2021 STUDENT BURSARY AWARD WINNER!

View the Top 10 Submissions 

For details on how you can apply for a 2022 awards, please watch for updates on the Student Bursary page

Xuyang Han | York University

Clustering Marine Automatic Identification System (AIS) Data Using Optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) 

Abstract: Today, maritime transportation represents substantial international trade. Sustainable development of marine transportation requires systematic modeling and surveillance for maritime situational awareness. In this research, we present an enhanced density-based spatial clustering (DBSCAN) method to model vessel behaviours. The proposed methodology enhances the DBSCAN clustering performance by integrating the Mahalanobis Distance metric that considers the correlations of the points representing the locations of the vessels. The clustering method is applied to historical Automatic Identification System (AIS) data by proposing an algorithm for generating a clustering model of the vessels' trajectories and a model for detecting vessel trajectories anomalies such as unexpected stops, deviations from regulated routes, or inconsistent speed. Besides, an automatic and data-driven approach is proposed to choose the required initial parameters for enhanced DBSCAN.

Two case studies present outcomes from the openly available Gulf of Mexico AIS data and Saint Lawrence Seaway and Great Lakes AIS licensed data acquired from ORBCOMM (a maritime AIS data provider). This work's findings demonstrate the applicability and scalability of proposed method for modeling more water regions, contributing to the situational awareness, vessel collision prevention, safe navigation, route planning, and detection of vessel behaviour anomalies for auto-vessels development towards the sustainability of marine transportation.