Abstract | ||
---|---|---|
In this paper, we present the topology preserving mapping for maritime anomaly detection. Specifically, the topology preserving mapping is applied as an unsupervised learning method, which captures the vessel behaviors and visualizes the extracted underlying data structure. At the same time, the topology preserving mapping is used as the probability estimator, where the data likelihood can be evaluated and the anomalies can be detected. Real satellite AIS data, used by the Next Generation Recognized Maritime Picture project (NG-RMP) funded by the European Space Agency, is used in this paper as the main data source. We demonstrate that the topology preserving mapping can classify the vessel observations and detect the anomalies reasonably and with high accuracy. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-09153-2_24 | ICCSA (6) |
Field | DocType | Volume |
Data source,Anomaly detection,Data mining,Topology,Data structure,Satellite,Computer science,Unsupervised learning,Bayesian network,Mixture model,Estimator | Conference | 8584 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.36 |
References | Authors | |
11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ying Wu | 1 | 9 | 2.26 |
Anthony Patterson | 2 | 1 | 0.36 |
Rafael D. C. Santos | 3 | 1 | 0.70 |
Nandamudi L. Vijaykumar | 4 | 54 | 7.18 |