Adoption of data-driven decision making in fire emergency management

Stephen Smith, Vincent Pang, Kurt Liu, Manolya Kavakli-Thorne, Andrew Edwards, Mehmet Orgun, Richard Host

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Building fires fortunately rarely occur however they may cause the tragic loss of properties and lives. While we all watch the news and see the damage caused by fire on buildings and on rural vegetation, very little research has been undertaken on the rate a fire consumes a building's structure. This research began when the question was asked "If a building is ablaze, how long does it take before the structure is severely damaged". This project is an implementation of Big Data Analysis for Emergency Management through the use of statistical computing tool R and its data visualisation features to analyse historical data set provided by a NSW Government Public Safety Agency that responds to structural fire incidents. The main goal of this project is to determine the optimum fire services' response time on property losses due to urban fires in Australia. More precisely, the results of this study will aid the decision making of Fire Service Agencies by determining the correlation between the damage level and the Emergency services response time. This project has implications for Fire Services not only in NSW but nationally and internationally as there is a research gap in the analysis of (Australian) fire data.

LanguageEnglish
Title of host publication24th European Conference on Information Systems, ECIS 2016
Place of PublicationAtlanta, GA
PublisherAssociation for Information Systems
Pages1-15
Number of pages15
Publication statusPublished - 2016
Event24th European Conference on Information Systems, ECIS 2016 - Istanbul, Turkey
Duration: 12 Jun 201615 Jun 2016

Other

Other24th European Conference on Information Systems, ECIS 2016
CountryTurkey
CityIstanbul
Period12/06/1615/06/16

Fingerprint

Fires
Decision making
Emergency services
Data visualization

Keywords

  • Big data
  • Data-driven decision making (DDDM)
  • Emergency management
  • Theory of action

Cite this

Smith, S., Pang, V., Liu, K., Kavakli-Thorne, M., Edwards, A., Orgun, M., & Host, R. (2016). Adoption of data-driven decision making in fire emergency management. In 24th European Conference on Information Systems, ECIS 2016 (pp. 1-15). Atlanta, GA: Association for Information Systems.
Smith, Stephen ; Pang, Vincent ; Liu, Kurt ; Kavakli-Thorne, Manolya ; Edwards, Andrew ; Orgun, Mehmet ; Host, Richard. / Adoption of data-driven decision making in fire emergency management. 24th European Conference on Information Systems, ECIS 2016. Atlanta, GA : Association for Information Systems, 2016. pp. 1-15
@inproceedings{b0df3f83eabd49339791938fed41e243,
title = "Adoption of data-driven decision making in fire emergency management",
abstract = "Building fires fortunately rarely occur however they may cause the tragic loss of properties and lives. While we all watch the news and see the damage caused by fire on buildings and on rural vegetation, very little research has been undertaken on the rate a fire consumes a building's structure. This research began when the question was asked {"}If a building is ablaze, how long does it take before the structure is severely damaged{"}. This project is an implementation of Big Data Analysis for Emergency Management through the use of statistical computing tool R and its data visualisation features to analyse historical data set provided by a NSW Government Public Safety Agency that responds to structural fire incidents. The main goal of this project is to determine the optimum fire services' response time on property losses due to urban fires in Australia. More precisely, the results of this study will aid the decision making of Fire Service Agencies by determining the correlation between the damage level and the Emergency services response time. This project has implications for Fire Services not only in NSW but nationally and internationally as there is a research gap in the analysis of (Australian) fire data.",
keywords = "Big data, Data-driven decision making (DDDM), Emergency management, Theory of action",
author = "Stephen Smith and Vincent Pang and Kurt Liu and Manolya Kavakli-Thorne and Andrew Edwards and Mehmet Orgun and Richard Host",
year = "2016",
language = "English",
pages = "1--15",
booktitle = "24th European Conference on Information Systems, ECIS 2016",
publisher = "Association for Information Systems",
address = "United States",

}

Smith, S, Pang, V, Liu, K, Kavakli-Thorne, M, Edwards, A, Orgun, M & Host, R 2016, Adoption of data-driven decision making in fire emergency management. in 24th European Conference on Information Systems, ECIS 2016. Association for Information Systems, Atlanta, GA, pp. 1-15, 24th European Conference on Information Systems, ECIS 2016, Istanbul, Turkey, 12/06/16.

Adoption of data-driven decision making in fire emergency management. / Smith, Stephen; Pang, Vincent; Liu, Kurt; Kavakli-Thorne, Manolya; Edwards, Andrew; Orgun, Mehmet; Host, Richard.

24th European Conference on Information Systems, ECIS 2016. Atlanta, GA : Association for Information Systems, 2016. p. 1-15.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Adoption of data-driven decision making in fire emergency management

AU - Smith, Stephen

AU - Pang, Vincent

AU - Liu, Kurt

AU - Kavakli-Thorne, Manolya

AU - Edwards, Andrew

AU - Orgun, Mehmet

AU - Host, Richard

PY - 2016

Y1 - 2016

N2 - Building fires fortunately rarely occur however they may cause the tragic loss of properties and lives. While we all watch the news and see the damage caused by fire on buildings and on rural vegetation, very little research has been undertaken on the rate a fire consumes a building's structure. This research began when the question was asked "If a building is ablaze, how long does it take before the structure is severely damaged". This project is an implementation of Big Data Analysis for Emergency Management through the use of statistical computing tool R and its data visualisation features to analyse historical data set provided by a NSW Government Public Safety Agency that responds to structural fire incidents. The main goal of this project is to determine the optimum fire services' response time on property losses due to urban fires in Australia. More precisely, the results of this study will aid the decision making of Fire Service Agencies by determining the correlation between the damage level and the Emergency services response time. This project has implications for Fire Services not only in NSW but nationally and internationally as there is a research gap in the analysis of (Australian) fire data.

AB - Building fires fortunately rarely occur however they may cause the tragic loss of properties and lives. While we all watch the news and see the damage caused by fire on buildings and on rural vegetation, very little research has been undertaken on the rate a fire consumes a building's structure. This research began when the question was asked "If a building is ablaze, how long does it take before the structure is severely damaged". This project is an implementation of Big Data Analysis for Emergency Management through the use of statistical computing tool R and its data visualisation features to analyse historical data set provided by a NSW Government Public Safety Agency that responds to structural fire incidents. The main goal of this project is to determine the optimum fire services' response time on property losses due to urban fires in Australia. More precisely, the results of this study will aid the decision making of Fire Service Agencies by determining the correlation between the damage level and the Emergency services response time. This project has implications for Fire Services not only in NSW but nationally and internationally as there is a research gap in the analysis of (Australian) fire data.

KW - Big data

KW - Data-driven decision making (DDDM)

KW - Emergency management

KW - Theory of action

UR - http://www.scopus.com/inward/record.url?scp=84995752377&partnerID=8YFLogxK

M3 - Conference proceeding contribution

SP - 1

EP - 15

BT - 24th European Conference on Information Systems, ECIS 2016

PB - Association for Information Systems

CY - Atlanta, GA

ER -

Smith S, Pang V, Liu K, Kavakli-Thorne M, Edwards A, Orgun M et al. Adoption of data-driven decision making in fire emergency management. In 24th European Conference on Information Systems, ECIS 2016. Atlanta, GA: Association for Information Systems. 2016. p. 1-15