• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.459-473
• /
• 2007

In this paper, we suggest a spatial regression model to predict AADT. Although Euclidian distances between one monitoring site and its neighboring sites were usually used in the many analysis, we consider the shortest travel path between monitoring sites to predict AADT for unmonitoring site using spatial regression model. We used universal Kriging method for prediction and found that the overall predictive capability of the spatial regression model based on shortest travel path is better than that of the model based on multiple regression by cross validation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.491-494
• /
• 2019

The results from the analysis of recent security breach cases of industrial control systems revealed that most of them were caused by the employees of a partner company who had been managing the control system. For this reason, the majority of the current company security management systems have been developed focusing on their performances. Despite such effort, many hacking attempts against a major company, public institution or financial institution are still attempted by the partner company or outsourced employees. Thus, the institutions or organizations that manage Industrial Control Systems (ICSs) associated with major national infrastructures involving traffic, water resources, energy, etc. are putting emphasis on their security management as the role of those partners is increasingly becoming important as outsourcing security task has become a common practice. However, in reality, it is also a fact that this is the point where security is most vulnerable and various security management plans have been continuously studied and proposed. A system that enhances the security level of a partner company with a Virtual Desktop Infrastructure (VDI) has been developed in this study through research on the past performances of partner companies stationed at various types of industrial control infrastructures and its performance outcomes were statistically compiled to propose an appropriate model for the current ICSs by comparing vulnerabilities, measures taken and their results before and after adopting the VDI.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.243-250
• /
• 2019

In this paper, we propose a system for processing and analyzing drone image information which can be applied variously in disasters-security situation. The proposed system stores the images acquired from the drones in the server, and performs image processing and analysis according to various scenarios. According to each mission, deep-learning method is used to construct an image analysis system in the images acquired by the drone. Experiments confirm that it can be applied to traffic volume measurement, suspect and vehicle tracking, survivor identification and maritime missions.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.69-84
• /
• 2021

Awareness of boats is a main issue in areas of fishery management, illegal fishing, and maritime traffic, etc. For the awareness, Automatic Identification System (AIS) and Vessel-Pass System (V-PASS) have been widely used to collect the boat-related information. However, only using these systems makes it difficult to collect the accurate information. Recently, satellite-based data has been increasingly used as a cooperative system. In 2015, U.S. National Oceanic and Atmospheric Administration (NOAA) developed a boat detection algorithm using Visible Infrared Imaging Radiometer Suite (VIIRS) Day & Night Band (DNB) data. Although the detections have been widely utilized in many publications, it is difficult to estimate the night-time fishing boats immediately. Particularly, it is difficult to estimate the threshold due to the lunar irradiation effect. This effect must be corrected to apply a single specific threshold. In this study, the moon phase was considered as the main frequency of this effect. Considering the moon phase, relational expressions are derived and then used as offsets for relative correction. After the correction, it shows a significant reduction in the standard deviation of the threshold compared to the threshold of NOAA. Through the correction, this study can set a constant threshold every day without determination of different thresholds. In conclusion, this study can achieve the detection applying the single specific threshold regardless of the moon phase.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.169-176
• /
• 2021

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1998.10a
• /
• pp.263-269
• /
• 1998

The forecasting of container cargo volumes should be estimated correctly because it has a key roles on the establishment of port development planning, and the decision of port operating system. Container cargo volumes have a dynamic characteristics which was changed by effect of competitive ports. Accordingly forecasting was needed overall approach about competitive port's development, alternation and information. But, until now, traffic forecasting was not executed according to competitive situation, and that was accomplished at the point of unit port. Generally, considering the competition situation, simulation method was desirable at forecasting because system's scale was increased, and the influence power was intensified. In this paper, considering this situation, the objectives can be outlined as follows. 1) Structural model constructs by System dynamics method. 2) Structural simulation model develops according to modelling of competitive situation by expended SD method which included HEP(Hierarchical Fuzzy Process) And actually, effectiveness was verified according to proposed model to major port in northeast asia.

