• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.51-62
• /
• 1996

Electro sensitive traffic system can not consider passenger car unit, so it causes start up delay time and passenger waiting time. In this paper, it antecedently creates passenger car unit at the bottom intersection using neural network. But, sometimes it can make mistakes due to changes in car weight, car speed, and passing area. Therefore, it consequently reduces the car waiting time and start-up delay time using fuzzy control of feed-back data. Moreover, to prevent spillback, it can adapt control even though upper traffic intersection has a different saturation rate, road length, road slope and road width.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.2
• /
• pp.107-116
• /
• 2012

The experiment was performed to analyze the intersectional ventilation efficiency by intersection structure and Jet Fan in network-form road tunnel. For this, the size of real road tunnel was reduced by 1/45. To apply traffic inertia force when driving, blower fan was used to form an airflow in model tunnel and the intersectional efficiency was also investigated by measuring the speed at local point of the tunnel. To improve the reduction of ventilation caused by the structure character, Jet Fan was installed to optimize ventilation efficiency in tunnel.

• Journal of Korean Society of Transportation
• /
• v.12 no.3
• /
• pp.49-64
• /
• 1994

The development of a mathematical modular framework based on Petri Network theory to model a traffic network is the subject of this paper. Traffic intersections are the primitive elements of a transportation network and are characterized as event driven and asynchronous systems. Petri network have been utilized to model these discrete event systems; further analysis of their structure can reveal information relevant to the concurrency, parallelism, synchronization, and deadlock avoidance issuse. The Petri-net based model of a generic traffic junction is presented. These modular networks are effective in synchronizing their components and can be used for modeling purposes of an asynchronous large scale transportation system. The derived model is suitable for simulations on a multiprocessor computer since its program execution safety is secured. The software pseudocode for simulating a transportation network model on a multiprocessor system is presented.

• Structural Engineering and Mechanics
• /
• v.91 no.5
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.703-712
• /
• 2015

This paper proposes the UIGRP, which can tackle the problem of the network disconnection and packet transmission delay caused by turning vehicles frequently in an urban intersection. The UIGRP was designed as follows. First, it calculates the direction of vehicles using the moving direction of vehicles and the location of a destination. Second, it makes the RSU measure the density of an urban intersection. Third, the TGF Algorithm in the UIGRP decides the data transmission paths by setting as an intermediate node, not only the vehicle that is moving in the direction where a destination node is located, but also the node that has the highest density. The TGF algorithm using a moving direction and density minimizes or removes the occurrence of local maximum problems that the existing Greedy Forwarding algorithm has. Therefore, the simulation result shows that UIGRP decreases the occurrence of local maximum problems by 3 and 1 times, and the packet transmission time by 6.12 and 2.04(ms), and increases the success rate of packet transmission by 15 and 3%, compared to the existing GPSR and GPUR.

• Journal of the Korean Institute of Gas
• /
• v.13 no.2
• /
• pp.30-35
• /
• 2009

The result of this research explains an interactive behavior of buried steel pipe located below hume pipe using concept of effective depth and effective length against their intersection angle and burial distance. The cover depth of upper rigid (hume) pipe is 1.0m and depth range of flexible (steel) pipe is 0.5m to 5m from beneath bottom of hume pipe. And one more variable is their intersection angle in this study, it was considered from $0^{\circ}$ to $90^{\circ}$. From the results of this study, the effective depth is proportionally increasing with its intersection angle and decreasing with distance increment between two pipes. Finally, the relationship between effective length and summation of occurred bending stress is defined.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.1
• /
• pp.115-126
• /
• 2019

Recently, in order to solve the traffic congestion in urban areas and to improve the peripheral environment, research on the design and construction technology development of great depth underground double-deck tunnel is under way by using the underground space in the urban area. The network type double-deck tunnel is in the form of an intersection with a small cross section and a steep slope as per construction at the base of a flatland, so that the fire smoke spreads rapidly in case of fire, which is expected to cause damage of human life. Therefore, this study is analyzed the delay effect of fire smoke diffusion according to the installation and non - installation of delay system for fire smoke diffusion at the intersection. Fire fumes were delayed up to 270 seconds when the delay system for fire smoke diffusion was installed at the intersection and it is analyzed that the greater the operating area of the delay system for fire smoke diffusion, the more preventable the damage of human life of the intersection.

• 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.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.1
• /
• pp.41-48
• /
• 2007

Latest advances in network sensor technology and state of the art of mobile robot, and artificial intelligence research can be employed to develop autonomous and distributed monitoring systems. In this study, as the preliminary step for developing a multi-purpose "Intelligent Space" platform to implement advanced technologies easily to realize smart services to human. We will give an explanation for the ISpace system architecture designed and implemented in this study and a short review of existing techniques, since there exist several recent thorough books and review paper on this paper. Instead we will focus on the main results with relevance to the DIND data fusion with CI of Intelligent Space. We will conclude by discussing some possible future extensions of ISpace. It is first dealt with the general principle of the navigation and guidance architecture, then the detailed functions tracking multiple objects, human detection and motion assessment, with the results from the simulations run.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.