Abstract
Due to the vast amount of available tracking sensors in recent years, high-frequency and high-volume streams of data are generated every day. The maritime domain is no different as all larger vessels are obliged to be equipped with a vessel tracking system that transmits their location periodically. Consequently, automated methodologies able to extract meaningful information from high-frequency, large volumes of vessel tracking data need to be developed. The automatic identification of vessel mobility patterns from such data in real time is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Therefore, in this work, we present a novel approach that transforms streaming vessel trajectory patterns into images and employs deep learning algorithms to accurately classify vessel activities in near real time tackling the Big Data challenges of volume and velocity. Two real-world data sets collected from terrestrial, vessel-tracking receivers were used to evaluate the proposed methodology in terms of both classification and streaming execution performance. Experimental results demonstrated that the vessel activity classification performance can reach an accuracy of over 96% while achieving sub-second latencies in streaming execution performance.
Highlights
The sudden increase in mobility data volume and velocity has gained researchers’attention in event-based, distributed, and streaming knowledge extraction methodologies.The automatic identification of patterns in voluminous data is of uttermost importance.Currently, vessels over 300 gross tonnage worldwide are required to carry an AutomaticIdentification System (AIS) transponder on board, a vessel tracking system that allows vessels to report their position periodically
The goal of our methodology was to provide an efficient and alternative way to treat the problem of streaming vessel activity classification as an image classification task using state-of-the-art deep learning algorithms and to create a universal approach for the classification of vessel activities
To demonstrate the applicability of our work in real-world conditions, two real-world data sets of AutomaticIdentification System (AIS) messages were used, one collected from a terrestrial, vessel-tracking receiver installed on our premises and another one extracted from the MarineTraffic database
Summary
The sudden increase in mobility data volume and velocity has gained researchers’attention in event-based, distributed, and streaming knowledge extraction methodologies.The automatic identification of patterns in voluminous data is of uttermost importance.Currently, vessels over 300 gross tonnage worldwide are required to carry an AutomaticIdentification System (AIS) transponder on board, a vessel tracking system that allows vessels to report their position periodically. The sudden increase in mobility data volume and velocity has gained researchers’. The automatic identification of patterns in voluminous data is of uttermost importance. The AIS was initially developed to ensure safety at sea by aiding vessels in collision avoidance situations and assist officers on board, it did not take long for maritime authorities to realize that vessels’ mobility data can provide useful information. Mobility patterns formed by vessels through the AIS can reveal behaviors able to explain suspicious or illegal activities at sea, making the early identification of such events a prominent way for Maritime Situational Awareness (MSA). Several distinct use cases that demonstrate the need for increased MSA include the detection of anomalous vessel behavior due to the damage of the ship, Search And
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
