• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Journal of Korean Society of Transportation
• /
• v.32 no.6
• /
• pp.675-685
• /
• 2014

This paper develops a differentiated pricing strategy over each segment of expressways based on the second-best pricing method for reducing congestion. To this end, a bi-level problem is proposed, in which the upper level of the model is formulated to determine toll level of each segment for minimizing traffic congestion, whereas the lower level of the model is formulated as a variable demand assignment problem. The sensitivity analysis based algorithm is took placed to find optimal solutions of upper level model. An application of the proposed model uses the modified Sioux-Falls network. The results show that the segment-based differentiated pricing strategy performs better than the existing uniform pricing strategy in reducing traffic congestion. This study can be applied as a demand management method to relieve disutility of excessively congested segments of expressways.

• Journal of Broadcast Engineering
• /
• v.10 no.3
• /
• pp.297-312
• /
• 2005

The multimedia traffic of continuous video and audio data via streaming service accounts for a significant and expanding portion of the Internet traffic. This streaming data delivery is mostly based on RTP with UDP. However, UDP does not support congestion control. For this reason, UDP causes the starvation of congestion controlled TCP traffic which reduces its bandwidth share during overload situation. In this paper, we propose a new TCP-friendly rate control scheme called 'TF-RTP(TCP-Friendly RTP)'. In the congested network state, the TF-RTP exactly estimates the competing TCP's throughput by using the modified parameters. Then, it controls the sending rate of the video streams. Therefore, the TF-RTP adjusts its sending rate to TCP-friendly and fair share with competing TCP traffics. Through the simulation, we prove that the TF-RTP correctly estimates the TCP's throughput and improves the TCP-friendliness and fairness.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.51-62
• /
• 2022

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

• Journal of Korean Society of Transportation
• /
• v.30 no.3
• /
• pp.83-91
• /
• 2012

The objective of this study is to build a methodology for evaluating intelligent transportation systems (ITS) projects, by selecting measures of effectiveness (MOEs) and developing an approach to collect and process traffic data. While reviewing the existing MOEs and evaluation methodologies for ITS projects, several problems were found, such as the complication in delineating study areas, the absence of standardized evaluation methodologies, and the duplication in selecting MOEs. To tackle these problems, two MOEs capable of directly evaluating traffic conditions were chosen: i.e., average vehicle speed and traffic volume. Both MOEs can not only include all the functions of the existing MOEs, but also be simpler and more objective in evaluating real traffic conditions. The traffic volume can be measured by using either "cordon line" or "all point average" methods. On the other hand, measuring the average vehicle speed depends on site-specific characteristics such as traffic flow states (interrupted or uninterrupted) and traffic conditions (congested or uncongested). The present methodology is easily understandable for anyone and applicable for any ITS project, and is also expected to contribute to building a standardized evaluation system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1D
• /
• pp.51-63
• /
• 2011

This study suggests that prior to construction of the 2nd Changwon tunnel and implementation of the demanded free of charge on Changwon tunnel, it is recommended to improve the traffic facilities and management of the traffic condition in order to create an efficient road that will keep traffic flow to a minimum and maintain the facilities proper working order. It has been generally accepted that the 2nd Changwon tunnel is necessary to construct and open as soon as possible. This is due to the service level of current traffic volume in the Changwon tunnel pay toll road which have been so congested that the fees have increased causing a public complaint to be filed, demanding a early free of charge be implemented for the Changwon tunnel. Furthermore, the objective and impartial analysis of the traffic situation based on a simulation of the alternative and traffic congestion fees has been provided to make the early free of charge on toll road as soon as possible. Finally, careful attention should be paid to seek to make the early free of charge on toll road in order to minimize the damages both specified and unspecified that may arise the prompt settlement of construction repayments and security of minimum management fees should be given priority over other alternatives.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.1
• /
• pp.27-41
• /
• 2011

