을 제시하고 모의결과를 분석하였다. 현장조사를 실시하여 하도의 식생밀도를 산정하였으며. 식생밀도는 섬진강댐 하류 1.15 m-1, 송정 0.35 m-1로 조사되었다. 모의결과, 섬진강댐 하류에서 원심력에 의해 만곡부 외측에서 수심이 가장 깊게 나타났으며(최대 7.48 m), 최대유속도 동일지점에서 5.58 m/s로 형성되었고 하안침식으로 인한 하도변화 예측결과, 유속이 빠른 만곡부 외측에서 세굴되었으며, 내측에서는 퇴적되었고 만곡부가 끝난 지점부터 중앙사주가 발달하며 흐름이 하도 좌안으로 집중하여 세굴이 진행되었다. 송정구간에서 저수로 폭이 좁아지는No.40+200 지점에서 수심이 가장 깊으며(15.8 m), 유속은 하폭이 좁고 경사가 급해지는 No.39+800 지점에서 최대 7.97 m/s 로 나타났다. 하안침식으로 인한 하도변화 예측결과, 하폭이 넓어지는 No.40+800에서 유속이 감소하여 사주가 발달하였다. 본 연구에서는 섬진강 하류의 실제 식생밀도를 반영하여 수치모의를 하였기 때문에 흐름과 식생관리에 따른 실무적 대책방안 마련에 도움이 될 것으로 판단되며, 본 연구에서 활용한 분석방법과 결과들은 섬진강 유역의 하천관리 방안을 구축하기 위한 기초자료로 활용될 수 있을 것으로 기대된다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.3
• /
• pp.215-222
• /
• 2022

The purpose of air traffic flow management is to balance demand and capacity in the national airspace, and its performance relies on an accurate capacity prediction of the airport or airspace. This paper developed a regression model that predicts the number of aircraft actually departing and arriving in a terminal maneuvering area. The regression model is based on a boosting ensemble learning algorithm that learns past aircraft operational data such as time, weather, scheduled demand, and unfulfilled demand at a specific airport in the terminal maneuvering area. The developed model was tested using historical departure and arrival flight data at Incheon International Airport, and the coefficient of determination is greater than 0.95. Also, the capacity of the terminal maneuvering area of interest is implicitly predicted by using the model.

• 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.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.10a
• /
• pp.16-18
• /
• 2010

현재 우리나라에서 해상 수송은 무역 수 출입의 90%이상을 담당하고 있으며, 지정학적인 측면에서도 많은 중요한 역할을 하고 있다. 해상에서의 교통시스템 기능이 안정적으로 유지되고, 더욱 발전되기 위해서 무엇보다 연안 해역에서의 선박 교통에 대한 정확한 이해가 필요하다. 본 논문에서는 선박별 항적과 같은 선박 교통의 자료들을 기초로 하여, 우리나라의 각 수역별로 선박 흐름을 재현해 보는 연구를 수행하였다. 구체적으로 선박종류 항로특성 실제교통량 등을 해상 교통의 구성요소별로 분류하고, 자동피항 기능을 포함한 다수 선박간의 흐름을 재현하는 프로그램을 개발하였다. 개발된 프로그램은 목포항의 선박교통 자료를 기본으로 시뮬레이션을 실시하여 검증하였다. 또한 개발된 모델을 수역의 교통안전성 예측, 항로내 시설물 설치시 적정성 문제 등에 적용가능한 지를 고려하였다.