• Proceedings of KOSOMES biannual meeting
• /
• 2017.11a
• /
• pp.124-124
• /
• 2017

• Proceedings of KOSOMES biannual meeting
• /
• 2017.04a
• /
• pp.121-121
• /
• 2017

• Journal of the Korean Society of Safety
• /
• v.38 no.5
• /
• pp.51-57
• /
• 2023

Numerous studies have been conducted to analyze the causal relationships of maritime accidents using natural language processing techniques. However, when multiple causes and effects are associated with a single accident, the effectiveness of extracting these causal relations diminishes. To address this challenge, we compiled a dataset using verdicts from maritime accident cases in this study, analyzed their causal relations, and applied labeling considering the association information of various causes and effects. In addition, to validate the efficacy of our proposed methodology, we fine-tuned the KoELECTRA Korean language model. The results of our validation process demonstrated the ability of our approach to successfully extract multiple causal relationships from maritime accident cases.

• Journal of Navigation and Port Research
• /
• v.46 no.2
• /
• pp.92-98
• /
• 2022

Maritime accidents result in enormous economic loss and loss of life; thus, such accidents must be prevented, and risks must be managed to prevent these occurrences Risk management must be based on statistical evidence such as variables. Because calculating when variables increase statistically can be difficult, compressing the designated variables is necessary to use the maritime accident data in Korea. Thus, in this study, variables of marine accident data are compressed using statistical methods. The date, ship type, and marine accident type included in all maritime accident data were extracted, the number of optimal variables was confirmed using the hierarchical clustering analysis method, and the data were compressed. For the compressed variables, the validity of the data use was statistically confirmed using analysis of variance, and the data of the variables identified using the variable compression method were designated. Consequently, among the monthly and yearly data, statistical significance was confirmed in yearly data, and compression was possible. The significance of the data was confirmed in six and eight types of ships and accidents, respectively, and these were compressed. These results can be directly used for prevention or prediction based on past maritime accident data. Additionally, the data range extracted from past maritime accidents and the number of applicable data will be studied in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.207-215
• /
• 2023

The ship system is complex and advanced, and the operation relationship between each element is very high. So it is necessary to approach it in terms of an overall and integrated system in addition to the traditional sequential approach of finding and removing the direct cause of the accident when analyzing the accident. In this study, it is analyzed the recent fire accidents on ships occurred the Korean terrestrial water using a STAMP methodology that is different from conventional accident analysis techniques. This analysis reviews a range of factors, including safety requirements to prevent fires in ships, inappropriate decisions and actions, situations, equipment defects, and recommendations derived from accident analysis results. Through a comprehensive approach to accident prevention using STAMP, alternative evaluations are presented at the component level within the entire system of ships, and they are systematically used for accident prevention and risk evaluation as well as simple accident analysis.

• Journal of Navigation and Port Research
• /
• v.38 no.3
• /
• pp.247-252
• /
• 2014

Despite the facts that navigation technology and educational programs were developed, and that maritime law has been enforced strictly, the number of maritime accidents has not dropped significantly. Accident prevention is emphasized because of the extreme life, property, and environmental losses that accompany maritime accidents. Even though there are a variety of preventive activities, their performance is not satisfactory. In order to promote preventive activities and to organize safety management, a Preventive Index of Ship Accident(PISA) and a Preventive Level of Ship Accident(PLSA) which are abstracted from the statistical data of ship accidents (2009~2013) are proposed. The survey module by which these variables can be calculated is composed of preventive domains such as education, engineering, enforcement and information, and is applied for the preventive indexes measurement of cargo, passenger, tanker, tugboat and fishery ships. We compared and analyzed measured result with statistical accident rates and cases to confirm the index utilities. It was found that there is some correlation between the index value and the ship accident rate. It is expected that this index will become useful to evaluate a preventive status for the prevention of ship accidents and for the maritime safety culture.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.863-869
• /
• 2018

Due to recent changes in the maritime traffic environment, naval warship accidents are constantly occurring. Especially in 2017, serious loss of life was caused by a US navy destroyer accident. The purpose of this study is to analyze the characteristics of naval warship accident cases and construct an accident scenario by using naval training materials, adjudication of naval warship accidents and US navy destroyer accident reports. Based on the surveyed data, the status of accidents was identified and cases were analyzed. We reproduced 17 accident cases in accordance with accident reproduction procedure and constructed naval warship accident scenarios. As a result of analyzing the CPA, TCPA and PARK model for risk, reproducing 17 naval ship accident cases, collision risk increased on average 5-6 minutes before an accident. The result of this study represents basic data for naval and simulation education materials, contributing to the prevention of marine accidents.

• Journal of Navigation and Port Research
• /
• v.36 no.9
• /
• pp.715-720
• /
• 2012

This paper is to introduce the development of a LCD monitor-based pilots' ship handling simulator installed in the office of Korea Maritime Pilots Association. This simulator is composed of hardware which includes working server array, operation PC, monitor array, rudder, thruster and telegraph peripheral devices, and software which includes ship mathematical model software, ship conning software, image supporting software and so on. In this simulator, MMG mathematical model is used to create thirteen(13) ship models, which are based on sea trial data & pilots' opinion. According to requirements of pilots, virtual scenes of different port areas are built, and some required additional functions are also developed. By using this simulator, pilots can fulfill all kinds of training exercises, design of channel approaching ports, traffic safety analysis, prevention of accident research and other tasks, so as to grasp the characteristics of different ships, and accumulate experience for piloting.

• Journal of Navigation and Port Research
• /
• v.28 no.2
• /
• pp.113-119
• /
• 2004

Ships' collision accident has often occurred in congested waterways or in harbour areas. To examine the cause of collision accident may be necessary to prevention against another similar one. We discuss the construction of ship-manoeuvring-simulator system used for reproducing ships' collision phenomenon The system consists of one simulator bridge for own ship and two control consoles for own ship and target ship. Own ship and target ship are linked each other, and are simultaneously manoeuvred in simulator bridge or at control console respectively. And a simulator experiment for reproducing ships' collision phenomenon and for examining the cause of accident is carried out. Through the present case study, we find out that the constructed simulator system is very useful for reproducing ships' collision phenomenon and for examining the cause of accident.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.315-323
• /
• 2013

Vessel Traffic Service (VTS) is being used at ports and in coastal areas of the world for preventing accidents and improving efficiency of the vessels at sea on the basis of "IMO RESOLUTION A.857 (20) on Guidelines for Vessel Traffic Services". Currently, VTS plays an important role in the prevention of maritime accidents, as ships are required to participate in the system. Ships are diversified and traffic situations in ports and coastal areas have become more complicated than before. The role of VTS operator (VTSO) has been enlarged because of these reasons, and VTSO is required to be clearly aware of maritime situations and take decisions in emergency situations. In this paper, we propose a prediction table to improve the work of VTSO through the Cognitive Work Analysis (CWA), which analyzes the VTS work very systematically. The required data were collected through interviews and observations of 14 VTSOs. The prediction tool supports decision-making in terms of a proactive measure for the prevention of maritime accidents.