• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2020.11a
• /
• pp.182-184
• /
• 2020

복잡 다양한 해상교통 환경 재현을 목적으로 에이전트 모델 기반의 시뮬레이션 개발 연구가 진행 중이며, 에이전트 모델 기반 시뮬레이션 연구는 과거 해상 교통 데이터를 이용한 제한적인 분석이 아니라, 에이전트 모델 간 상호 연동을 통해 해상교통환경을 재현할 수 있다. 본 연구에서는 디지털 트윈 분야에서 적용하고 있는 기능 목업 인터페이스(FMI) 기반으로 연동기술 프로토타입을 개발 하였다. 에이전트 모델 간 연동을 위해 FMU를 제작하고, 오픈 소스 기반의 DACCOSIM을 적용하여 FMU 간 연동 및 시뮬레이션이 가능한 기술을 확보하였다. 교통특성, 선박항해, 항해사, 관제사, 연동, 수로환경으로 구성되는 해상교통 에이전트 간 정보 연계 및 결과 표현에 관한 프로토타입 개발 연구를 수행 하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.05a
• /
• pp.1-2
• /
• 2019

일반적인 해상교통 분석 방법은 대상 항만의 항적 데이터를 기반으로 데이터를 추출한 후 모델을 구축하며, 구축된 모델을 바탕으로 해상교통 현상을 재현하고 있지만, 이러한 방법은 항로 혹은 통항량 변동 등의 변화에 따른 교통류를 예측할 수 없어 그 활용에 제약이 많다. 본 논문에서는 기존의 해상교통 분석 사례를 통해 교통 특성 모델의 요소를 식별하고, 이를 동적인 해상교통 환경을 시뮬레이션 할 수 있는 에이전트 기반의 교통류 생성 기술 개발의 기초 자료로 활용하고자 한다.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.4
• /
• pp.109-118
• /
• 2022

The data of the missing section among the vertex surface sea temperature observation data was imputed using the Bidirectional Recurrent Neural Network(BiRNN). Among artificial intelligence techniques, Recurrent Neural Networks (RNNs), which are commonly used for time series data, only estimate in the direction of time flow or in the reverse direction to the missing estimation position, so the estimation performance is poor in the long-term missing section. On the other hand, in this study, estimation performance can be improved even for long-term missing data by estimating in both directions before and after the missing section. Also, by using all available data around the observation point (sea surface temperature, temperature, wind field, atmospheric pressure, humidity), the imputation performance was further improved by estimating the imputation data from these correlations together. For performance verification, a statistical model, Multivariate Imputation by Chained Equations (MICE), a machine learning-based Random Forest model, and an RNN model using Long Short-Term Memory (LSTM) were compared. For imputation of long-term missing for 7 days, the average accuracy of the BiRNN/statistical models is 70.8%/61.2%, respectively, and the average error is 0.28 degrees/0.44 degrees, respectively, so the BiRNN model performs better than other models. By applying a temporal decay factor representing the missing pattern, it is judged that the BiRNN technique has better imputation performance than the existing method as the missing section becomes longer.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.769-775
• /
• 2017

The International Maritime Organization's e-Navigation strategy is to introduce new technologies to ships to support easier and safer navigation. With the e-Navigation strategy, various equipment will be installed in vessels and the system structure will be linked to onshore systems. For this reason, a common data structure between systems became necessary, and finally the S-100 standard developed by the International Hydrographic Organization was selected. This paper describes a design of marine casualty data model based on the S-100 standard. The data model of the S-100 standard is designed in the form of a UML class diagram, and the final encoding follows the GML / XML format. We will look at the S-100 standard and product specifications under development, and describe the S-100 standards-based data design and portrayal definition of marine accident data.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.505-511
• /
• 2023

In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.5
• /
• pp.527-536
• /
• 2018

