EURO 2024 Copenhagen
Abstract Submission

• Home
• Abstract submission
• Search abstract
• Topic keywords
• Streams
• F.A.Q.
• Program
• Help

502. Detecting Drug Transfers via the Drop-off Method: A Supervised Model Approach using AIS Data

Invited abstract in session MC-28: Advancements of OR-analytics in statistics, machine learning and data science 3, stream Advancements of OR-analytics in statistics, machine learning and data science.

Monday, 12:30-14:00
Room: 065 (building: 208)

Authors (first author is the speaker)

1.	Britt van Leeuwen
	Stochastics, Centrum Wiskunde & Informatica
2.	Maike Nutzel
	Vrije Universiteit Amsterdam

Abstract

This paper introduces a novel approach for detecting sea-based drug transfers through the utilization of Automatic Identification System (AIS) data. We propose a model for the detection of the ’drop-off’ method, a prevalent technique for contraband smuggling at sea. Unlike the prevailing focus on unsupervised methods in existing maritime anomaly detection research, our paper introduces a supervised model tailored to the ‘drop-off’ method, particularly in the context of fishing vessels. We have developed a machine learning algorithm, employing a Long Short-Term Memory (LSTM) model capable of identifying ‘drop-offs’. This model holds the potential for integration into real-time surveillance systems. Furthermore, our model demonstrates generalizability, thereby enhancing maritime security efforts and providing invaluable assistance in countering drug traffic on a global scale.

Keywords

• Machine Learning

Status: accepted

---

Back to the list of papers

---