Machine Learning-Assisted Anomaly Detection in Maritime Navigation using AIS Data
- 1 April 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 832-838
Abstract
The automatic identification system (AIS) reports vessels' static and dynamic information, which are essential for maritime traffic situation awareness. However, AIS transponders can be switched off to hide suspicious activities, such as illegal fishing, or piracy. Therefore, this paper uses real world AIS data to analyze the possibility of successful detection of various anomalies in the maritime domain. We propose a multi-class artificial neural network (ANN)-based anomaly detection framework to classify intentional and non-intentional AIS on-off switching anomalies. The multi-class anomaly framework captures AIS message dropouts due to various reasons, e.g., channel effects or intentional one for carrying illegal activities. We extract position, speed, course and timing information from real world AIS data, and use them to train a 2-class (normal and anomaly) and a 3-class (normal, power outage and anomaly) anomaly detection models. Our results show that the models achieve around 99.9% overall accuracy, and are able to classify a test sample in the order of microseconds.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Vessel Classification from Space-based AIS Data Using Random Forest2019
- Maritime anomaly detection: A reviewWIREs Data Mining and Knowledge Discovery, 2018
- Exploiting AIS Data for Intelligent Maritime Navigation: A Comprehensive Survey From Data to MethodologyIEEE Transactions on Intelligent Transportation Systems, 2017
- A novel anomaly detection approach to identify intentional AIS on-off switchingExpert Systems with Applications, 2017
- Detection of false AIS messages for the improvement of maritime situational awareness2015
- Maritime Traffic Monitoring Based on Vessel Detection, Tracking, State Estimation, and Trajectory PredictionIEEE Transactions on Intelligent Transportation Systems, 2012
- Bayesian networks for imputation in classification problemsJournal of Intelligent Information Systems, 2007
- Theory of the Backpropagation Neural Network**Based on “nonindent” by Robert Hecht-Nielsen, which appeared in Proceedings of the International Joint Conference on Neural Networks 1, 593–611, June 1989. © 1989 IEEE.1992