There is an urgent migrant crisis in much of Europe, fueled by conflict in the Middle East. With a rise of seaborne migration from Turkey to Greece and Italy, there is a need to save lives and secure external borders. This research sets out to expand the foundation of knowledge available on migrant vessels, and by doing so aid in the intervention of migrant ships adrift at sea. By using a partially unsupervised anomaly detection approach potential migrant vessels will be identified. Affinity propagation clustering is used to this end. Affinity propagation will also be used to identify when during a vessel’s voyage it may be identified as a migrant vessel. The sooner the model is able to identify migrant vessels, the sooner authorities will be able to intervene and offer assistance.
LANGFORD Chad;
CHENG Tao;
VESPE Michele;
2016-10-10
European Commission
JRC102616
978-92-79-61301-2,
https://bluehub.jrc.ec.europa.eu/static/KDAD/KDAD_Proceedings.pdf,
https://publications.jrc.ec.europa.eu/repository/handle/JRC102616,
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Additional supporting files
| File name | Description | File type | |
|---|
