A generative model for predicting terrorist incidents

Whitaker, Roger Marcus ORCID: https://orcid.org/0000-0002-8473-1913 2017. A generative model for predicting terrorist incidents. Presented at: SPIE Defense + Security Symposium: Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII, Anaheim, California United States., 9 - 13 April 2017. SPIE,

Preview

PDF Download (391kB) | Preview

Abstract

A major concern in coalition peace-support operations is the incidence of terrorist activity. In this paper, we propose a generative model for the occurrence of the terrorist incidents, and illustrate that an increase in diversity, as measured by the number of different social groups to which that an individual belongs, is inversely correlated with the likelihood of a terrorist incident in the society. A generative model is one that can predict the likelihood of events in new contexts, as opposed to statistical models which are used to predict the future incidents based on the history of the incidents in an existing context. Generative models can be useful in planning for persistent Information Surveillance and Reconnaissance (ISR) since they allow an estimation of regions in the theater of operation where terrorist incidents may arise, and thus can be used to better allocate the assignment and deployment of ISR assets. In this paper, we present a taxonomy of terrorist incidents, identify factors related to occurrence of terrorist incidents, and provide a mathematical analysis calculating the likelihood of occurrence of terrorist incidents in three common real-life scenarios arising in peace-keeping operations.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Completion
Status:	Submitted
Schools:	Computer Science & Informatics Crime and Security Research Institute (CSURI)
Subjects:	T Technology > T Technology (General) U Military Science > U Military Science (General)
Publisher:	SPIE
Related URLs:	Organisation
Last Modified:	21 Oct 2022 06:59
URI:	https://orca.cardiff.ac.uk/id/eprint/98907

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item