In order support the design support system of small and medium-sized shipbuilding companies that carry out designs using 2D CAD, this study developed a system that automatically calculates the cable length by extracting the Y-axis value expressed as text data in 2D CAD. By setting the equipment where the cable starts and ends, the essential route and the installation rate were checked so that the optimal route of the cable could be calculated. As a result, the value calculated based on the optimal route and length of the cable by extracting the data of 2D CAD through this study was the same as the value previously calculated by the actual user, and the installation rate was less than 130% so there was no problem with the on-site installation. In addition, it was confirmed that the cable length calculated through this was reduced by about 7% compared to the existing work.

빠르게 발전하는 이미지 인식 기술에도 불구하고 표 형식의 문서와 수기로 작성된 문서를 완벽하게 디지털화하기에는 아직 어려움이 따른다. 본 연구는 표 형식의 수기 문서인 선박 항해일지를 작성하는 데에 사용되는 규칙을 이용하여 보정 작업을 수행함으로 써 OCR 결과물의 정확도를 향상시키고자 한다. 이를 통해 OCR 프로그램을 통하여 추출된 항해일지 데이터의 정확성과 신뢰성을 높일 것 으로 기대된다. 본 연구는 목포해양대학교 실습선 새누리호의 2023년에 항해한 57일간의 항해일지 데이터를 대상으로 OCR 프로그램 인 식 후 발생한 오류를 보정하여 그 정확도를 개선하고자 하였다. 이 모델은 항해일지 기재 시 고려되는 몇 가지 규칙을 활용하여 오류를 식별한 후, 식별된 오류를 보정하는 방식으로 구성하였다. 모델을 활용하여 오류를 보정 후, 그 효과를 평가하고자 보정 전과 후의 데이터 를 항차별로 구분한 후, 같은 항차의 같은 변수끼리 비교하였다. 본 모델을 활용하여 실제 셀 오류율은 약 11.8% 중 약 10.6%의 오류를 식 별하였고, 123개의 오류 중 56개를 개선하였다. 본 연구는 항해일지 중 항해정보를 기입하는 Dist.Run부터 Stand Course까지의 정보만을 대 상으로 수행하였다는 한계점이 있으므로, 추후 항해정보 뿐만 아니라 기상정보 등 항해일지의 더 많은 정보를 보정하기 위한 연구를 진 행할 예정이다.

In order to optimising the sea traffic network efficiency, improving the safety of shipping and the protection of the environment, it is useful to model the sea network and its spatio-temporal characteristics of the ship patterns. These maritime patterns could also be an a-priori set of knowledge for the upcoming Maritime Autonomous Surface Ships (MASS) which are starting to navigate our seas with or without remote human controls. The above concepts are crucial and essential elements for defining and understanding the Maritime Situational Awareness (MSA). Nowadays the applied methodologies for modelling the maritime traffic use large scale of database for extracting the patterns. The Knowledge Discovery from Data (KDD), strictly connected with Data Mining (DM) is growing significantly to modelling the behaviour of the vessels in relations to their surroundings. This is just one example that confirms the growing up of the cloud computing usage for maritime applications too. Besides these applications there are also a continuous and fast evolution of the IT services, which more often than not means data centre scale-ups with consequent improve of power consumptions. This paper is a case study based on real world data assessing a multi-objective energy consumption analysis. It is based on the comparison between the traditional air conditioning structures known as Heating, Ventilation and Air Conditioning (HVAC) and the Free Cooling Technique (FCT) in order to reduce the data centre power consumption keeping the same number of computational calculations performed.

Due to the high risk of personal injury and property damage, the safety of maritime transport is an important concern for everyone involved. Ship navigation officers usually look up a ship's collision profile for safety-at-sea information before entering an unknown coastal area. Near-ship collisions are very important when assessing the potential risk of shipping. This paper undertakes a ship encounter risk assessment, involving analyses of the trajectory data of merchant ships and then extracts ship encounter data, creates a probabilistic model to determine whether an encounter event is a near miss, and suggests risk indicators. The proposed method will be useful for navigators to plan safe passages.

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.