• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2020.11a
• /
• pp.108-110
• /
• 2020

본 연구의 목적은 딥러닝 기법의 하나인 인공신경망 모델을 활용하여 선박의 가치평가 모델을 개발하는 것이다. 선박의 가치는 해운시장 변화와 밀접한 관계가 있으며, 경기 변동성이 크고 시장 민감성이 높은 해운시장의 특성상 가치의 불확실성 역시 높게 나타나고 있다. 이러한 선박가치의 중요성에도 불구하고 국내외적으로 선박가치평가의 체계 개선 및 평가모델의 객관성과 신뢰성을 제고시키기 위한 연구는 부족한 실정이다. 따라서 본 연구에서는 딥러닝 방법을 통해 선박의 가치를 산출하는 새로운 평가모델을 제시하고자 한다. 가치평가의 대상은 중고 VLCC선이며, 선행연구를 통해 선박의 가치 변화를 유발하는 주요 요인들을 선별하여 변수를 설정하고 2010년 1월부터 현재까지의 해당 데이터를 확보하였다. 교차검증을 통해 파라미터들을 추정하여 인공신경망의 최적 구조를 식별하고 이에 대한 객관성과 신뢰성을 검증한 결과 인공신경망 모델의 가치평가 정확성이 우수함을 확인하였다. 본 연구는 선박가치평가의 전통적 방법론에서 탈피하여 기계학습 기반의 딥러닝 모델을 활용한 측면에서 독창적인 의미가 있다.

• Journal of Korea Port Economic Association
• /
• v.31 no.3
• /
• pp.1-14
• /
• 2015

This study utilizes Monte Carlo simulation to forecast the time charter rate of vessels, the three-month Libor interest rate, and the ship demolition price, to mitigate future uncertainties involving these factors. The simulation was performed 10,000 times to obtain an exact result. For the empirical analysis - based on considerations in ordering ships in 2010-a comparison between the Monte Carlo simulation-based stochastic discounted cash flow (DCF) method and traditional DCF methods was made. The analysis revealed that the net present value obtained through Monte Carlo simulation was lower than that obtained via regular DCF methods, alerting the owners to risks and preventing them from placing injudicious orders for ships. This research has implications in reducing the uncertainties that future shipping markets face, through the use of a stochastic DCF approach with relevant variables and probability methods.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.13-21
• /
• 2021

The purpose of this study is to develop the ship valuation model by utilizing the neural network model. The target of the valuation was secondhand VLCC. The variables were set as major factors inducing changes in the value of ship through prior research, and the corresponding data were collected on a monthly basis from January 2000 to August 2020. To determine the stability of subsequent variables, a multi-collinearity test was carried out and finally the research structure was designed by selecting six independent variables and one dependent variable. Based on this structure, a total of nine simulation models were designed using linear regression, neural network regression, and random forest algorithm. In addition, the accuracy of the evaluation results are improved through comparative verification between each model. As a result of the evaluation, it was found that the most accurate when the neural network regression model, which consist of a hidden layer composed of two layers, was simulated through comparison with actual VLCC values. The possible implications of this study first, creative research in terms of applying neural network model to ship valuation; this deviates from the existing formalized evaluation techniques. Second, the objectivity of research results was enhanced from a dynamic perspective by analyzing and predicting the factors of changes in the shipping. market.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.263-268
• /
• 2005

Nowadays, the vessel size is tending to be bigger and bigger, so port facilities are following this trend, which has been shown inthe competition of Hub-Port among the main ports such as Port of Busan and Port of Shanghai. But there are limited numbers of large container vessels and $70\%$ of the call ships at Busan port are middle and small sized ships which are less than 20,000ton. So we need to consider the handling facilities for these sized ships, but it has disregarded. In this paper, we estimate the optimum level of crane and labor according to vessel's size by container handling cost value reflecting size of vessel; size and number of crane and labor structure.

