The maritime industry is an important part of the global trade system with a growing volume, intensity, and needs. Increasing intensity of maritime traffic raises the need for incident prevention-oriented traffic control.
The maritime anomaly or abnormal movement detection is one of the control techniques. It is based on vessel trajectory analysis and search of irregular, illegal, and other anomalous appearances in trajectory data. A maritime trajectory can include vessel identification data, traffic parameters (e.g. speed and rotation), auxiliary data (e.g., meteorological data) for a vessel, and such dataset presents a large-scale, complex data structure. Nowadays, machine learning-based data analysis and mining techniques is a natural choice for this type of task: the obtained structure of data, the extracted information, detected data regularities could help to estimate vessel movement and make some safety decision, to enable the automatic anomaly detection even. Researches in this field are conducted jointly with the University of Klaipeda by scientists VU Faculty of Mathematics and Informatics (Institute of Data Science and Digital Technologies – Julius Venskus, Povilas Treigys, Jolita Bernatavičienė, Gintautas Tamulevičius, Viktor Medvedev). Algorithms of deep learning neural networks for analysis and processing of sensor traffic data, classification of marine traffic data and detection of unusual traffic are being developed here.
The research is multi-disciplinary and addresses problems related to the analysis of big data, detection of anomalies, retraining of neural networks, processing of sensory data. The results obtained are very useful for solving applied research tasks, contributing to the detection of abnormal ship movement in heavy traffic areas using neural networks.
The results of the research were presented at the international conferences ITISE 2019 (Granada, Spain) and CDAM 2019 (Minsk, Belarus) and published in the journals indexed by the Science Citation Index Expanded (Clarivate Analytics Web of Science): Informatica and Sensors (Q1).
Read more about research here:
Real-Time Maritime Traffic Anomaly Detection Based on Sensors and History Data Embedding