پیش بینی ماهیت حریق مبتنی بر یادگیری ماشین: رگرسیون لجستیک یک الگوریتم تفسیر پذیر

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس تحول و نوسازی سازمان آتش نشانی و خدمات ایمنی شهرداری مشهد، مشهد، ایران

2 استادیار مهندسی صنایع، دانشکده مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران

3 شهرداری مشهد، سازمان آتش نشانی و خدمات ایمنی، مشهد، ایران

چکیده

یکی از وظایف سازمان‌های آتش‌نشانی ارائه گزارش حریق و حوادث به مراجع قضائی، بیمه و سایر نهادهای درخواست‌کننده جهت تصمیم‌گیری و پرداخت خسارت است، لذا یافتن ماهیت حریق به‌نحوی‌که مؤلفه‌های غیرعملیاتی در تصمیم کارشناسان آتش‌نشانی کمترین تأثیر را داشته باشد، اهمیت این پژوهش را بیشتر خواهد نمود. باتوجه‌به اینکه حدود 1 درصد از گزارشات حریق این سازمان ماهیت نامعلوم دارند، این موضوع باعث سردرگمی در ارائه خدمات مناسب به ارباب رجوع را داشته و تصمیم گیری با مشکل مواجه شده است. هدف از این پژوهش پیش بینی ماهیت حریق مبتنی بر الگوریتم های یادگیری ماشین در شهر مشهد می باشد. در این پژوهش ابتدا مجموعه داده حریق 7 ساله (1395-1401) مورد بررسی و واکاوی قرار گرفت و پس از آن با توجه به مسئله و ادبیات موضوع و با انجام پیش پردازش و مهندسی ویژگی مجموعه داده ای با تعداد 46 ویژگی و 28930 نمونه تهیه شد. در مرحله بعد برای پیش بینی ماهیت حریق از سه الگوریتم یادگیری ماشین با ناظر استفاده شد و نتایج آن ها با هم مقایسه شد که الگوریتم رگرسیون لجستیک با 79.66 درصد دقت با زمان اجرای 1 ثانیه نتیجه بهتری را بین سه الگوریتم جهت پیش بینی ماهیت حریق ایجاد نموده است.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting the nature of fire based on machine learning: Logistic regression is an interpretable algorithm

نویسندگان [English]

  • Fatemeh Mosalmanzadeh 1
  • Hamidreza Koosha 2
  • Kazem Saedi 3
1 Organizational modernization and transformation expert, Fire&Safety Services Department, Mashhad municipality
2 Ferdowsi University of Mashhad, Sharif University of Technology, Tarbiat Modares University
3 Mashhad Municipality, Fire and Services department, Mashhad, Iran
چکیده [English]

One of the duties of firefighting organizations is to submit fire and accident reports to judicial authorities, insurance, and other requesting institutions to make decisions and pay damages, therefore, finding the nature of the fire in such a way that non-operational components have the least impact on the decision of firefighting experts increases the importance of this research. Considering that about 1% of the fire reports of this organization are unknown, this issue has confused providing proper services to Arbab-Rojoo and decision-making has been difficult. This research aims to predict the nature of fire based on machine learning algorithms in the city of Mashhad. In this research, the 7-year fire data set (1395-1401) was first examined and analyzed, and then, according to the problem and the literature, a data set with 46 features and 28930 samples was prepared by pre-processing and feature engineering. In the next step, to predict the nature of the fire, three machine learning algorithms were used with the observer and their results were compared. The logistic regression algorithm, with 79.66% accuracy and an execution time of 1 second, created a better result between the three algorithms in predicting the nature of the fire.

کلیدواژه‌ها [English]

