Paper title: Anomaly Detection in Vessel Tracking A Bayesian Networks (Bns) Approach
D Handayani, Department of Computer Science, Faculty of Information and Communication Technology, International Islamic University Malaysia
W Sediono, Department of Mechatronics Engineering, Faculty of Engineering, International Islamic University Malaysia
A Shah, Department of Information Systems, Faculty of Information and Communication Technology, International Islamic University Malaysia
The paper describes the supervised method approach to identifying vessel anomaly behaviour. The vessel anomaly behaviour is determined by learning from self-reporting maritime systems based on the Automatic Identification System (AIS). The AIS is a real world vessel reporting data system, which has been recently made compulsory by the International Convention for the Safety of Life and Sea (SOLAS) for vessels over 300 gross tons and most commercial vessels such as cargo ships, passenger vessels, tankers, etc. In this paper, we describe the use of Bayesian networks (BNs) approach to identify the behaviour of the vessel of interest. The BNs is a machine learning technique based on probabilistic theory that represents a set of random variables and their conditional independencies via directed acyclic graph (DAG). Previous studies showed that the BNs have important advantages compared to other machine learning techniques. Among them are that expert knowledge can be included in the BNs model, and that humans can understand and interpret the BNs model more readily. This work proves that the BNs technique is applicable to the identification of vessel anomaly behaviour.
Transactions RINA, Vol 157, Part A3, International Journal Maritime Engineering, Jul-Sep 2015
DOI No: 10.3940/rina.ijme.2015.a3.316
Search and Order IJME papers
All International Journal of Maritime Engineering (IJME) papers are listed in the RINA Publications Database. You can search the database by author name and paper title. Publications may be ordered and paid for online. Other publications are also listed, some of which may be downloaded free of charge. Follow the link to Search Publications & Order.