In this paper, we developed a prototype model accident management SMART-Navigation project. In order to develop a prototype model, we analyzed the status of maritime data exchange standard and procedure. We developed accident management prototype application schema, feature catalog and portrayal catalog in accordance with S-100 standard data model development procedure by collecting requirements related services and referring to related standards. In order to verify accident management prototype model, we test data set based on Gwang-yang Port. The prototype model and test data verified verification software, and it was confirmed that the designated symbol was displayed at the correct position through the S-100 simple viewer.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.11a
• /
• pp.252-252
• /
• 2017

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.571-580
• /
• 2022

Marine deposited waste is a major cause of problems such as a lot of damage and an increase in the estimated amount of garbage due to abandoned fishing grounds caused by ghost fishing. In this paper, we implement a real-time marine deposited waste detection artificial intelligence system to understand the actual conditions of waste fishing gear usage, distribution, loss, and recovery, and study methods for performance improvement. The system was implemented using the yolov5 model, which is an excellent performance model for real-time object detection, and the 'data screening process' and 'class segmentation' method of learning data were applied as performance improvement methods. In conclusion, the object detection results of datasets that do screen unnecessary data or do not subdivide similar items according to characteristics and uses are better than the object recognition results of unscreened datasets and datasets in which classes are subdivided.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.4-4
• /
• 2022

낙동강 하구 환경/생태 복원을 위하여 "해수유입"으로 하구환경을 조성하는 사업이 추진되고 있으며, 해수 유입 규모와 빈도에 따른 생태환경변화를 예측하는 연구수요가 증가하고 있는 상황이다. 보다 구체적으로는 단기간의 해수유입에 의한 흐름 및 염분 확산범위 예측과 더불어 보다 장기간의 지형변화, 수질환경 변화, 생태환경 변화 등에 대한 예측이 필요한 상황이다. 그리고 그 예측의 대부분을 수치모델에 크게 의존하고 있는 상황이다. 그러나, 수치모형을 이용한 단기 예측은 가까운 미래에 대한 입력조건을 사용하여야 하기 때문에 입력조건에 대한 불확실성이 포함되고, 환경생태모형의 불확실성에 따른 예측 한계 등으로 인하여 오차가 누적되기 때문에 직접적인 활용에 크게 제한이 따를 수 있다. 또한 운영과정에서 어떤 분산, 편향 오차 등이 지속적으로 발생하는 경우, 모델 예측 결과에 대한 신뢰수준이 크게 감소하기 때문에 모델의 적절한 운영기법이 요구된다. 모델은 관심을 가지는 자연현상에 대한 근사(approximation)이고, 예상하지 못한 오차가 발생할 수 있기 때문에 관측 자료를 이용한 자료동화(data assimilation) 과정이 운영모델에서는 필수적인 부분이다. 이론적인 기반이 탄탄한 유체역학 기반 기상예측의 경우에도, 가용한 모든 지점의 관측 자료를 이용한 자료 동화과정을 통하여 모델 예측 결과를 개선하여 나가는 과정을 포함하여 운영하고 있다. 이 과정이 포함하는 중요한 개념은 수치모델이 가지고 있는 (예측 수준의) 한계를 인정하고, 수치모델에 전적으로 의존하는 것이 아니라 관측 자료를 이용하여 그 한계를 저감하여 나가는 과정이다. 모니터링은 모델의 한계를 알려주는 지표이다. 모델링과 모니터링의 불가피한 상호의존 관계를 의미하는 이 개념은 단기간의 흐름, 염분 확산 예측으로 한정되지 않고, 장기적인 변화가 예상되는 생태환경변화 모델에도 적용이 된다. 즉각적인 변화보다는 장기적인 관점에서 파악하여야 하는 생태학적인 변화는 보다 다양한 인자가 관여하기 때문에 어떤 측면에서는 모델보다는 적절한 빈도와 항목에 대한 관측계획 수립(monitoring design)이 더 중요하다고 할 수 있다. 이론적인 질량보존(mass conservation) 방정식을 기반으로 하는 모델은 다양한 현실적인 인자의 영향을 받기 때문에 모델의 한계를 인정하고, 모니터링 자료를 적극적으로 활용하여 불확실성을 저감하는 접근방식이 요구된다.