The automatic detection of anomalies in the maritime domain requires representative anomalous instances. Presto is an application that enables maritime-domain experts to create artificial anomalous vessel trajectories, characteristic of traffic violations, illegal fishing activities, drug smuggling, or piracy. When merged with existing real-world data the artificial trajectories enable the application and evaluation of machine learning algorithms for the automatic detection of anomalies.
Presto was developed by Jeroen Janssens during his Ph.D. on outlier selection and one-class classification at Tilburg University for the Poseidon project. It was first demonstrated at the 22nd Benelux Conference on Artificial Intelligence:
Janssens, J.H.M. and Hiemstra, H. and Postma, E.O. Creating artificial vessel trajectories with Presto. In Proceedings of the 22nd Benelux Conference on Artificial Intelligence, Luxembourg, 2010
Tilburg University, Embedded Systems Institute, and Thales Nederland BV have kindly given permission to make Presto open source.
To build the Presto application, you will need Eclipse 3.4.2 for RCP/Plug-in Developers with the RCP plugin (Rich Client Applications) and a Windows machine.
Import Presto in Eclipse:
- In the Eclipse package explorer, right-click and select Import
- Under Plug-in Developement, select Plugin-ins and Fragments and click Next
- Specify the plugin location
- In 'Add Source Code Locations', add source (Presto/src)
- Click Next
- You will get a list of plug-ins and fragments found. Select Presto and click Add
- Click Finish to import the Presto plugin
You should now be able to build and run Presto in Eclipse.
Copyright Tilburg University. Distributed under the GPLv3 license.