This research proposes new tram signal coordination model, called MAXBAND MILP-Tram for a passive tram signal priority strategy. The proposed model was formulated based on the MAXBAND model that was a traditional arterial signal optimization model. The model could calculate the bandwidth solutions for both general-purpose-lane traffic and median-tram-lane traffic. Lower progression speed are applied for the tram traffic considering lower running speed and dwell time at the stations. A phase sequence procedure determines the green times and left-turn phase sequences for tram traffic in median tram lane. To estimate the performance of the MILP-Tram model, the control delay of trams were estimated using the micro simulation model, VISSIM. The analysis results showed 57 percent decrease of the tram compared to the conventional signal timing model. The delay for car, however, increased 18 percent. The sensitivity analysis indicated that the passive tram signal priority strategy using the offset and phase sequence optimization was effective in reducing the person delay under the congested traffic condition.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.5
• /
• pp.1999-2007
• /
• 2013

The key characteristics of two-lane-and-two-way traffic flow are platoon and overtaking caused by low-speed vehicle such as truck. In order to develop two-way traffic flow model comprised of CF(car-following) and overtaking model, it is essential to develop a car-following model which is suitable to two-way traffic flow. Short distance between vehicles is caused when a high-speed vehicle tailgates and overtakes foregoing low-speed vehicle on two-way road system. And a vehicle following low-speed vehicle decides to overtake the front low-speed vehicle using suitable space within the headway distribution of opposite traffic flow. For this reason, a two-way CF model should describes not only running within short gap but also headway distribution. Additionally considering domestic two-way-road size, there is a on-going need for large-network simulation, but there are few studies for two-way CF model. In this paper, a two-way CA model is developed, which explains two-way CF behavior more realistic and can be applied for large road network. The experimental results show that the developed model mimics stop-and-go phenomenon, one of features of congested traffic flow, and efficiently generates the distribution of headway. When the CF model is integrated with overtaking model, it is, therefore, expected that two-way traffic flow can be explained more realistically than before.

• Journal of Navigation and Port Research
• /
• v.39 no.3
• /
• pp.199-207
• /
• 2015

In ports of Korea, the marine traffic flow is congested due to a large number of vessels coming in and going out. In order to improve the safety and efficiency of these vessels, South Korea is operating with a Vessel Traffic Service System, which is monitoring its waters for 24 hours. However despite these efforts of the VTS (Vessel Traffic Service) officers, collisions are occurring continuously, the risk situation is analyzed that occurs once in about 20 minutes, the risk may be greater. It investigated to reduce these accidents by providing a safety standard for collision danger in a timely manner. Thus, this study has developed a risk prediction module to predict risk in advance. This module can avoid collision risk to adjust the speed and course of ship using a risk evaluation model based on ship operator's risk perspective. Using this module, the ship operators and VTS officers can easily be identified risks in complex traffic situations, so they can take an appropriate action against danger in near future including course and speed change. To verify the effectiveness of this module, this paper predicted the risk of each encounter situation and confirmed to be capable of identifying a risk changes in specific course and speed changes at Busan coastal water.

• Journal of Radiation Protection and Research
• /
• v.27 no.3
• /
• pp.189-198
• /
• 2002

The time for evacuation of residents in emergency planning zone(EPZ) of Uljin nuclear site in case of a radiological emergency was estimated with traffic analysis. Evacuees were classified into 4 groups by considering population density, local jurisdictions, and whether they ate residents or transients. The survey to investigate the behavioral characteristics of the residents was made for 200 households and included a hypothetical scenario explaining the accident situation and questions such as dwelling place, time demand for evacuation preparation transportation means for evacuation, sheltering place, and evacuation direction. The microscopic traffic simulation model, CORSIM, was used to simulate the behavior of evacuating vehicles on networks. The results showed that the evacuation time required for total vehicles to move out from EPZ took longer in the daytime than at night in spite that the delay times at intersections were longer at night than in the daytime. This was analyzed due to the differences of the trip generation time distribution. To validate whether the CORSIM model fan appropriately simulate the congested traffic phenomena assumable in case of emergency, a benchmark study was conducted at an intersection without an actuated traffic signal near Uljin site during the traffic peak-time in the morning. This study indicated that the predicted output by the CORSIM model was in good agreement with the observed data. satisfying the purpose of this study.