Vessel Motion Statistical Learning based on Stored AIS Data and Its Application to Trajectory Prediction

摘要

A vessel motion statistical learning based on stored AIS data is proposed in this paper. This paper divide the region of interest into a uniformly sized grid, and analyze the stored AIS data messages according the vessel's position and index the motion information into the unique grid. The sailing state variation between messages are highlighted. Several predictors are designed to predict the vessel's position and the prediction error is get comparing the true position achieved from AIS messages. Experimental results show that the proposed model is credible and the prediction accuracy is higher.