• Tunnel and Underground Space
• /
• v.13 no.6
• /
• pp.434-443
• /
• 2003

In this study, it was purposed to develop the new method for the prediction of pollutant concentration in road tunnels. The new method was the use of artificial neural network with the back-propagation algorithm which can model the non-linear system of tunnel environment. This network system was separated into two parts as the visibility and the CO concentration. For this study, data was collected from two highway road tunnels on Yeongdong Expressway. The tunnels have two lanes with one-way direction and adopt the longitudinal ventilation system. The actually measured data from the tunnels was used to develop the neural network system for the prediction of pollutant concentration. The output results from the newly developed neural network system were analysed and compared with the calculated values by PIARC method. Results showed that the prediction accuracy by the neural network system was approximately five times better than the one by PIARC method. In addition, the system predicted much more accurately at the situation where the drivers have to be stayed for a while in tunnels caused by the low velocity of vehicles.

• International Journal of Highway Engineering
• /
• v.19 no.6
• /
• pp.105-115
• /
• 2017

PURPOSES : The occurrence of unexpected disasters, including fire events, increases as the road network becomes complicated and traffic volume increases. When a fire event occurs on and under bridges, the damage extensively influences direct damage to structures, vehicles, and human life and secondary socioeconomic issues owing to traffic blockage. This study investigated potential fire-hazard risks on bridges of the Korean national route road. METHODS : The investigation was conducted using field investigation and analysis with satellite pictures and road views from commercial websites and the Bridge Management System (BMS). From the filed investigation, various potential fire resources were identified. The satellite pictures and road views were helpful in measuring and recognizing conditions underneath bridges, stowage areas, etc. RESULTS : There are various potential fire resources underneath bridges such as piled agricultural products, parked petroleum tanks, construction equipment, and attached high-voltage cables. A total of 94.6% of bridges have underneath clearances of less than 15 m. A bridge underneath volume that can stow a potential fire hazard resource was $7,332m^3$ on average, and most bridges have about $4,000m^3$ of space. Based on the BMS data, the amounts of PSC and steel girders were 29% and 25%, respectively. CONCLUSIONS : It was found that the amount of stowed potential fire hazard resources was proportional to the underneath space of bridges. Most bridges have less than 15 m of vertical clearance that can be considered as a critical value for a bridge fire. The fire risk investigation results should be helpful for developing bridge fire-protection tools.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.4
• /
• pp.39-46
• /
• 2009

Generally, Path-finding algorithms which use heuristic function may occur a problem of the increase of exploring cost in case of that there is no way determined by heuristic function or there are 2 way more which have almost same cost. In this paper, we propose an abstract graph for path-finding with dynamic information. The abstract graph is a simple graph as real road network is abstracted. The abstract graph is created by fixed-size cells and real road network. Path-finding with the abstract graph is composed of two step searching, path-finding on the abstract graph and on the real road network. We performed path-finding algorithm with the abstract graph against A* algorithm based on fixed-size cells on road network that consists of 106,254 edges. In result of evaluation of performance, cost of exploring in path-finding with the abstract graph is about 3~30% less than A* algorithm based on fixed-size cells. Quality of path in path-finding with the abstract graph is, However, about 1.5~6.6% more than A* algorithm based on fixed-size cells because edges eliminated are not candidates for path-finding.

• Tunnel and Underground Space
• /
• v.27 no.3
• /
• pp.132-145
• /
• 2017

Shock loss was not applied for the tunnel ventilation of road tunnel in the past. However, pressure losses due to the shock loss can be significant in network double-deck road tunnel in which combining and separating road structures exist. For the optimum ventilation design of network double-deck road tunnel, this study conducted 3D CFD numerical analysis for the shock loss at the combining and separating flows. The CFD model was made with the real-scale model that was the standard section of double-deck road tunnel. The shock loss coefficient of various combining and separating angles and road width was obtained and compared to the existing design values. As a result of the comparison, the shock loss coefficient of the $30^{\circ}$ separating flow model was higher and that of the two-lane combining flow model was lower. Since the combining and separating angles and road width can be important for the design of shock loss estimation, it is considered that this study can provide the accurate design factors for the calculation of ventilation system capacity. In addition, this study conducted 3D CFD analysis in order to calculate the shock loss coefficient of both combining and separating flows at flared intersection, and the result was compared with the design values of ASHRAE. The model that was not widened at the intersection showed three times higher at the most, and the other model that was widened at the intersection resulted two times higher shock loss coefficients.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.3
• /
• pp.19-30
• /
• 2008

