• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.321-327
• /
• 2023

With the development of artificial intelligence, the prediction system has become one of the essential technologies in our lives. Despite the growth of these technologies, traffic congestion at intersections in the 21st century has continued to be a problem. This paper proposes a system that predicts intersection traffic jams using a Convolutional LSTM (Conv-LSTM) algorithm. The proposed system models data obtained by learning traffic information by time zone at the intersection where traffic congestion occurs. Traffic congestion is predicted with traffic volume data recorded over time. Based on the predicted result, the intersection traffic signal is controlled and maintained at a constant traffic volume. Road congestion data was defined using VDS sensors, and each intersection was configured with a Conv-LSTM algorithm-based network system to facilitate traffic.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.6D
• /
• pp.623-636
• /
• 2012

Roundabout is an intersection that allows vehicles to pass through the intersection by circulating the circular traffic island at the center of the intersection. In this study, a comparative analysis was conducted on roundabout at five locations in order to deduce the operational result and financial effect of roundabout and signal intersection. As for the operational result, it was found that roundabout showed improvement effect in the average delay per vehicle compared to that of signal intersection by minimum of 65.6% and maximum of 91.77%. it was found that roundabout showed financial cost-saving effect in the traffic congestion cost compared to that of signal operation by minimum of 58.59% and maximum of 81.69% per year. It can be known from these analysis results that roundabout has significant operational effects under certain amount of traffic volume by allowing vehicles to pass through the intersection in a continuous way without much waiting time and stoppage from signal control.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.643-654
• /
• 2018

In order to understand and manage traffic flows in urban areas in the past, a variety of traffic engineering theoretical indicators such as intersection lag and highway speed have been applied. However, these theories and indicators have been developed under the constraints of traffic engineering research before the construction of intelligent transportation system. Since the ATIS system currently exists, it is necessary to introduce a separate traffic engineering technology that utilizes the data. In this paper, it is aimed to confirm whether it is applicable to intermittent flow (approach road, intersection, control group, main road axis) by using 'congestion intensity' which is already used in traffic engineering field. The results of this study are as follows: (1) The traffic signal improvement effect of urban road access road, intersection road, control group, Two verification studies were performed to verify the derived congestion intensity index. (1) verification of congestion intensity threshold value analysis and (2) crossing improvement using the congestion intensity. Through verification, it was confirmed that it is possible to apply the congestion intensity in the inter - city intermittent flow using the 5 - minute unit speed data so as to be able to escape from the existing traffic signal operation management which is past passive and manpower limit.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.8
• /
• pp.719-724
• /
• 2012

A traffic detection system is a device that collects traffic information around an intersection. Most existing traffic detection systems provide very limited traffic information for signal control due to the restriction of vehicle detection area. A signal control scheme determines the transition among signal phases and the time that a phase lasts for. However, the existing signal control scheme do not resolve the traffic congestion effectively since they use restricted traffic information. In this paper, a new traffic detection system with a zone division signal control scheme is proposed to provide correct and detail traffic information and decrease the vehicle's waiting time at the intersection. The traffic detection system obtains traffic information in a way of vehicle-to-roadside communication between vehicles and sensor network. A new signal control scheme is built to exploit the sufficient traffic information provided by the proposed traffic detection system efficiently. Simulation results show that the proposed signal control scheme has 121 % and 56 % lower waiting time and delay time of vehicles at an intersection than other fuzzy signal control scheme.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.5
• /
• pp.1111-1121
• /
• 2015

Roundabouts face a congestion problem when there are unbalanced traffic conditions, especially during peak times. The congestion at roundabouts results in long delay times and low level of service. Some research has addressed congestion problems of the metering roundabout, however, few studies have focused on the congestion issues of the double signals metering roundabout. This research bridges this gap through analyzing the congestion issues of the Old Belair double signals roundabout in Adelaide. The research proposes a new analysis method based on a four-nodes intersection in order for double signals roundabout analysis to be carried out as follows: firstly, at the modeling stage, a connection of four individual intersections, adjustment of lane geometry, input of directional traffic volumes, priority and phase time set up are proposed. Secondly, for calibration, PFF, critical gap, follow-up headway and extra bunching values have been applied. The results from the analysis show that the new method is able to analyze the delay time, level of service, degree of saturation and allow for further analysis.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1381-1386
• /
• 2019

