In recent years, the development of low-cost global positioning systems (GPS) transceivers has made it possible to equip all trucks in a fleet withequipment for automatically reporting the status of the trucks to a fleetmanagement system. The downside is that huge amounts of information is gathered and must be evaluated in real-time by an operator. We propose the use of a data-driven anomaly detection algorithm that learns normal truckbehavior and can automatically detect anomalous behavior such as smuggling, accidents and hijacking. The algorithm is evaluated on real data from trucks equipped with GPS transceivers and the results support that anomaly detection can be achieved. This ability can increase transportation security by altering an operator on anomalous truck behavior.
Abstract