A generative model for predicting terrorist incidents

Dinesh C. Verma, Archit Verma, Diane Felmlee, Gavin Pearson, Roger Whitaker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

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.

Original languageEnglish (US)
Title of host publicationGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII
EditorsTien Pham, Michael A. Kolodny
PublisherSPIE
ISBN (Electronic)9781510608818
DOIs
StatePublished - Jan 1 2017
Event8th Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR - Anaheim, United States
Duration: Apr 10 2017Apr 13 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10190
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

Other8th Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR
CountryUnited States
CityAnaheim
Period4/10/174/13/17

Fingerprint

Generative Models
Likelihood
Surveillance
reconnaissance
occurrences
surveillance
Predict
Theaters
Taxonomies
Coalitions
Taxonomy
taxonomy
Mathematical Analysis
Statistical Model
applications of mathematics
Incidence
Assignment
Planning
planning
Scenarios

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Verma, D. C., Verma, A., Felmlee, D., Pearson, G., & Whitaker, R. (2017). A generative model for predicting terrorist incidents. In T. Pham, & M. A. Kolodny (Eds.), Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII [101900E] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10190). SPIE. https://doi.org/10.1117/12.2264909
Verma, Dinesh C. ; Verma, Archit ; Felmlee, Diane ; Pearson, Gavin ; Whitaker, Roger. / A generative model for predicting terrorist incidents. Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII. editor / Tien Pham ; Michael A. Kolodny. SPIE, 2017. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{d7635d9a3439426d874c09d2a78583c4,
title = "A generative model for predicting terrorist incidents",
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.",
author = "Verma, {Dinesh C.} and Archit Verma and Diane Felmlee and Gavin Pearson and Roger Whitaker",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2264909",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Tien Pham and Kolodny, {Michael A.}",
booktitle = "Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII",
address = "United States",

}

Verma, DC, Verma, A, Felmlee, D, Pearson, G & Whitaker, R 2017, A generative model for predicting terrorist incidents. in T Pham & MA Kolodny (eds), Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII., 101900E, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10190, SPIE, 8th Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR, Anaheim, United States, 4/10/17. https://doi.org/10.1117/12.2264909

A generative model for predicting terrorist incidents. / Verma, Dinesh C.; Verma, Archit; Felmlee, Diane; Pearson, Gavin; Whitaker, Roger.

Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII. ed. / Tien Pham; Michael A. Kolodny. SPIE, 2017. 101900E (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10190).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A generative model for predicting terrorist incidents

AU - Verma, Dinesh C.

AU - Verma, Archit

AU - Felmlee, Diane

AU - Pearson, Gavin

AU - Whitaker, Roger

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85022206978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022206978&partnerID=8YFLogxK

U2 - 10.1117/12.2264909

DO - 10.1117/12.2264909

M3 - Conference contribution

AN - SCOPUS:85022206978

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII

A2 - Pham, Tien

A2 - Kolodny, Michael A.

PB - SPIE

ER -

Verma DC, Verma A, Felmlee D, Pearson G, Whitaker R. A generative model for predicting terrorist incidents. In Pham T, Kolodny MA, editors, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII. SPIE. 2017. 101900E. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2264909