As traffic congestion in cities becomes more serious, intelligent traffic control is actively being researched. Reinforcement learning is the most actively used algorithm for traffic signal control, and recently Deep reinforcement learning has attracted attention of researchers. Extended versions of deep reinforcement learning have been emerged as deep reinforcement learning algorithm showed high performance in various fields. However, most of the existing traffic signal control were studied in a single intersection environment, and there is a limitation that the method at a single intersection does not consider the traffic conditions of the entire city. In this paper, we propose a cooperative traffic control at multi-intersection environment. The traffic signal control algorithm is based on a combination of extended versions of deep reinforcement learning and we considers traffic conditions of adjacent intersections. In the experiment, we compare the proposed algorithm with the existing deep reinforcement learning algorithm, and further demonstrate the high performance of our model with and without cooperative method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.143-148
• /
• 2024

Traffic congestion has caused issues in various forms such as the environment and economy. Recently, an intelligent transport system (ITS) using artificial intelligence (AI) has been focused so as to alleviate the traffic congestion problem. In this paper, we propose a reinforcement learning-based traffic signal control algorithm that can smooth the flow of traffic while reducing discomfort levels of drivers and pedestrians. By applying the proposed algorithm, it was confirmed that the discomfort levels of drivers and pedestrians can be significantly reduced compared to the existing fixed signal control system, and that the performance gap increases as the number of roads at the intersection increases.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.697-702
• /
• 2018

Recently, the number of private cars has increased sharply due to the increase in national income. The sudden increase in the number of vehicles in limited territory has caused serious traffic congestion and the traffic congestion cost wasted on the road due to such traffic congestion is increasing every year. To solve this problem, we propose a traffic signal control system using image processing. In this paper, we use the camera installed at the intersection to measure the amount of traffic flowing in and out of each road simultaneously. We propose a traffic signal control system that can prevent traffic congestion before it happens. In the case of applying the traffic signal control system proposed in this paper to the daytime, the traffic volume could be measured accurately. However, the result of the experiment with the night-time general camera and the headlight with the infrared camera at the night-time of 72.8% was 86.6%.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.2D
• /
• pp.121-127
• /
• 2012

One of the traffic problems has been caused by the illegal parking because of the lack of parking space. Especially, the illegal occupancy of the road near an intersection makes an serious reduction of road capacity. The current illegal parking and stop-prohibited areas have been designated for less than 5 meters from the edge or the corner of the 4-leg intersection. However, in reality, the cars parked at the place over 5 meters have had a significant impact on the intersection traffic. In addition, many variables such as intersection type, size, and service levels should be considered as factors which influence on the traffic condition at the intersection. It was assumed that through and right-turn traffic rate have a significant impact on the 4-leg intersection with the illegal parking or stop near it. This study tried to verify the impact through the simulation implementation with MOE and LOS. It shows a guideline to designate the parking or stop-prohibited area near the 4-leg intersection under various traffic conditions.

• Journal of Korean Society of Transportation
• /
• v.21 no.6
• /
• pp.57-65
• /
• 2003

Traffic congestion on the streets is the major concern of Metropolitan areas in Korea. Especially the signalized intersections are the main spots where traffic congestion is to be created. Currently the subway construction has been on the process in Taegu Metropolitan city. The subway stations are usually located at the intersections where a large number of vehicles and people are moving. During the constructional period, such an intersection creates profoundly a great deal of traffic congestion due to the open-cut constructional method. Under circumstance of the constructional method, the lane configurations should be changed frequently and the surface conditions make drivers uncomfortable. The propose of this study is to propose the improved method of traffic operation at the large circled intersection under the construction. The Signalized Modern Roundabout(SMR) is applied modifying from the modern roundabout. The geometric design and signal operation of SMR is developed in this study. To verify the operation of SMR the comparative study is conducted between the operation of the open-cut method and SMR method using the micro-simulation program, NETSIM. The result of simulation shows that the delay caused by the operation of SMR is not higher than that under the open-cut method. SMR makes also the constructional period shorten, makes the cost of construction lessened and makes drivers more comfortable as well than the method of open-cut. Therefore, the study concludes that the operation of SMR is more efficient, economic and safer method than that of open-cut method at the large circled intersection under construction.