Abstract
In the recent years, fire departments started to build databases containing detailed information about their interventions during fires, road accidents, and other types of incidents. Their goal is to invest this information using data analysis methods in order to better understand the trends of certain events. This could help them enhance the management of their allocated resources, which leads to a reduction in the operational costs, increase in efficiency and the overall intervention speed. Therefore, in this research paper, we investigate the possibility of predicting future incidents using machine learning algorithms that are trained on a set of data containing information on almost 200,000 interventions that happened during the last 6 years. These data, provided by the fire department in the region of Doubs, France, were not sufficient to detect patterns. Thus, we have imported additional information from external resources that we thought it would improve the accuracy of the predictions. Finally, we tested multiple machine learning algorithms and we compared their results, aiming to determine which algorithm performs better. The results look promising as we were able to predict the number of interventions for each 3 hours block for a whole year, with an acceptable error margin.
Similar content being viewed by others
Data availibility statement
Datasets used in this study are available on request from the authors.
References
Gerstner GR, Mota JA, Giuliani HK, Weaver MA, Shea NW, and Ryan ED (2022) The impact of repeated bouts of shiftwork on rapid strength and reaction time in career firefighters. Ergonomics, pages 1–9
Jiang W, Chen C, and Cai Y (2016) The design on intelligent physical warning system for fireman. In 2016 International Conference on Audio, Language and Image Processing (ICALIP), pages 694–698. IEEE,
Jayapandian N (2019) Cloud enabled smart firefighting drone using internet of things. In 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT), pages 1079–1083. IEEE
Eltom RH, Hamood EA, Mohammed AA, and Osman AA (2018) Early warning firefighting system using internet of things. In 2018 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), pages 1–7. IEEE
Yaseen ZM, Deo RC, Hilal A, Abd AM, Bueno LC, Salcedo-Sanz S, Nehdi ML (2018) Predicting compressive strength of lightweight foamed concrete using extreme learning machine model. Adv Eng Soft 115:112–125
Umair S and Sharif MM (2018) Predicting students grades using artificial neural networks and support vector machine. In Encyclopedia of information science and technology, Fourth Edition, pages 5169–5182. IGI Global
Samanpour AR, Ruegenberg A, and Ahlers R (2018) The future of machine learning and predictive analytics. In Digital marketplaces unleashed, pages 297–309. Springer, 2018
Lewis-Beck C and Lewis-Beck M (2015) Applied regression: an introduction, volume 22. Sage publications,
Montgomery DC, Peck EA, Vining GG (2012) Introduction to linear regression analysis. John Wiley & Sons
Breiman L (2017) Classification and regression trees. Routledge, 2017
Andy L, Matthew W (2002) Classification and regression by randomforest. R News 2(3):18–22
Wang Lipo (2005) Support vector machines: theory and applications. . Springer Science & Business Media
Smola AJ, Bernhard S (2004) Statistics and computing. Tutor Support Vector Regres 14(3):199–222
Tibshirani R, Wainwright M, and Hastie T (2015) Statistical learning with sparsity: the lasso and generalizations. Chapman and Hall/CRC, 2015
Orages : des inondations aussi dans le Territoire de Belfort (2016) https://www.estrepublicain.fr/
Fabian P, Gaël V, Alexandre G, Vincent M, Bertrand T, Olivier G, Mathieu B, Peter P, Ron W, Vincent D (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Cerna S, Guyeux C, and Laiymani D (2021) The usefulness of nlp techniques for predicting firefighting responses. Neural Computing and Applications, 2021
Nahuis SLC, Guyeux C, Arcolezi H, Couturier R, Royer G, and Lotufo AD (2020) A comparison of lstm and xgboost for predicting firemen interventions. In Reis L.-Costanzo S. Orovic I. Moreira F. Rocha Á, Adeli H, editor, 8th World Conference on Information Systems and Technologies, volume 1160, pages 424–434. Springer (AISC series)
Acknowledgements
This document is the results of the research project supported by the EIPHI Graduate School (contract “ANR-17-EURE-0002”), and the Hubert Curien CEDRE project n 46543ZD.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Guyeux, C., Bou Tayeh, G., Makhoul, A. et al. Using data science to predict firemen interventions: a case study. J Supercomput 79, 7160–7175 (2023). https://doi.org/10.1007/s11227-022-04956-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-022-04956-9