Unsupervised Behavior Change Detection in Multidimensional Data Streams for Maritime Traffic Monitoring
This work addresses maritime monitoring challenges for safety and security, but appears incremental as it investigates existing methods for domain-specific gaps.
The paper tackles the problem of detecting vessel behavior changes in real-time maritime traffic data streams using unsupervised and semi-supervised methods, aiming to identify and label unusual events for accident prevention and illegal activity detection.
The worldwide growth of maritime traffic and the development of the Automatic Identification System (AIS) has led to advances in monitoring systems for preventing vessel accidents and detecting illegal activities. In this work, we describe research gaps and challenges in machine learning for vessel behavior change and event detection, considering several constraints imposed by real-time data streams and the maritime monitoring domain. As a starting point, we investigate how unsupervised and semi-supervised change detection methods may be employed for identifying shifts in vessel behavior, aiming to detect and label unusual events.