Exploiting multiclass classification algorithms for the prediction of ship routes: a study in the area of Malta

Abstract

Purpose Ship route prediction (SRP) is a quite complicated task, which enables the determination of the next position of a ship after a given period of time, given its current position. This paper aims to describe a study, which compares five families of multiclass classification algorithms to perform SRP. Design/methodology/approach Tested algorithm families include: Naive Bayes (NB), nearest neighbors, decision trees, linear algorithms and extension from binary. A common structure for all the algorithm families was implemented and adapted to the specific case, according to the test to be done. The tests were done on one month of real data extracted from automatic identification system messages, collected around the island of Malta. Findings Experiments show that K-nearest neighbors and decision trees algorithms outperform all the other algorithms. Experiments also demonstrate that linear algorithms and NB have a very poor performance. Research limitations/implications This study is limited to the area surrounding Malta. Thus, findings cannot be generalized to every context. However, the methodology presented is general and can help other researchers in this area to choose appropriate methods for their problems. Practical implications The results of this study can be exploited by applications for maritime surveillance to build decision support systems to monitor and predict ship routes in a given area. For example, to protect the marine environment, the use of SRP techniques could be used to protect areas at risk such as marine protected areas, from illegal fishing. Originality/value The paper proposes a solid methodology to perform tests on SRP, based on a series of important machine learning algorithms for the prediction.