• Ocean Systems Engineering
• /
• v.13 no.4
• /
• pp.385-399
• /
• 2023

A collision between a ship and an offshore platform may result in structural damage and closure; therefore, damage analysis is required to ensure the platform's integrity. This paper presents a damage assessment of a three-legged jacket platform subjected to ship collisions using the industrial finite element program Bentley SACS. This study considers two ships with displacements of 2,000 and 5,000 tons and forward speeds of 2 and 6.17 meters per second. Ship collision loads are applied as a simplified point load on the center of the platform's legs at inclinations of 1/7 and 1/8; diagonal bracing is also included. The jacket platform is modelled as beam elements, with the exception of the impacted jacket members, which are modelled as nonlinear shell elements with elasto-plastic material and constant isotropic hardening to provide realistic dented behavior due to ship collision load. The structural response is investigated, including kinetic energy transfer, stress distribution, and denting damage. The simulation results revealed that the difference in leg inclination has no effect on the level of localized denting damage. However, it was discovered that a leg with a greater inclination (1/8) resists structural displacement more effectively and absorbs less kinetic energy. In this instance, the three-legged platform collapses due to the absorption of 27.30 MJ of energy. These results provide crucial insights for enhancing offshore platform resilience and safety in high-traffic maritime regions, with implications for design and collision mitigation strategies.

• Journal of Korean Society of Transportation
• /
• v.27 no.6
• /
• pp.79-88
• /
• 2009

The objective of this study is to develop the new vehicle classification algorithm and minimize classification errors. The existing vehicle classification algorithm collects data from loop and piezo sensors according to the specification("Vehicle classification guide for traffic volume survey" 2006) given by the Ministry of Land, Transport and Maritime Affairs. The new vehicle classification system collects the vehicle length, distance between axles, axle type, wheel-base and tire type to minimize classification error. The main difference of new system is the "Wandering" sensor which is capable of measuring the wheel-base and tire type(single or dual). The wandering sensor obtains the wheel-base and tire type by detecting both left and right tire imprint. Verification tests were completed with the total traffic volume of 762,420 vehicles in a month for the new vehicle classification algorithm. Among them, 47 vehicles(0.006%) were not classified within 12 vehicle types. This results proves very high level of classification accuracy for the new system. Using the new vehicle classification algorithm will improve the accuracy and it can be broadly applicable to the road planning, design, and management. It can also upgrade the level of traffic research for the road and transportation infrastructure.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.5
• /
• pp.476-482
• /
• 2013

This study aims to enhance the effectivity of VTS(Vessel Traffic Service) control by investigating the minimum safe distance between vessel and vessel, vessel and land(obstacle) for the vessel's safe navigation within the VTS control area. In addition, to suggest basic data for the safe navigation, this study has done survey and analysis to each VTS center, and individual on the minimum safe distance to VTS operators of each ports of korea. Through ocean voyage by training ship, Singapore and Malacca strait's congested vessel traffic zone's control distance was compared and investigated the difference on safe distance by the different VTS operators. As a result, there was huge difference of minimum safe distance between the VTS operators belong to the same center. Over all, the port with gentle coastline, like donghae, the safe distance was wider than the other port. On the other hand, port with complex coastline and frequent entry and departure of the vessel, like mokpo, the safe distance was the shortest of all. Therefore, development of module suitable to port's natural conditions and traffic volume's necessity is required, for the operators affiliated to the same VTS center control according to formal method. Lastly, the full discussion by the expert group about establishment of standard control procedure in the future should be considered as well.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1900-1906
• /
• 2008

According as zone of life of big city is expanded by new city development etc.., need special skill master plan compensation which can be systematic for wide area traffic problem solution and confusion expense minimization in the metropolitan area because wide area of capital region traffic is gone continuously and continues. Accordingly, Kyonggi Province suggested rapid-transit railway achievement that can connect Seoul Gangnam in 20 minutes with Dongtan new city recently. MLTM(Ministry of Land Transport and Maritime Affaris) announced "Capital region railway network improvement plan research services (2007.12)" result that Gangnam High-speed railway route (Suse $\sim$ Dongtan $\sim$ Pyeongtaek) construction for offer High-speed railway service to capital region and Kyonggi southern part area inhabitantses and need to line capacity tribe solution by Seoul-Busan high-speed railway second-stage and Honam high speed railroad completion. Is judged that need examination about wide area rapid-transit railway combined application operation that take advantage of rail track reserve capacity of High-speed railway for utilization efficiency elevation of country and efficient investment of national finance according as High-speed railway and Gangnam rapid-transit railway route that is suggested in Kyonggi Province are overlaped. Therefore, in this research, I wish to quote investment efficiency plan of railroad business by that different kind's train is run in uniformity track by presenting combined application operation plan and working expenses curtailment effect etc. that is optimized through analysis of roadbed and E & M technology condition, intermediate station plan, train operation planning etc. in case of wide area rapid-transit railway and high-speed railway run combined application.