  • Nature of fire
  • intentional
  • unintentional
  • machine learning
  • logistic regression
[1]         M. Niknam, “Tehran: Organization of Records and National Library of the Islamic Republic of Iran, Research and Education Management Publications; 2006,” Combating fire, 2006.
[2]         http://www.firedata.org.
[3]         Gorbett, G.E., Meacham, B.J., Wood, C.B. et al. "Use of damage in fire investigation: a review of fire patterns analysis, research and future direction". Fire Sci Rev 4, 4 (2015). https://doi.org/10.1186/s40038-015-0008-4
[4]         NFPA (2014) NFPA 921-"Guide for Fire and Explosion Investigations". National Fire Protection Association, Quincy (USA)
[5]         C. R. Jennings, “Socioeconomic characteristics and their relationship to fire incidence: a review of the literature,” Fire Technol., vol. 35, no. 1, pp. 7–34, 1999, doi: 10.1023/A:1015330931387.
[6]         T. Curt, T. Fréjaville, and S. Lahaye, “Modelling the spatial patterns of ignition causes and fire regime features in southern France: Implications for fire prevention policy,” Int. J. Wildl. Fire, vol. 25, no. 7, pp. 785–796, 2016, doi: 10.1071/WF15205.
[7]         Y. Zhang, “Federal Emergency Management Agency (FEMA),” Encycl. Glob. Heal., 2012, doi: 10.4135/9781412963855.n451.
[8]         P. Chhetri, J. Corcoran, R. J. Stimson, and R. Inbakaran, “Modelling potential socio-economic determinants of building fires in South East Queensland,” Geogr. Res., vol. 48, no. 1, pp. 75–85, 2010, doi: 10.1111/j.1745-5871.2009.00587.x.
[9]         S. E. Chandler, A. Chapman, and S. J. Hollington, “Fire Incidence, Housing and Social Conditions - the Urban Situation in Britain.,” Fire Prev., no. 172, pp. 15–20, 1984.
[10]       M. Duncanson, A. Woodward, and P. Reid, “Socioeconomic deprivation and fatal unintentional domestic fire incidents in New Zealand 1993-1998,” Fire Saf. J., vol. 37, no. 2, pp. 165–179, 2002, doi: 10.1016/S0379-7112(01)00033-9.
[11]       J. Corcoran, G. Higgs, C. Brunsdon, and A. Ware, “The use of comaps to explore the spatial and temporal dynamics of fire incidents: A case study in South Wales, United Kingdom,” Prof. Geogr., vol. 59, no. 4, pp. 521–536, 2007, doi: 10.1111/j.1467-9272.2007.00639.x.
[12]       J. Corcoran, G. Higgs, and A. Higginson, “Fire incidence in metropolitan areas: A comparative study of Brisbane (Australia) and Cardiff (United Kingdom),” Appl. Geogr., vol. 31, no. 1, pp. 65–75, 2011, doi: 10.1016/j.apgeog.2010.02.003.
[13]       J. Corcoran, G. Higgs, C. Brunsdon, A. Ware, and P. Norman, “The use of spatial analytical techniques to explore patterns of fire incidence: A South Wales case study,” Comput. Environ. Urban Syst., vol. 31, no. 6, pp. 623–647, 2007, doi: 10.1016/j.compenvurbsys.2007.01.002.
[14]       A. Balboa, A. Cuesta, J. González-Villa, G. Ortiz, and D. Alvear, “Logistic regression vs machine learning to predict evacuation decisions in fire alarm situations,” Saf. Sci., vol. 174, no. April 2023, 2024, doi: 10.1016/j.ssci.2024.106485.
[15]       S. M. Lo, M. Liu, P. H. Zhang, and R. K. K. Yuen, “An artificial neural-network based predictive model for pre-evacuation human response in domestic building fire,” Fire Technol., vol. 45, no. 4, pp. 431–449, 2009, doi: 10.1007/s10694-008-0064-6.
[16]       N. Qu, Z. Li, X. Li, S. Zhang, and T. Zheng, “Multi-parameter fire detection method based on feature depth extraction and stacking ensemble learning model,” Fire Saf. J., vol. 128, 2022, doi: 10.1016/j.firesaf.2022.103541.
[17]       J. L. Hodges, B. Y. Lattimer, and K. D. Luxbacher, “Compartment fire predictions using transpose convolutional neural networks,” Fire Saf. J., vol. 108, p. 102854, 2019, doi: 10.1016/j.firesaf.2019.102854.
[18]       Y. O. Sayad, H. Mousannif, and H. Al Moatassime, “Predictive modeling of wildfires: A new dataset and machine learning approach,” Fire Saf. J., vol. 104, pp. 130–146, 2019, doi: 10.1016/j.firesaf.2019.01.006.
[19]       Y. Hong, J. Kang, and C. Fu, “Rapid prediction of mine tunnel fire smoke movement with machine learning and supercomputing techniques,” Fire Saf. J., vol. 127, 2022, doi: 10.1016/j.firesaf.2021.103492.
[20]       J. Wang et al., “P-Flash – A machine learning-based model for flashover prediction using recovered temperature data,” Fire Saf. J., vol. 122, no. June 2020, p. 103341, 2021, doi: 10.1016/j.firesaf.2021.103341.
[21]       J. Gubbi, S. Marusic, and M. Palaniswami, “Smoke detection in video using wavelets and support vector machines,” Fire Saf. J., vol. 44, no. 8, pp. 1110–1115, 2009, doi: 10.1016/j.firesaf.2009.08.003.
[22]       L. Fan, W. C. Tam, Q. Tong, E. Y. Fu, and T. Liang, “An explainable machine learning based flashover prediction model using dimension-wise class activation map,” Fire Saf. J., vol. 140, 2023, doi: 10.1016/j.firesaf.2023.103849.
[23]       “A Bayesian analysis of domestic fire response and fire injury”.
[24]       C. Couto, Q. Tong, and T. Gernay, “Predicting the capacity of thin-walled beams at elevated temperature with machine learning,” Fire Saf. J., vol. 130, no. February, p. 103596, 2022, doi: 10.1016/j.firesaf.2022.103596.
[25]       M. Z. Naser, “Mechanistically Informed Machine Learning and Artificial Intelligence in Fire Engineering and Sciences,” Fire Technol., vol. 57, no. 6, pp. 2741–2784, 2021, doi: 10.1007/s10694-020-01069-8.
[26]       Incidents statistics reports for the I. M. Fire & Safety service organization, “http://www.mahar.mashhad.ir.”