A spatio-temporal data representation framework with applications to anomaly detection in the maritime domain

Maritime security and disaster response are critical for many nations to address the vulnerability of their sea lanes, ports, and harbours to a variety of illegal activities as well as to prevent, minimize, and respond to environmental and human disasters. With increasing volume of spatio-temporal data available from systems like the Automatic Identification System, satellite, marine radar, and other sources it is increasingly problematic to analyze this enormous volume of data. This work builds on the state-of-the art in spatio-temporal anomaly detection by proposing a representation framework for spatio-temporal data, providing a software implementation as an API, and evaluating it. The aim of the framework is to represent spatio-temporal data using abstract concepts to describe motion over time in order to concisely represent high level abstract motion behaviours. The framework is generic and can be applied to any type of spatio-temporal data, but the focus is on the maritime domain.

[1]  K. Jarrod Millman,et al.  Python for Scientists and Engineers , 2011, Comput. Sci. Eng..

[2]  Roozbeh Farahbod,et al.  A Formal Engineering Approach to High-Level Design of Situation Analysis Decision Support Systems , 2011, ICFEM.

[3]  Xavier Ferrer,et al.  European Atlantic: the hottest oil spill hotspot worldwide , 2004, Naturwissenschaften.

[4]  Uwe Glässer,et al.  Anomaly detection in spatiotemporal data in the maritime domain , 2012, 2012 IEEE International Conference on Intelligence and Security Informatics.

[5]  W. Cleveland.  Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .

[6]  Rikard Laxhammar,et al.  Conformal prediction for distribution-independent anomaly detection in streaming vessel data , 2010, StreamKDD '10.

[7]  Christer Carlsson,et al.  Past, present, and future of decision support technology , 2002, Decis. Support Syst..

[8]  Douglas M. Hawkins.  Identification of Outliers , 1980, Monographs on Applied Probability and Statistics.

[9]  Roozbeh Farahbod,et al.  Engineering Situation Analysis Decision Support Systems , 2011, 2011 European Intelligence and Security Informatics Conference.

[10]  Mica R. Endsley,et al.  Theoretical Underpinnings of Situation Awareness, A Critical Review , 2000 .

[11]  Etienne Martineau,et al.  Maritime Anomaly Detection: Domain Introduction and Review of Selected Literature , 2011 .

[12]  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.

[13]  Santiago Iglesias Baniela.  Piracy at Sea: Somalia an Area of Great Concern , 2010, Journal of Navigation.

[14]  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.

[15]  Wilfried Brauer,et al.  Qualitative Motion Representation in Egocentric and Allocentric Frames of Reference , 1999, COSIT.

[16]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[17]  Wilfried Brauer,et al.  From Motion Observation to Qualitative Motion Representation , 2000, Spatial Cognition.

[18]  H. J. Arnold.  Introduction to the Practice of Statistics , 1990 .

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

[20]  D. W. Scott.  Kernel Density Estimators , 2008 .

[21]  Richard O. Lane,et al.  Maritime anomaly detection and threat assessment , 2010, 2010 13th International Conference on Information Fusion.

[22]  Kevin B. Korb,et al.  Learning Abnormal Vessel Behaviour from AIS Data with Bayesian Networks at Two Time Scales , 2010 .