Volume 1, Issue 4 (9-2025)
2025, 1(4): 32-36 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
kheiry M, veisani Y, Sayyadi H S, Havasy B, Sahebi A. Predicting Firefighting Response Time in Urban Settings Using Machine Learning: Key Factors for Enhanced Emergency Management. Journal of Health Sciences Perspective 2025; 1 (4) :32-36
URL: http://jhsp.medilam.ac.ir/article-1-49-en.html
URL: http://jhsp.medilam.ac.ir/article-1-49-en.html
Non-Communicable Diseases Research Center, Ilam University of Medical Sciences, Ilam, Iran
Abstract: (42 Views)
Introduction: This study addresses the challenge of accurately predicting firefighting operation times in urban areas using machine learning techniques.
Materials & Methods: Data from 1,399 firefighting incidents in Ilam City during 2022 were analyzed after preprocessing, focusing on 19 key variables out of an initial 31. Among the evaluated models, the Generalized Linear Model (GLM) showed the best performance with the lowest RMSE (14.21 ± 1.65) and estimated an average operation time of 26.96 minutes (95% CI: 12.75–41.17).
Results: Important factors influencing operation duration included the number of personnel, rescue equipment, fire engines, and manual extinguishers. The results demonstrate the potential of ML models to optimize resource allocation and response strategies, contributing to more efficient urban fire management and reduced losses.
Conclusion: Further work is needed to enhance data quality and model accuracy for improved operational planning.
Materials & Methods: Data from 1,399 firefighting incidents in Ilam City during 2022 were analyzed after preprocessing, focusing on 19 key variables out of an initial 31. Among the evaluated models, the Generalized Linear Model (GLM) showed the best performance with the lowest RMSE (14.21 ± 1.65) and estimated an average operation time of 26.96 minutes (95% CI: 12.75–41.17).
Results: Important factors influencing operation duration included the number of personnel, rescue equipment, fire engines, and manual extinguishers. The results demonstrate the potential of ML models to optimize resource allocation and response strategies, contributing to more efficient urban fire management and reduced losses.
Conclusion: Further work is needed to enhance data quality and model accuracy for improved operational planning.
Type of Study: Research |
Subject:
Health program evaluation
Received: 2025/07/7 | Accepted: 2025/08/27 | Published: 2025/09/22
Received: 2025/07/7 | Accepted: 2025/08/27 | Published: 2025/09/22
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |