• Journal of Navigation and Port Research
• /
• v.43 no.6
• /
• pp.420-428
• /
• 2019

Although marine structures are a risk factor interfering with the passage of ships, there are no obvious guidelines on the required safety distance between ships and marine structures under regulations and laws. In this study, the width of the shipping route width was set based on the AIS data to analyze the separation distance between marine structures and ships, and the ships were classified by the length of each ship. By analyzing the distribution at marine structures, this study confirmed that the ships' traffic volume was in the form of normal distribution. To statistically analyze the separation distance between the traffic distribution results and the normal distribution of ships in this study, the traffic pattern analysis around the marine structures was performed. As a result, the traffic pattern was different by length and the recommended safety distance for each length is presented accordingly. Referring to the IMO (International Maritime Organization) the standard turning circle and reference of safety separation distance between ships and offshore wind turbines of the CESMA (Confederation of European Shipmasters' Associations) and P IANC (World Association for Waterborne Transport Infrastructures), the analysis was conducted on ships that did not follow the set distance among the AIS data by setting the distance within the recommended ship safety distance to 5-7 overall length. As a result, the 5.5 length over all of the safety recommendations were selected as appropriate, and based on the above results, the two cases recommending ship safety distance were proposed.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.737-746
• /
• 2022

Utilizing weather independent SAR images along with machine learning based object detector is effective in robust vessel monitoring. While conventional SAR images often applied amplitude data from Single Look Complex, exploitation of polarimetric parameters acquired from multiple polarimetric SAR images was yet to be implemented to vessel detection utilizing machine learning. Hence, this study used four polarimetric parameters (H, p₁, DoP, DPRVI) retrieved from eigen-decomposition and two backscattering coefficients (γ₀, _VV, γ₀, _VH) from radiometric calibration; six bands in total were respectively exploited from 52 Sentinel-1 SAR images, accompanied by vessel training data extracted from AIS information which corresponds to acquisition time span of the SAR image. Evaluating different cases of combination, the use of polarimetric indexes along with amplitude values derived enhanced vessel detection performances than that of utilizing amplitude values exclusively.

• Journal of Mechanical Science and Technology
• /
• v.14 no.11
• /
• pp.1232-1243
• /
• 2000

Motor vehicle accidents in rear impacts cause more than fifty percents of drivers to suffer from neck injuries. It is known that most neck injuries are associated with rear-end collisions at a speed lower than 32 km/h and between the Abbreviated Injury Scale (AIS) 1 and AIS 2. Two different types of low speed crash tests such as the frontal barrier and rear moving barrier crashes have been conducted by following the procedure of the Research Committee for Automobile Repairs (RCAR). The injury for the neck and the Head Injury Criteria (HIC) were measured by using the sensors mounted on dummies. We reviewed neck injures and the relationship between the neck and head injuries, and examined the deceleration of the body. Using the experimental test data at the neck, we investigated an improved neck injury criterion Nij. Also, the effects of the position of a head restraint on reducing the frequency and severity of the neck injury in rear-end collisions were investigated.

• Journal of the Society of Naval Architects of Korea
• /
• v.45 no.5
• /
• pp.554-561
• /
• 2008

This paper deals with an intelligent digital ship which aims at development to support economic and safe services through an integration into the hierarchically layered digital signals such as ship's navigation, maneuvering and control signal and establishing a one-man bridge system in order to provide a support systems between ship and land station. This paper introduces the results of the mid-term project sponsored from Ministry of Commerce, Industry and Energy which consists of three sub-project such as INS(Intelligent Navigation System), AIS(Automatic Identification System), and IMIT (Integrated Maritime Information Technology). The INS system that can allow ships to navigate economically and safely through the integration and analysis of national data within the ship. AIS is a system that reports automatically on the location of the ship in order to prevent the collision between ships and between the ship and the land. IMIT is a integrated system for providing an efficient and economic support system between ships and the land and a ship-land platform and technologies.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.57 no.4
• /
• pp.479-488
• /
• 2024

In recent years, changes in the fishing ground environment have led to reduced catches by fishermen at traditional fishing spots and increased operational costs related to vessel exploration, fuel, and labor. In this study, we developed a deep learning model to classify the fishing activities of drift gillnet fishing boats using AIS (automatic identification system) trajectory data. The proposed model integrates long short-term memory and 1-dimensional convolutional neural network layers to effectively distinguish between fishing (throwing and hauling) and non-fishing operations. Training on a dataset derived from AIS and validation against a subset of CCTV footage, the model achieved high accuracy, with a classification accuracy of 90% for fishing events. These results show that the model can be used effectively to monitor and manage fishing activities in coastal waters in real time.