• Journal of Korea Port Economic Association
• /
• v.39 no.1
• /
• pp.35-46
• /
• 2023

This study was conducted to evaluating the willingness to pay for marine leisure ships through a contingent valuation method that can estimate the value of non-market economy. The questionnaire adopted a double-bound dichotomous choice Model and the variables for evaluating the amount of willingness to pay consisted of demographic variables and respondent behavior variables, and related information verified through previous studies. As a result of collecting and analyzing a total of 309 questionnaires, the amount of willingness to pay for marine leisure ships was estimated to be 25,510 won. In addition, significant variables affecting the amount of willingness to pay were the experience of visiting the island, satisfaction with the introduction of new maritime transportation, and intention to revisit the island. Through this study, it can be used as a basis for evaluating the economic value of new maritime transportation by estimating the willingness to pay for marine leisure ships using the contingent valuation method.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.06a
• /
• pp.165-166
• /
• 2012

국내 선사와 선박의 안전관리시스템을 평가하기 위하여 평가 지표들을 종합적으로 적용할 수 있는 평가기준을 개발하였다. 추정된 비용과 편익을 기초로 순편익현재가치와 편익비용비율을 구하여 안전관리시스템 도입의 타당성을 분석하였다. - 생략

• Journal of Navigation and Port Research
• /
• v.41 no.4
• /
• pp.181-188
• /
• 2017

In the existing ship sales market, prices determined based on the prices of similar ship types that recently traded. ince the 2008 financial crisis, ship prices have fluctuated, and ship price criteria have become ever more necessary to the imminent value of the ship. Therefore, this research used the hedonic price model to estimate imminent values of ships. In this study, the influence on ship prices was analyzed by the value of each characteristic and an estimated functional formula was. Out of the four models suggested by the hedonic price model, an optimal model was selected with variance inflation factors and a stepwise selection. For this, the influence of determinants of ship prices was analyzed based on actually traded ships and characteristic data. The selected model s the Log-Line model; as a result of regression analysis, eight variables, including DWT, Age, Market Value, Short-Term Charter, Long-Term Charter, Enbloc, Special Survey Due and Builder were to affect the ship price model. This model is expected to be useful for objective and balanced ship price evaluation.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.91-99
• /
• 2022

The shipping industry is a service industry that operates its business by transporting cargo on ships and receiving freight. Therefore, large-scale capital investment is required for ship operation, and if the value of the ship is uncertain, the risk of shipping management increases. This study aims to identify the factors affecting changes in ship value and to analyze the importance of each variable. To achieve the goal, the factors affecting changes in ship value were identified and structured using the techniques of text mining and topic modeling, and classified into three main factors and 12 sub-factors. This study used AHP analysis to examine the relative importance of each factor. Results indicated that the main factor influencing the change in the vessel value was the shipping factor, followed by the investment factor and the environment factor. Other auxiliary factors that substantially affect the ship value include the volatility of the shipping market and of shipping freight.

• Journal of Navigation and Port Research
• /
• v.30 no.6 s.112
• /
• pp.465-470
• /
• 2006

Nowadays, vessel's size is tending to bigger, Therefore port facilities are developed according to this trend, which has been shown in the competition of Hub-Port among the main ports such as Port of Busan and Port of Shanghai. However there are the limited number of large containerships more specifically so 70% of the total ships calling at Busan Port are small and medium sized ships which are less than 20,000 ton As a result, it is necessary to consider the handling facilities of these ships which had been disregarded The big size of facilities increases handling cost bemuse of high investment so it is possible for small and medium sized ships to have disadvantages financially and avoid calling. In this paper, we estimate the propriety of utilization of crane and labor according to the size of vessels after analyzing time value cost, reflecting the size of vessels, size and number of crane and labor structure, and container handling cost value.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2007.12a
• /
• pp.5-7
• /
• 2007

IMO MSC 에서 제안된 E-Navigation 개념은 전자정보통신기술에 기반한 선박과 육상간 해양정보의 수집, 통합, 교환, 표현, 분석 풍을 통해서 항행 안전과 효율을 높이고, 해양환경을 보호하는 항행서비스를 개선하는 것이다. E-Navigation 전략을 개발하고 E-Navigation 환경을 구축하는 과정에서 해상교통환경의 주체가 되는 관제센터와 운항 선박의 정보교환 연동 시뮬레이션은 E-Navigation 환경 구축에서 중요한 의의가 있다. 육상-선박간 연동 시뮬레이션을 통해서 E-Navigation의 다양한 정보 교환의 기술적 가치와 새로운 교통환경의 안전성과 효율성을 평가할 수 있다. 본 연구에서는 항만 관제 모의를 수행하는 VTS 시뮬레이터와 선박운항을 모의하는 선박운항 시뮬레이터를 통합 운영하여 고급의 교통 정보를 양방향으로 교환하고, 각 선박마다 차별화된 교통 정보를 제공받을 수 있는 방안을 마련하기 위한 E-Navigation 환경을 시뮬레이션하는 시스템을 연구하였다.