Recently, the query processing algorithm in the field of spatial network database(SNDB) has been attracted by many Interests. But, there is little research on route-based queries. Since the moving objects move only in spatial networks, the efficient route-based query processing algorithms, like in-route nearest neighbor(IRNN), are essential for Location-based Service(LBS) and Telematics application. However, the existing IRNN query processing algorithm has a problem that it does not consider traffic jams in the road network. In this thesis, we propose an IRNN query processing algorithm which considers space restriction. Finally, we show that space-constrained IRNN query processing algorithm is efficient compared with the existing IRNN algorithm.

• Journal of the Korean Society of Safety
• /
• v.32 no.6
• /
• pp.150-156
• /
• 2017

A frozen road surface increases traffic accidents during the winter season. Hence, information on easily-frozen road sections and their specificities are required to prevent traffic accidents. Frozen road surfaces are determined by equipment measuring road surface temperatures. However, there are limitations in investigating the entire road network. Therefore, it is imperative to develop new methods that effectively determine road surface freezing risks. Meteorologically, road surfaces are frozen when the actual temperature cools down to the dew point temperature. Under this condition, there is likely to be frost if relative humidity reaches 100% and frozen road surfaces as the temperature gets lower. Meteorological characteristics give us an alternative to a direct measurement road surface temperature to estimate risks of road surface freezing. Based on the clues, the relationship between severity of traffic accidents and temperature changes is empirically investigated using Paju weather data. The results reveal that as the temperature gets lower and changes in current temperature are relatively small, the severity of traffic accidents become higher. In addition, the same is true when the difference between current temperature and the dew point temperature is relatively small, as it increases possibilities of road surface freezing. Future studies must investigate how current temperature and the dew point temperature affect road surface freezing and thereby establish a time-space scope to estimate possible road surface freezing sections using only weather and road material type data. This would provide invaluable information for predicting and preventing frozen road accidents based on weather patterns.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.149-158
• /
• 2005

The object of this paper is to develop the shortest path algorithm. The existing shortest path algorithm models are developed while considering travel time and travel distance. A few problems occur in these shortest path algorithm models, which have paid no regard to cognition of users, such as when user who doesn't have complete information about the trip meets a strange road or when the route searched from the shortest path algorithm model is not commonly used by users in real network. This paper develops a shortest path algorithm model to provide ideal route that many people actually prefer. In order to provide the ideal shortest path with the consideration of travel time, travel distance and road cognition, travel time is predicted by using Kalman filtering and travel distance is predicted by using GIS attributions. The road cognition is considered by using space data of GIS. Optimal routes provided from this paper are shortest distance path, shortest time path, shortest path considering distance and cognition and shortest path considering time and cognition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.199-202
• /
• 2009

The optimal path on real road network has been changed by traffic flow of roads frequently. Therefore a path finding system to find the optimal path on real network should consider traffic flow of roads that is changed on real time. The most of existing path finding methods do not consider traffic flow of roads and do not also perform efficiently if they use traffic information. In this paper, we propose an abstraction method of real road network based on the Terminal Based Navigation System (TBNS) with technique such as TPEG. TBNS can be able to provides quality of path better than before as using traffic information that is transferred by TPEG. The proposed method is to abstract real network as simple graph in order to use traffic information. It is composed boundary nodes based on real nodes, all boundary nodes that have the same of connection are merged together. The result of path finding on an abstract graph diminishes the search space.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.2
• /
• pp.120-134
• /
• 2015

Under the hypothesis that the form of road network could affect crime occurrence, this study demonstrates to prove them using Space Syntax with real crime data. We calculated integration, control, connection index by means of Space Syntax and analyzed the relationship between the three indexes and the number of crime occurrence on the each road. Next, in order to generalize the analysis results we adopted Multi-Agent Model and simulated several scenarios on the computer virtual space. The results revealed that integration index has the strongest relationship with crime occurrence both in the case of real study area and virtual space simulations. Though this study has several limitations on the extent of virtual space and realistic computer programming of agents' behavior, the results are meaningful to verify the relationship between the form of read network and crime occurrence. Moreover the simulation platform that this study developed has promising possibilities to find realistic solutions on the effective police deployment or facility layout to improve smart safe city development.