Statistical analysis of motion patterns in AIS Data: Anomaly detection and motion prediction

The paper is devoted to statistical analysis of vessel motion patterns in the ports and waterways using AIS ship self-reporting data. From the real historic AIS data we extract motion patterns which are then used to construct the corresponding motion anomaly detectors. This is carried out in the framework of adaptive kernel density estimation. The anomaly detector is then sequentially applied to the real incoming AIS data for the purpose of anomaly detection. Under the null hypothesis (no anomaly), using the historic motion pattern data, we predict the motion of vessels using the Gaussian sum tracking filter.