Asymmetric Threat (Crime) Prediction and Patrol Optimization

Project Overview

The U.S. military faces a variety of opponents (e.g., insurgencies) that are poorly equipped and funded by U.S. standards; however, these opponents often have the advantage of local knowledge and tactics (e.g., improvised explosive devices) that are difficult to counter. The PTL is developing a variety of methods to predict threat from these sources with the ultimate goal of mitigating harm to U.S. personnel and assets. Our general approach is to build statistical spatiotemporal models of incidents (e.g., IED emplacements and other crimes) that take in account the decision making process of attackers. This is accomplished by analyzing the physical and virtual (in the case of Twitter [1]) environment in which candidate crime locations exist [2][3][4][5][6][7][8][9][10][11][12][13].

We have also developed methods to optimize patrol district design to counter the threats described above [14][15][16][17][18].

Software

Many of the methods mentioned above are developed and maintained within the Asymmetric Threat Tracker (ATT) software, a screenshot of which is shown below:

The ATT is an end-to-end solution for data ingest through prediction evaluation and rendering. The system is currently available free of charge under the Apache 2.0 license.

Members


References

  1. [gerber2014predicting] Gerber, M., "Predicting Crime using Twitter and Kernel Density Estimation", Decision Support Systems (Elsevier), vol. 61, pp. 115-125, 2014.
  2. [huddleston2013using] Huddleston, S., and D. Brown, "Using Discrete Event Simulation to Evaluate Time Series Forecasting Methods for Security Applications", Winter Simulation Conference, Washington, D.C., 12/2013.
  3. [huddleston2013geographic] Huddleston, S., M. Gerber, and D. Brown, "Geographic Profiling of Criminal Groups for Military Cordon and Search", Social Computing, Behavioral-Cultural Modeling and Prediction, Charlottesville, VA, Springer-Verlag Berlin, Heidelberg, 2013.
  4. [bernica2013analysis] Bernica, T. W., V. E. Guarino, A. J. Han, L. F. Hennet, M. A. Mitchell, M. Gerber, and D. Brown, "Analysis and Prediction of Insurgent Influence for US Military Strategy", 2013 IEEE Systems and Information Engineering Design Symposium: IEEE, 2013.
  5. [huddleston2012mapping] Huddleston, S., J. Fox, and D. Brown, "Mapping Gang Spheres of Influence", Crime Mapping: A Journal of Research and Practice, vol. 4, issue 2, pp. 39-67, 12/2012.
  6. [wang2012spatio] Wang, X., and D. Brown, "The Spatio-Temporal Modeling for Criminal Incidents", Security Informatics, vol. 1, 02/2012.
  7. [wang2012automatic] Wang, X., M. Gerber, and D. Brown, "Automatic Crime Prediction Using Events Extracted from Twitter Posts", Social Computing, Behavioral - Cultural Modeling and Prediction, vol. 7227: Springer Berlin / Heidelberg, pp. 231-238, 2012.
  8. [fox2012investigating] Fox, J., S. Huddleston, M. Gerber, and D. Brown, "Investigating a Bayesian Hierarchical Framework for Feature-Space Modeling of Criminal Site-Selection Problems", Proceedings of the 23rd Midwest Artificial Intelligence and Cognitive Science Conference, pp. 185--192, 2012.
  9. [wang2012aspatio] Wang, X., D. Brown, and M. Gerber, "Spatio-Temporal Modeling of Criminal Incidents Using Geographic, Demographic, and Twitter-derived Information", International Conference on Intelligence and Security Informatics: IEEE Press, 2012.
  10. [wang2011spatio] Wang, X., and D. Brown, "The Spatio-Temporal Generalized Additive Model for Criminal Incidents", Proceedings of the IEEE International Conference on Intelligence and Security Informatics, 2011.
  11. [huddleston2009statistical] Huddleston, S., and D. Brown, "A Statistical Threat Assessment", IEEE Transactions on Systems, Man, and Cybernetics Part A – Systems and Humans, vol. 39, no. 6, 2009.
  12. [huddleston2008statistical] Huddleston, S., The Statistical Threat Assessment, : University of Virginia, 2008.
  13. [wang2007crime] Wang, X., D. Brown, and J. Conklin, "Crime Incident Association with Consideration of Narrative Information", Proceedings of the IEEE Systems and Information Engineering Design Symposium, 2007.
  14. [zhang2012police] Zhang, Y., and D. Brown, "Police Patrol District Design Using Agent-Based Simulation and GIS", International Conference on Intelligence and Security Informatics: IEEE Press, 2012.
  15. [zhang2013comparison] Zhang, Y., S. Huddleston, D. Brown, and G. Learmonth, "A Comparison of Evaluation Methods for Police Patrol District Designs", Winter Simulation Conference, Washington, DC, 12/2013.
  16. [zhang2013police] Zhang, Y., and D. Brown, "Police Patrol Districting Method and Simulation Evaluation Using Agent-Based Model & GIS", Security Informatics, vol. 2, issue 13, pp. 1-13, 03/2013.
  17. [zhang2014simulation] Zhang, Y., and D. Brown, "Simulation Optimization of Police Patrol District Design Using an Adjusted Simulated Annealing Approach", 2014 Spring Simulation Multi-Conference, Symposium on Theory of Modeling & Simulation - DEVS Integrative M&S Symposium, Tampa, Florida, Curran Associates, 04/2014.
  18. [zhang2014rsm] Zhang, Y., and D. Brown, "Simulation Optimization of Police Patrol Districting Plans Using Response Surfaces", SIMULATION: Transactions of The Society for Modeling and Simulation International, vol. 90, issue 6, pp. 687 - 705, 06/2014.