• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.1
• /
• pp.41-52
• /
• 2016

When the queue length of congestion vehicles in tunnel fire is extended beyond tunnel length, the capacity of smoke control system needs to be increased in line with ventilation resistance. However, the vehicle queue length is not defined, so a rational equation is necessary in current fire prevention guideline. This study is intended to propose an equation to calculate the queue length considering the number of vehicles in queue in tunnel fire and evaluate the applicability by tunnel length as well. When it comes to normal tunnel, it is necessary to compare the vehicle queue length with tunnel length up to the length of 1,200 m in a bid to avoid applying the vehicle queue length excessively in case of fire. As a result of evaluation of applicability to model a tunnel, saving the number of jet fan for smoke control appeared to be effective. Besides, quantitative approach to explain the vehicle queue length through the relationship between the percentage of large vehicles and tunnel length was presented. Consequently, when the queue length of the congestion vehicles exceeds the tunnel length in determining the capacity of smoke control system in case of fire, the number of vehicles beyond the tunnel length needs to be excluded from estimating the ventilation resistance by vehicles.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.39-57
• /
• 2018

The purpose of this study was to construct an artificial intelligence model that learns and estimates the relationship between vehicle queue length and link travel time in urban areas. The vehicle queue length estimation model is modeled by three models. First of all, classify whether vehicle queue is a link overflow and estimate the vehicle queue length in the link overflow and non-overflow situations. Deep learning model is implemented as Tensorflow. All models are based DNN structure, and network structure which shows minimum error after learning and testing is selected by diversifying hidden layer and node number. The accuracy of the vehicle queue link overflow classification model was 98%, and the error of the vehicle queue estimation model in case of non-overflow and overflow situation was less than 15% and less than 5%, respectively. The average error per link was about 12%. Compared with the detecting data-based method, the error was reduced by about 39%.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.3
• /
• pp.59-72
• /
• 2017

As the part of study which handles the measure to use the individual vehicle information of taxi GPS data on signal controls in order to overcome the limitation of Loop detector-based collecting methods of real-time signal control system, this paper conducted series of evaluations and improvements on link travel time, queue vehicle time estimates and traffic condition decision algorithm from the research introduced in 2016. considering the control group and the other, the link travel time has enhanced the travel time and the length of queue vehicle has enhanced the estimated model taking account of the traffic situation. It is analyzed that the accuracy of the average link travel time and the length of queue vehicle are respectably both approximately 95 % and 85%. The traffic condition decision algorithm reflected the improved travel speed and vehicle length. Smoothing was performed to determine the trend of the traffic situation and reduce the fluctuation of the data, and the algorithms have refined so as to reflect the pass period on overflow judgment criterion.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5D
• /
• pp.563-570
• /
• 2009

This study is aimed to analyze the overall effects of the additional delay caused by the vehicle in front of the queue, at the signal, to the total delay estimation. To estimate the average vehicle delay at the signalized intersection, as survey of the queue length at the intersection and traffic counts were conducted. As a result of this analysis, all of the three delay estimation methods turned out to be similar in that the estimation of the average delay for the test vehicle was less than 60 sec/vehicle. However, the average delay time for the vehicle in front of the queue only, was estimated at 60-70 sec/vehicle which is similar to the average delay of the test vehicle.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.3
• /
• pp.45-51
• /
• 2016

Existing real-time signal control system was brought up typical problems which are supersaturated condition, point detection system and loop detection system. For that reason, the next generation signal control system of advanced form is required. Following thesis aimed at calculating queue length for the next generation signal control system to utilize basic parameter of signal control in crossing queue instead of the volume of real-time through traffic. Overflow saturated condition which was appeared as limit of existing system was focused to set-up range. Real-time location information of individual vehicle which is collected by GPS data. It converted into the coordinate to apply shock wave model with an linear equation that is extracted by regression model applied by a least square. Through the calculated queue length and link length by contrast, If queue length exceed the link, queue of downstream intersection is included as queue length that upstream queue vehicle is judeged as affecting downstream intersection. In result of operating correlation analysis among link travel time to judge confidence of extracted queue length, Both of links were shown over 0.9 values. It is appeared that both of links are highly correlated. Following research is significant using real-time data to calculate queue length and contributing to signal control system.

