A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams

Abstract

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 timesampling. 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.

arXiv commentAccepted to IEEE DSAA 2018

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• A Recurrent Latent Variable Model for Sequential Data
• Sequential Neural Models with Stochastic Layers
• TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

Cited by in corpus (12)

• GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection
• TrAISformer -- A Transformer Network with Sparse Augmented Data Representation and Cross Entropy Loss for AIS-based Vessel Trajectory Prediction
• Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning
• A semi-supervised methodology for fishing activity detection using the geometry behind the trajectory of multiple vessels
• Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning
• Deep Learning Methods for Vessel Trajectory Prediction based on Recurrent Neural Networks
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection
• The Unsupervised Method of Vessel Movement Trajectory Prediction
• Space-based Global Maritime Surveillance. Part II: Artificial Intelligence and Data Fusion Techniques
• Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning
• Detection of Abnormal Vessel Behaviours from AIS data using GeoTrackNet: from the Laboratory to the Ocean