By Paolo Franchi
Computational maritime situational awareness techniques for unsupervised port area estimation. Millefiori, Leonardo; Zissis, Dimitrios; Cazzanti, Luca; Arcieri, Gianfranco. CMRE-FR-2016-004. September 2016.
This report presents work on estimating port locations and operational areas in a scalable, data-driven, unsupervised way. Knowing the extent of port areas is an important component of larger maritime traffic analysis systems that inform stakeholders and decision makers in the maritime industry, governmental agencies, and international organizations. The proposed approach uses a cloud-based MapReduce implementation of the Kernel Density Estimation (KDE) algorithm and exploits a large volume of Automatic Identification System (AIS) data to learn the extent of port areas in a data-driven way. The results from three case studies are presented and discussed for the port of La Spezia (ITA), Rotterdam (NLD), and Shanghai (CHN).