Securing harbor by combining probabilistic approach with event-based approach

Abstract : As a part of SECuring MARitime (SECMAR) project that aimed to improve security at Marseilles harbor, we developed a decision support system that helps port staff to better monitor ship behavior. It consists of two complementary sub-systems. The first system is based on the probabilistic Hidden Markov Model (HMM) approach and deals with nominal (regular and recurrent) behavior of large to medium size of commercial ships. The second system is based on the reactive synchronous language Esterel and concerns aggressive and transgressive behavior of small ships that may navigate freely in the harbor. Real-time evaluations showed that the proposed decision support system efficiently captured and evaluated ship behavior.