Multi-task Learning for Maritime Traffic Surveillance from AIS Data Streams

In a world of global trading, maritime safety, security and efficiency are crucial issues. We propose a multi-task deep learning framework for vessel monitoring using Automatic Identification System (AIS) data streams. We combine recurrent neural networks with latent variable modeling and an embedding of AIS messages to a new representation space to jointly address key issues to be dealt with when considering AIS data streams: massive amount of streaming data, noisy data and irregular time-sampling. We demonstrate the relevance of the proposed deep learning framework on real AIS datasets for a three-task setting, namely trajectory reconstruction, anomaly detection and vessel type identification.

[1]  Leto Peel,et al.  Fast Maritime Anomaly Detection using KD Tree Gaussian Processes , 2011 .

[2]  Rikard Laxhammar,et al.  Anomaly detection for sea surveillance , 2008, 2008 11th International Conference on Information Fusion.

[3]  Paolo Braca,et al.  Multiple Ornstein–Uhlenbeck Processes for Maritime Traffic Graph Representation , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Bradley J. Rhodes,et al.  Probabilistic prediction of vessel motion at multiple spatial scales for maritime situation awareness , 2008, 2008 11th International Conference on Information Fusion.

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[6]  Stan Matwin,et al.  TrajectoryNet: an embedded GPS trajectory representation for point-based classification using recurrent neural networks , 2017, CASCON.

[7]  Fabio Mazzarella,et al.  Knowledge-based vessel position prediction using historical AIS data , 2015, 2015 Sensor Data Fusion: Trends, Solutions, Applications (SDF).

[8]  Ole Winther,et al.  Sequential Neural Models with Stochastic Layers , 2016, NIPS.

[9]  B.J. Rhodes,et al.  Maritime situation monitoring and awareness using learning mechanisms , 2005, MILCOM 2005 - 2005 IEEE Military Communications Conference.

[10]  Mark R. Morelande,et al.  Statistical analysis of motion patterns in AIS Data: Anomaly detection and motion prediction , 2008, 2008 11th International Conference on Information Fusion.

[11]  F. Johansson,et al.  Detection of vessel anomalies - a Bayesian network approach , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[12]  Michele Vespe,et al.  Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction , 2013, Entropy.

[13]  Allen M. Waxman,et al.  Associative Learning of Vessel Motion Patterns for Maritime Situation Awareness , 2006, 2006 9th International Conference on Information Fusion.

[14]  Fawzi Nashashibi,et al.  Real time trajectory prediction for collision risk estimation between vehicles , 2009, 2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing.

[15]  Lokukaluge P. Perera,et al.  Maritime Traffic Monitoring Based on Vessel Detection, Tracking, State Estimation, and Trajectory Prediction , 2012, IEEE Transactions on Intelligent Transportation Systems.

[16]  Leto Peel,et al.  Maritime anomaly detection using Gaussian Process active learning , 2012, 2012 15th International Conference on Information Fusion.

[17]  Uri Shalit,et al.  Structured Inference Networks for Nonlinear State Space Models , 2016, AAAI.

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Edmund Førland Brekke,et al.  AIS-based vessel trajectory prediction , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[20]  Paolo Braca,et al.  Context-enhanced vessel prediction based on Ornstein-Uhlenbeck processes using historical AIS traffic patterns: Real-world experimental results , 2014, 17th International Conference on Information Fusion (FUSION).

[21]  S. Ertugrul,et al.  Prediction of Position and Course of a Vessel Using Artificial Neural Networks by Utilizing GPS/Radar Data , 2007, 2007 3rd International Conference on Recent Advances in Space Technologies.

[22]  Yee Whye Teh,et al.  Filtering Variational Objectives , 2017, NIPS.

[23]  M. Ammar,et al.  AN A-CONTRARIO APPROACH FOR OBJECT DETECTION IN VIDEO SEQUENCE , 2013 .

[24]  Kevin B. Korb,et al.  Anomaly detection in vessel tracks using Bayesian networks , 2014, Int. J. Approx. Reason..

[25]  Alessandro De Gloria,et al.  A Reliability Game for Source Factors and Situational Awareness Experimentation , 2018, Int. J. Serious Games.

[26]  Stan Matwin,et al.  Improving Fishing Pattern Detection from Satellite AIS Using Data Mining and Machine Learning , 2016, PloS one.

[27]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  R. A. Best,et al.  A new model and efficient tracker for a target with curvilinear motion , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[29]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[30]  Gerd Wanielik,et al.  Comparison and evaluation of advanced motion models for vehicle tracking , 2008, 2008 11th International Conference on Information Fusion.