Topology Preserving Mapping for Maritime Anomaly Detection

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.

[1]  Leto Peel,et al.  Maritime anomaly detection using Gaussian Process active learning , 2012, 2012 15th International Conference on Information Fusion.

[2]  Pragya Agarwal,et al.  Self-Organising Maps , 2008 .

[3]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[4]  Subrata Das,et al.  Situation assessment via Bayesian belief networks , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[5]  Rikard Laxhammar,et al.  Anomaly detection for sea surveillance , 2008, 2008 11th International Conference on Information Fusion.

[6]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[7]  Paul Strauch,et al.  A robust 60 GHz wireless network with parallel relaying , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).

[8]  Tobias Schreck,et al.  Visual Cluster Analysis of Trajectory Data with Interactive Kohonen Maps , 2008, 2008 IEEE Symposium on Visual Analytics Science and Technology.

[9]  Colin Fyfe,et al.  Topology-Preserving Mappings for Data Visualisation , 2008 .

[10]  Jean Roy,et al.  Rule-based expert system for maritime anomaly detection , 2010, Defense + Commercial Sensing.

[11]  Bradley J. Rhodes,et al.  Adaptive Mixture-Based Neural Network Approach for Higher-Level Fusion and Automated Behavior Monitoring , 2009, 2009 IEEE International Conference on Communications.

[12]  James B. Kraiman,et al.  Automated anomaly detection processor , 2002, SPIE Defense + Commercial Sensing.

[13]  Mark R. Morelande,et al.  Statistical analysis of motion patterns in AIS Data: Anomaly detection and motion prediction , 2008, 2008 11th International Conference on Information Fusion.

[14]  Victor J. Rayward-Smith,et al.  Intelligent Data Engineering and Automated Learning - IDEAL 2011 , 2011, Lecture Notes in Computer Science.

[15]  Ying Wu,et al.  Multi-layer Topology Preserving Mapping for K-Means Clustering , 2011, IDEAL.

[16]  Shie Mannor,et al.  A Tutorial on the Cross-Entropy Method , 2005, Ann. Oper. Res..

[17]  C. Fyfe,et al.  The on-line cross entropy method for unsupervised data exploration , 2007 .

[18]  Jean Roy,et al.  Anomaly detection in the maritime domain , 2008, SPIE Defense + Commercial Sensing.

[19]  Andrei Zinovyev,et al.  Principal Manifolds for Data Visualization and Dimension Reduction , 2007 .

[20]  Göran Falkman,et al.  Anomaly detection in sea traffic - A comparison of the Gaussian Mixture Model and the Kernel Density Estimator , 2009, 2009 12th International Conference on Information Fusion.

[21]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[22]  Tobias Schreck,et al.  Visual Cluster Analysis of Trajectory Data with Interactive Kohonen Maps , 2009 .

[23]  Ian Lewis,et al.  Proceedings of the SPIE , 2012 .

[24]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.

[25]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[26]  Colin Fyfe,et al.  Two topographic maps for data visualisation , 2007, Data Mining and Knowledge Discovery.