Detection of Abnormal Vessel Behaviours Based on AIS Data Features Using HDBSCAN+

R. Hari Kumar; CP Ramanarayanan; K.S.R.R.P. Murthy

doi:10.14429/dsj.73.18626

R. Hari Kumar Defence Institute of Advanced Technology, Girinagar, Pune - 411 025, India https://orcid.org/0000-0001-5773-0264
CP Ramanarayanan Defence Institute of Advanced Technology, Girinagar, Pune - 411 025, India https://orcid.org/0000-0002-7917-9706
K.S.R.R.P. Murthy Defence Institute of Advanced Technology, Girinagar, Pune - 411 025, India https://orcid.org/0000-0003-3049-5502

DOI: https://doi.org/10.14429/dsj.73.18626

Keywords: Maritime anomaly, AIS, Machine Learning, Maritime security, HDBSCAN

Abstract

Achieving maritime security is challenging due to the vastness and complexity of the domain. Monitoring all Achieving maritime security is challenging due to the vastness and complexity of the domain. Monitoring
all vessels that use this medium is humanly impossible but is needed for law enforcement. This paper proposes a
machine learning solution based on HDBSCAN+ to classify the movements of vessels into ‘normal’ or ‘abnormal’.
This classification reduces the number of vessels that have to be monitored by law enforcement agencies to a
manageable size. To date, AIS is the primary source of information that can represent vessel movements and
enable the detection of maritime anomalies. The proposed model uses latitude, longitude, type of vessel, course
and speed as features of the AIS data for analysis. The performance of the proposed model is validated against the marine incidents reported by Information Fusion Centre-Indian Ocean Region (IFC-IOR). The proposed model has successfully detected the incidents reported by IFC-IOR.