Maritime Pattern Extraction from AIS Data Using a Genetic Algorithm
Authors:
- Andrej DobrkovicADAndrej Dobrkovic
- Maria-Eugenia IacobMIMaria-Eugenia Iacob
- Jos Van HillegersbergJHJos Van Hillegersberg
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 642-651
Abstract
The long term prediction of maritime vessels' destinations and arrival times is essential for making an effective logistics planning. As ships are influenced by various factors over a long period of time, the solution cannot be achieved by analyzing sailing patterns of each entity separately. Instead, an approach is required, that can extract maritime patterns for the area in question and represent it in a form suitable for querying all possible routes any vessel in that region can take. To tackle this problem we use a genetic algorithm (GA) to cluster vessel position data obtained from the publicly available Automatic Identification System (AIS). The resulting clusters are treated as route waypoints (WP), and by connecting them we get nodes and edges of a directed graph depicting maritime patterns. Since standard clustering algorithms have difficulties in handling data with varying density, and genetic algorithms are slow when handling large data volumes, in this paper we investigate how to enhance the genetic algorithm to allow fast and accurate waypoint identification. We also include a quad tree structure to preprocess data and reduce the input for the GA. When the route graph is created, we add post processing to remove inconsistencies caused by noise in the AIS data. Finally, we validate the results produced by the GA by comparing resulting patterns with known inland water routes for two Dutch provinces.Keywords
This publication has 10 references indexed in Scilit:
- Smart Logistics Corridors and the Benefits of Intelligent Transport Systems2016
- Using machine learning for unsupervised maritime waypoint discovery from streaming AIS data2015
- Synchromodal Container Transportation: An Overview of Current Topics and Research Opportunities2015
- Towards an Approach for Long Term AIS-Based Prediction of Vessel Arrival Times2015
- Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route PredictionEntropy, 2013
- Visually driven analysis of movement data by progressive clusteringInformation Visualization, 2008
- A Design Science Research Methodology for Information Systems ResearchJournal of Management Information Systems, 2007
- Trajectory pattern mining2007
- An Evolutionary Approach to Multiobjective ClusteringIEEE Transactions on Evolutionary Computation, 2007
- Quad trees a data structure for retrieval on composite keysActa Informatica, 1974