• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2013년도 춘계학술대회
• /
• pp.169-171
• /
• 2013

The ships always have had the risk of collision. There are also a number of near-miss situations especially in the congested area such as port entrance, restricted waters and crossing point of the ship's route. In those areas, the navigator might have more stress than other areas. If the collision risk of decided area is calculated, it might be possible to analyse the human factors by using this data. It is also helpful for deciding a position of aids to navigation or any other system for the safety navigation. For this purpose, the model of collision risk with AIS data has been explained in this paper. The calculated result from the proposed model has been examined by using the simulation.

• 대한조선학회논문집
• /
• 제54권4호
• /
• pp.275-285
• /
• 2017

In order to predict the sailing performance of a LNGC during actual operation, it is necessary to consider not only the information about resistance, maneuverability etc. but also the information such as sea route and sailing scenario etc., comprehensively. In this paper, we propose a new approach to conduct the sailing simulation of a LNGC without full scale measurement data. Latitude, longitude, sea route, speed over ground, time in UTC obtained from AIS data are substituted for the measured data. By combining the model test results, design information, and AIS data, prediction of sailing performance is conducted from the coast of southern Taiwan to the coast of Madagascar. The simulation is verified by comparing the calculated time histories of RPM and power with those of measured RPM and power.

• Asia pacific journal of information systems
• /
• 제5권2호
• /
• pp.79-100
• /
• 1995

Internal Control(IC) comprises the plan of organization and all of the coordinating methods and measures adopted in a business to safeguard its assets, check the accuracy and reliability of its accounting data, promote operational efficiency and encourage adherence to the prescribed managerial policies. If an organization's IC is not adequate, Accounting Information System (AIS) will be vulnerable to accomplish the organizations successes. Therefore, an effective and efficient IC is essential to its successes. The purpose of this study is to analyze the impact of EDP IC on the perceived usefulness of AIS. Do the general controls indirectively affect to the usefulness of AIS through th application controls? To solve these problems, a research model and a set of hypotheses were established and empirically tested. 60 financial institutions (banks, insurance companies, security companies) agreed to participate in the study. Data were gathered through structured interviews with 60 information systems managers and 537 users of accounting information of each company. Survey forms were designed and collected from financial institutions in Seoul. Information systems' managers of financial institutions responded to questionnaire(1) which consists of a series of 70 questions related to practice and perceived importance. Questionnaire (2) was received from 537 users, who responded to series of 17 questions related to the perceived usefulness. The results of analysis are summarized below. Effects of general controls are more direct on AIS's usefulness than those of application controls. Whereas, indirect effects of application controls are geater than those of general controls. Therefore, the greater the effects of application controls on general controls, the higher the perceived usefulness of AIS. In conclusion, this study supports that the perceived usefulness of AIS is affected by IC which are composed of general controls and application controls. The results of this study has significant implication to financial institution as computer fraud potential increases. Because of global competitions, financial institutions should restructure to IC and AIS in order to take advantage of the technological progress in Information System.

• 한국항해항만학회지
• /
• 제42권4호
• /
• pp.277-282
• /
• 2018

최근 해상교통량이 증가하고 선박교통 관제구역이 확대됨에 따라 관제사의 업무 부하가 증가하고 있으며, 이로 인해 교통량이 급증하는 경우 관제사가 위험을 인지하지 못하는 상황도 발생하게 된다. 이러한 배경에서 본 논문에서는 관제 업무의 지원을 위해 이상 거동 선박을 자동으로 식별하는 방법을 제안한다. 본 방법은 누적된 AIS 데이터를 이용하여 관제구역 내의 통항 패턴을 학습하고, 학습된 모델과의 비교를 통해 이상치를 계산하여 이상 거동 선박을 식별한다. 특히, 선박의 거동 상태에 대한 분류 정보가 없더라도 비지도 학습법을 기반으로 항적 데이터를 자동으로 분류하여 통항 패턴을 학습할 수 있으며, 항적의 군집화와 분류 과정을 통해 이상 거동 선박을 실시간으로 식별할 수 있는 특징을 가진다. 또한, 본 논문에서는 선박운항 시뮬레이터 및 실제 AIS 항적 데이터를 이용한 식별 실험을 수행하였으며, 이를 통해 선박교통관제 시스템에의 활용 가능성을 고찰하였다.

