Modeling threats of mass incidents using scenario-based Bayesian network reasoning

Lida Huang, Guoray Cai, Hongyong Yuan, Jianguo Chen, Yan Wang, Feng Sun

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

1 Citation (Scopus)

Abstract

Mass incidents represent a global problem, putting potential threats to public safety. Due to the complexity and uncertainties of mass incidents, law enforcement agencies lack analytical models and structured processes for anticipating potential threats. To address such challenge, this paper presents a threat analysis framework combining the scenario analysis method and Bayesian network (BN) reasoning. Based on a case library of mass incidents in China, a BN capturing the interaction of twelve key factors in mass incidents is developed, where the network structure is determined by data and expert knowledge. The model is compared with two base-line BN models (use only expert knowledge or data) and a logistic regression model, proving to be the most robust. Using sensitivity analysis, we further identify a more critical subset of those threat-predicting factors. Finally, we present a case study to demonstrate how to apply the proposed framework to assessing the threat of ongoing mass incidents.

Original languageEnglish (US)
Title of host publicationConference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018
EditorsBrian Tomaszewski, Kees Boersma
PublisherInformation Systems for Crisis Response and Management, ISCRAM
Pages121-134
Number of pages14
ISBN (Electronic)9780692127605
StatePublished - Jan 1 2018
Event15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018 - Rochester, United States
Duration: May 20 2018May 23 2018

Publication series

NameProceedings of the International ISCRAM Conference
Volume2018-May
ISSN (Electronic)2411-3387

Other

Other15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018
CountryUnited States
CityRochester
Period5/20/185/23/18

Fingerprint

Bayesian networks
Law enforcement
Sensitivity analysis
Logistics
Analytical models
Modeling
Incidents
Threat
Scenarios
Expert knowledge
Factors

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Electrical and Electronic Engineering

Cite this

Huang, L., Cai, G., Yuan, H., Chen, J., Wang, Y., & Sun, F. (2018). Modeling threats of mass incidents using scenario-based Bayesian network reasoning. In B. Tomaszewski, & K. Boersma (Eds.), Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018 (pp. 121-134). (Proceedings of the International ISCRAM Conference; Vol. 2018-May). Information Systems for Crisis Response and Management, ISCRAM.
Huang, Lida ; Cai, Guoray ; Yuan, Hongyong ; Chen, Jianguo ; Wang, Yan ; Sun, Feng. / Modeling threats of mass incidents using scenario-based Bayesian network reasoning. Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018. editor / Brian Tomaszewski ; Kees Boersma. Information Systems for Crisis Response and Management, ISCRAM, 2018. pp. 121-134 (Proceedings of the International ISCRAM Conference).
@inproceedings{28f8665ae4f344d2be6ff6fb73bd5c14,
title = "Modeling threats of mass incidents using scenario-based Bayesian network reasoning",
abstract = "Mass incidents represent a global problem, putting potential threats to public safety. Due to the complexity and uncertainties of mass incidents, law enforcement agencies lack analytical models and structured processes for anticipating potential threats. To address such challenge, this paper presents a threat analysis framework combining the scenario analysis method and Bayesian network (BN) reasoning. Based on a case library of mass incidents in China, a BN capturing the interaction of twelve key factors in mass incidents is developed, where the network structure is determined by data and expert knowledge. The model is compared with two base-line BN models (use only expert knowledge or data) and a logistic regression model, proving to be the most robust. Using sensitivity analysis, we further identify a more critical subset of those threat-predicting factors. Finally, we present a case study to demonstrate how to apply the proposed framework to assessing the threat of ongoing mass incidents.",
author = "Lida Huang and Guoray Cai and Hongyong Yuan and Jianguo Chen and Yan Wang and Feng Sun",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
series = "Proceedings of the International ISCRAM Conference",
publisher = "Information Systems for Crisis Response and Management, ISCRAM",
pages = "121--134",
editor = "Brian Tomaszewski and Kees Boersma",
booktitle = "Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018",

}

Huang, L, Cai, G, Yuan, H, Chen, J, Wang, Y & Sun, F 2018, Modeling threats of mass incidents using scenario-based Bayesian network reasoning. in B Tomaszewski & K Boersma (eds), Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018. Proceedings of the International ISCRAM Conference, vol. 2018-May, Information Systems for Crisis Response and Management, ISCRAM, pp. 121-134, 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018, Rochester, United States, 5/20/18.

Modeling threats of mass incidents using scenario-based Bayesian network reasoning. / Huang, Lida; Cai, Guoray; Yuan, Hongyong; Chen, Jianguo; Wang, Yan; Sun, Feng.

Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018. ed. / Brian Tomaszewski; Kees Boersma. Information Systems for Crisis Response and Management, ISCRAM, 2018. p. 121-134 (Proceedings of the International ISCRAM Conference; Vol. 2018-May).

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

TY - GEN

T1 - Modeling threats of mass incidents using scenario-based Bayesian network reasoning

AU - Huang, Lida

AU - Cai, Guoray

AU - Yuan, Hongyong

AU - Chen, Jianguo

AU - Wang, Yan

AU - Sun, Feng

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Mass incidents represent a global problem, putting potential threats to public safety. Due to the complexity and uncertainties of mass incidents, law enforcement agencies lack analytical models and structured processes for anticipating potential threats. To address such challenge, this paper presents a threat analysis framework combining the scenario analysis method and Bayesian network (BN) reasoning. Based on a case library of mass incidents in China, a BN capturing the interaction of twelve key factors in mass incidents is developed, where the network structure is determined by data and expert knowledge. The model is compared with two base-line BN models (use only expert knowledge or data) and a logistic regression model, proving to be the most robust. Using sensitivity analysis, we further identify a more critical subset of those threat-predicting factors. Finally, we present a case study to demonstrate how to apply the proposed framework to assessing the threat of ongoing mass incidents.

AB - Mass incidents represent a global problem, putting potential threats to public safety. Due to the complexity and uncertainties of mass incidents, law enforcement agencies lack analytical models and structured processes for anticipating potential threats. To address such challenge, this paper presents a threat analysis framework combining the scenario analysis method and Bayesian network (BN) reasoning. Based on a case library of mass incidents in China, a BN capturing the interaction of twelve key factors in mass incidents is developed, where the network structure is determined by data and expert knowledge. The model is compared with two base-line BN models (use only expert knowledge or data) and a logistic regression model, proving to be the most robust. Using sensitivity analysis, we further identify a more critical subset of those threat-predicting factors. Finally, we present a case study to demonstrate how to apply the proposed framework to assessing the threat of ongoing mass incidents.

UR - http://www.scopus.com/inward/record.url?scp=85060736266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060736266&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060736266

T3 - Proceedings of the International ISCRAM Conference

SP - 121

EP - 134

BT - Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018

A2 - Tomaszewski, Brian

A2 - Boersma, Kees

PB - Information Systems for Crisis Response and Management, ISCRAM

ER -

Huang L, Cai G, Yuan H, Chen J, Wang Y, Sun F. Modeling threats of mass incidents using scenario-based Bayesian network reasoning. In Tomaszewski B, Boersma K, editors, Conference Proceedings - 15th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2018. Information Systems for Crisis Response and Management, ISCRAM. 2018. p. 121-134. (Proceedings of the International ISCRAM Conference).