• Journal of Korean Society of Transportation
• /
• v.23 no.8 s.86
• /
• pp.181-191
• /
• 2005

This study developed an algorithm for real-time signal control based on the detection system that can collect sectional travel time. The signal control variable is maximum queue length per cycle and this variable has a sectional meaning. When a individual vehicle pass through the detector, we can gather the vehicle ID and the detected time. Therefor we can compute the travel time of an individual vehicle between consecutive detectors. This travel time informations were bisected including the delay and not. We can compute queue withdrawing time using this bisection and the max queue length is computed using the deterministic delay model. The objective function of the real-time signal control aims equalization of queue length for all direction. The distribution of the cycle is made by queue length ratios.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.54-62
• /
• 2018

As a part of realization of artificial intelligence signal(AI Signal), this study proposed an actuated signal algorithm based on vehicle queue length that estimates in real time by deep learning. In order to implement the algorithm, we built an API(COM Interface) to control the micro traffic simulator Vissim in the tensorflow that implements the deep learning model. In Vissim, when the link travel time and the traffic volume collected by signal cycle are transferred to the tensorflow, the vehicle queue length is estimated by the deep learning model. The signal time is calculated based on the vehicle queue length, and the simulation is performed by adjusting the signaling inside Vissim. The algorithm developed in this study is analyzed that the vehicle delay is reduced by about 5% compared to the current TOD mode. It is applied to only one intersection in the network and its effect is limited. Future study is proposed to expand the space such as corridor control or network control using this algorithm.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.2 s.7
• /
• pp.13-22
• /
• 2005

The purpose of this research is how to estimate the traffic queue length in the signal intersection accurately. The current traffic queue length algorithm in COSMOS has been using the congestion diagram which comes from the speed of an average separated vehicle - using average vehicle length and the occupancy time from loop detectors. So some errors were occurred by the speed estimation method using average vehicle lengths. And Operators had been difficult to optimize some variables for measuring the traffic queue length estimation algorithm in COSMOS. Therefore the traffic queue length estimation algorithm on the basis of the relation between distances and occupancy rates from loop detectors was developed in this thesis. This thesis had the advantage of using occupancy rates which came out from loop detectors easily and no need to optimize some variables for the established algorithm in COSMOS. And the results of testing this algorithm in some sites which had installed COSMOS system showed better results than COSMOS system's results. But it was noted that further studies which carry it out in various sites and under various cases are necessary for applying to actual intersections.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.2
• /
• pp.133-141
• /
• 2021

The probe vehicle penetration rate is a required parameter in the estimation of entire volume, density, and queue length from probe vehicle data. The previous studies have proposed estimation methods without point detectors, which are based on probability structures for the locations of probe and non-probe vehicles; however, such methods are poorly suited to the case of multi-lane streets. Therefore, this study aimed to estimate the probe vehicle penetration rate at a multi-lane intersection and introduce a probability distribution of the queue length of each lane. Although a gap between estimates and observations was found, the estimates followed the trend of observations; the estimation could be improved by the correction factor hereafter. This study is expected to be used as a basic study for the estimation of entire volume, density, and queue length at multi-lane intersections without point detectors.

• Journal of Korean Society of Transportation
• /
• v.27 no.2
• /
• pp.179-187
• /
• 2009

Currently, the signalized intersections in Korea are operated without providing an emergency vehicle preemption control strategy. Thus, it might threaten the safety of the pedestrians and drivers on highways when an emergency vehicle faces congested traffic conditions. The existing preemption control is activated when an emergency vehicle is detected along a path. This enables emergency vehicles to progress uninterrupted, but it also increases the delay of other vehicles. In this paper, a revised preemption control strategy considering queue length restrictions is proposed to make both a progressive movement of an emergency vehicle and reduce delay of other vehicles simultaneously. By applying the preemption control strategy through a simulation study, it was shown that delay of an emergency vehicle decreased to 44.3%-96.1% and speed increased to 8.8%-42.0% in all 9 cases as compared with a conventional signal control. The existing preemption control is superior for oversaturated conditions (v/c >1.0) or a link length less than 200m. However, the preemption control considering queue length constraints shows better performance than the existing preemption control when the v/c is less than 0.8 and a link length is longer than 500m.