• 한국지능시스템학회논문지
• /
• 제21권2호
• /
• pp.198-205
• /
• 2011

선박의 항해사가 안전 항해를 위해 GPS, ARPA, AIS, NAVTEX, VHF 등 다수의 항해장비가 제공하는 화상, 수치, 텍스트 및 음성 정보를 숙지하여야 하나, 항해당직에 임하면서 동시에 이들 정보를 획득하여 안전 항해를 위한 판단자료로 활용하는 것은 대단히 번거롭고 어려운 작업이다. 따라서 이들 멀티미디어 항해안전정보를 이해하고 융합하여 항해사가 처한 상황을 인식하고 항해사의 의사결정에 필요한 정보를 추론하여 언어로서 제공해주는 시스템이 필요하다. 본 연구에서는 멀티미디어 항해안전정보를 이해하고 융합하여 언어로 제공하는데 필요한 의미해석 모델을 Semantic Network를 이용하여 구축하고자 한다.

• 해양환경안전학회지
• /
• 제20권3호
• /
• pp.285-291
• /
• 2014

This study applied regression analysis to evaluate the impact of hourly average congestion calculated by bumper model in the congested area of each passage of each port on the peak time congestion, to suggest the model formula that can predict the peak time congestion. This study conducted regression analysis of hourly average congestion and peak time congestion based on the AIS survey study of 20 ports in Korea. As a result of analysis, it was found that the hourly average congestion has a significant impact on the peak time congestion and the prediction model formula was derived. This formula($C_p=4.457C_a+29.202$) can be used to calculate the peak time congestion based on the predicted hourly average congestion.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1463-1478
• /
• 2022

한국 수출입의 99.7%는 해상운송이 차지하고 있으며, 항만의 효율적 운영을 위해 해운 물류 모니터링 시스템 개발 필요성이 대두되고 있다. 현재 automatic identification system (AIS)를 기반으로 선박의 정보를 조회하여 해상 물동량 추정 연구가 진행되고 있지만, AIS를 운영하지 않는 선박들에 대한 모니터링은 불가능하다는 한계가 있다. 고해상도 광학 위성 영상은 광역의 범위에서 AIS 미운영 선박 및 소형 선박을 식별할 수 있기 때문에 AIS 기반 물동량 모니터링의 공백을 보완할 수 있다. 그러므로 선박 및 물동량 모니터링에 활용하기 위해, 고해상도 광학 위성영상에서 선박을 탐지하고 화물선 및 소형 선박을 분류하는 연구가 필요하다. 본 연구는 초기 국토위성영상을 이용하여 생산된 학습 자료 기반으로 인공지능 모델을 훈련시키고 다른 영상에서 탐지를 수행함으로써, 국토위성영상의 딥러닝 학습 자료 생산 및 선박 모니터링 활용 가능성을 알아보고자 하였다. 학습 자료는 황해 및 황해 주요 항만 구역 내 선박들을 추출하여 제작했으며, You Only Look Once (YOLO) 알고리즘을 사용하여 탐지 모델은 구축하고 국내외 주요 항만 각 1개소를 대상으로 선박 탐지 성능을 평가하였다. 항만 접안 및 해상 정박중인 선박을 대상으로 탐지 모델에 적용한 결과를 AIS의 선종 정보와 비교하였고, 국내 항만에서 85.5%와 89%, 국외 항만에서 70%의 선종 분류 정확도를 확인하였다. 본 연구 결과는 정박중인 선박을 중심으로 고해상도 국토위성영상을 활용하여 모니터링이 가능함을 확인하였다. 향후 지속적인 학습 자료 구축을 통해 탐지 모델의 정확도를 향상시킨다면 전세계 주요 항만에서 선박 및 물동량 모니터링 분야에 활용할 수 있을 것으로 기대된다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2016년도 춘계학술대회
• /
• pp.67-68
• /
• 2016

해상교통환경평가는 선박 간 항행상황의 위험도를 정량화하여 나타냄으로써 선박의 안전운항을 효과적으로 지원하는 역할을 한다. 대표적인 해상교통환경평가모델로는 ES(Environmental Stress model)와 CR(Collision Risk)모델이 있다. 이러한 모델을 살펴보면, 각각의 평가지수를 이용하여 항행상황의 위험도를 정량화하며, 선박 간 조우관계를 기반으로 평가요소를 구성함을 알 수 있다. 이번 연구에서는 선박 간 조우관계를 포함한 항행상황의 위험도에 영향을 줄 것으로 기대되는 다양한 요소를 고려한 평가지수의 타당성을 살펴보고자 한다. 이를 위하여, AIS data를 이용하여 해상교통환경을 재현하고 분석하였으며, 동일한 항행상황을 ES, CR과 제안한 모델을 이용하여 위험도 평가를 실시하였다. 그 결과를 비교하여 제시함으로써 본 모델이 해상교통환경모델로서 항만 내 통항 안전성 평가에 적용 가능성을 평가하였다.

• 산업경영시스템학회지
• /
• 제43권4호
• /
• 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.

• Korean Journal of Radiology
• /
• 제23권8호
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.