Vessel Traffic Services operators have kept sharp monitoring and provided the appropriate information to ensure safe and effective navigation. While attending the tasks, analysis of traffic patterns and navigational data is required to conduct accurate situation assessment in decision-making process of VTS operators (VTSO). Unfortunately, there are problems in the process of data analysis such as appropriateness of time, VTSO’s personal error and improper judgment. Therefore, objective and proper data analysis is necessary to solve above matters. However, it is virtually impossible to monitor all vessels because there are many vessels in the VTS area and at the same time complex traffic situations are produced. In this study, we proposed a machine learning algorithms for objective and accurate pattern recognition and data modeling. Support Vector Regression algorithm was used for data learning and modeling. The optimal parameters were selected through v-fold cross validation and grid search. The machine learning was conducted with virtual route and ship tracks that are similar with real navigational environment. As a result, we presented reference route and navigational patterns. We expect that the proposed modeling methods could be utilized for relevant tasks as the useful information to VTSO and/or ship’s mater.

Keywords: Vessel Traffic Services, Machine learning, Sea traffic route, Decision making, Pattern recognition

No potential conflict of interest relevant to this article was reported.