• Journal of Navigation and Port Research
• /
• v.34 no.5
• /
• pp.397-404
• /
• 2010

The Currently, most cargos of container transshipment between Busan Port and New Port are transported over land, and the rest is transported by barge. This study estimated firstly the traffic between those ports through simulations in order to analyze the feasibility of container transshipment by barge. It forecasted annual profitability using determinants to affect on the barge business by the traffic, and then, discussed the feasibility. This study supposed the flexible scenarios with 50%, 60%, 80%, or 100% transshipment and the 25 monthly barge service numbers between two ports, and measured the influences of different factors according to the above various scenarios. And then the sales were evaluated by the different traffics and freights scenarios provided the business would be actually operated. Finally, Net incomes were simulated to analyze the feasibility of different scenarios by various traffics and freights. The net income should be positive to get the feasibility. To achieve this, the minimum traffic should be secured and the lowest freight per TEU should be determined. While all countries of the world is controlling CO2 emissions and emphasizes the green logistics, this study contributed to solve at the same time the problems about the pollution and the efficiency of transportation by reviewing positively the feasibility of barge transportation as an alternative to transportation overland.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.377-379
• /
• 2022

선교 상황 인식 시스템을 개발하기 위한 합성곱 신경망 기반의 인공지능카메라를 개발한다. 부이 등의 항로표지를 포함한 컨테이너선, 유조선, 자동차 운반선 등 선박 종류 구분이 가능하도록 YOLO5를 이용하여 학습을 수행하고 그 결과를 보인다.

• The Science & Technology
• /
• no.3 s.406
• /
• pp.10-11
• /
• 2003

• Bulletin of the Society of Naval Architects of Korea
• /
• v.44 no.3
• /
• pp.23-28
• /
• 2007

• Bulletin of the Society of Naval Architects of Korea
• /
• v.54 no.1
• /
• pp.34-39
• /
• 2017

• Bulletin of the Society of Naval Architects of Korea
• /
• v.28 no.2
• /
• pp.80-82
• /
• 1991

• Bulletin of the Society of Naval Architects of Korea
• /
• v.51 no.3
• /
• pp.49-59
• /
• 2014

• Bulletin of the Society of Naval Architects of Korea
• /
• v.31 no.1
• /
• pp.49-50
• /
• 1994

• Bulletin of the Society of Naval Architects of Korea
• /
• v.60 no.6
• /
• pp.13-15
• /
• 2023

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.65-79
• /
• 2003

In general, the extraction and recognition of identifier is very hard work, because the scale or location of identifier is not fixed-form. And, because the provided image is contained by camera, it has some noises. In this paper, we propose methods for automatic detecting edge using canny edge mask. After detecting edges, we extract regions of identifier by detected edge information's. In regions of identifier, we extract each identifier using contour tracking algorithm. The self-generation supervised learning algorithm is proposed for recognizing them, which has the algorithm of combining the enhanced ART1 and the supervised teaming method. The proposed method has applied to the container images. The extraction rate of identifier obtained by using contour tracking algorithm showed better results than that from the histogram method. Furthermore, the recognition rate of the self-generation supervised teaming method based on enhanced ART1 was improved much more than that of the self-generation supervised learning method based conventional ART1.