• Economic and Environmental Geology
• /
• v.53 no.2
• /
• pp.147-157
• /
• 2020

Mass change in the Antarctic Ice Sheet(AIS) is the most important indicator of changes in Earth's climate system including global mean sea level rise that are largely affected by ongoing global warming. In this study, AIS mass variations are examined with satellite gravity data and outputs from a regional climate model. The analysis of gravity data shows that along the coastal region the Western AIS has experienced a continuous and significant ice loss while a slight increasing in the Eastern AIS during the study period (2002.08-2016.08). The temporal and spatial variations in ice mass changes are recovered by a regional climate model, but the recovered amplitudes are much smaller than those of observations. This under-estimation is remarkably resolved by modifying a base flow field for the ice discharge. The recovered estimates based on the ice-flow field can explain about 97% of the rate of mass change in observations before 2009. This implies that changes in ice flow dynamics along the coast line plays a pivotal role in regulating long-term budget of ice mass in AIS.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.3
• /
• pp.146-154
• /
• 2023

Efforts have been made to reduce the greenhouse gas emissions from ships by limiting the energy efficiency index, and net zero CO₂ emission was proposed recently. The most ideal measure to achieve zero emission ship is electrification, and fuel cells are considered as a practical power source of the electrified propulsion system. The electric efficiency in the electrochemical reaction of fuel cells can be achieved up to 60% practically. The remaining energy is converted to heat energy but most of them are dissipated by cooling. In the author's previous research, a hybrid propulsion system utilizing not only electricity but also heat was introduced by combining electric motor and steam turbine. In this article, long term efficiency is evaluated for the introduced hybrid propulsion system by considering a virtual 24,000 TEU class container carrier model. To reflect a more practical operating condition, the actual navigation data of a similar real ship in the real world were collected from automatic identification system data and applied. From the result, the overall efficiency of the hybrid propulsion system is expected to be higher than a conventional electric propulsion fuel cell ship by 30%.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.08a
• /
• pp.208-216
• /
• 2004

Since 2000, the authors have been developing remote radar network system to observe the vessel traffic in Tokyo Bay. In December 2002, the first operational remote radar station was set at the National Defense Academy in Yokosuka, and vessel traffic observation was started. However, it was impossible to perform accurate observation in the northern part of Tokyo Bay by this Yokosuka radar station only. In September 2003, the second remote radar station and AIS receiving station were installed at Higashi Ogishima in Kawasaki. This second radar enabled us to carry out accurate observation in that area. Both radars can be remotely controlled from the monitoring station in Tokyo University of Marine Science and Technology. On September 30 and October 1,2003, the vessel traffic observation was carried out using both radars. Combining radar images observed by both radars, the ships' tracks were taken and the dangerous ships were extracted by using SJ value and Bumper Model. The time changes of dangerous ship density in some areas in Tokyo Bay and utilization ratio of the traffic routes were also investigated. In addition, analyzing the AIS date received at Kawasaki station, the positions and speed vectors of the ships equipped with AIS were shown.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.190-197
• /
• 2020

Recently there was an incident that military radars, coastal CCTVs and other surveillance equipment captured a small rubber boat smuggling a group of illegal immigrants into South Korea, but guards on duty failed to notice it until after they reached the shore and fled. After that, the detection of such vessels before it reach to the Korean shore has emerged as an important issue to be solved. In the fields of marine navigation, Automatic Identification System (AIS) is widely equipped in vessels, and the vessels incessantly transmits its position information. In this paper, we propose a method of automatically identifying abnormally behaving vessels with AIS using convolutional autoencoder (CAE). Vessel anomaly detection can be referred to as the process of detecting its trajectory that significantly deviated from the majority of the trajectories. In this method, the normal vessel trajectory is gridded as an image, and CAE are trained with images from historical normal vessel trajectories to reconstruct the input image. Features of normal trajectories are captured into weights in CAE. As a result, images of the trajectories of abnormal behaving vessels are poorly reconstructed and end up with large reconstruction errors. We show how correctly the model detects simulated abnormal trajectories shifted a few pixel from normal trajectories. Since the proposed model identifies abnormally behaving ships using actual AIS data, it is expected to contribute to the strengthening of security level when it is applied to various maritime surveillance systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.635-638
• /
• 2009

ENC Optimizer S/W was developed for light weight, ENC speed improvement, nested data, and optimization of the data module. ENC optimizer customize based on Korea Ocean's ENC data by Investigators of the National Marine.Based on the modification of K-Map ENC through enhancemen to fENC Web OCX module and ENC Optimizier, AIS service by WebWM Shad been developed. WebVMS make it possible to view the ship information anywherevia WebBrowser. Later, through the expansion of the surveillance ship WebVMS the past, information about access, satellite communications, tracking and monitoring are currently used invarious applications such as shipping informationis available.