Anomaly Detection in Vessel Tracking Using Support Vector Machines (SVMs)

摘要

The paper is devoted to supervise method approach to identify the vessel anomaly behaviour in waterways using the Automated Identification System (AIS) vessel reporting data. In this work, we describe the use of SVMs to detect the vessel anomaly behaviour. The SVMs is a supervised method that needs some pre knowledge to extract the maritime movement patterns of AIS raw data into information. This is the basis to remodel information into a meaningful and valuable form. The result of this work shows that the SVMs technique is applicable to be used for the identification of vessel anomaly behaviour. It is proved that the best accuracy result is obtained from dividing raw data into 70% for training and 30% for testing stages.