pp. 3241-3256
S&M3388 Research Paper of Special Issue https://doi.org/10.18494/SAM4252 Published in advance: April 10, 2023 Published: September 29, 2023 Fire Risk Prediction Analysis Using Machine Learning Techniques [PDF] Min Song Seo, Ever Enrique Castillo-Osorio, and Hwan Hee Yoo (Received November 16, 2022; Accepted March 16, 2023) Keywords: fire property damage, support vector machine, random forest, gradient-boosted regression tree, k-fold cross-validation
The damage caused by fire accidents is increasing worldwide. In particular, when a fire occurs, property damage directly affects the lives of citizens. Therefore, in this study, machine learning techniques were applied to analyze the prediction of the future amount of property damage from fire as well as the fire occurrence factors within a geographic area. To achieve this, three years of spatially distributed fire big data for Seoul, the capital of Korea, was used. For the predictive analysis of the amount of fire property damage, the results of analysis by applying machine learning techniques through k-fold cross-validation were calculated. As part of these results, when predicting and analyzing the amount of fire property damage using the random forest (RF) algorithm, an accuracy of 83% was calculated by comparing the predicted data with the actual data. On this basis, the importance of the fire risk factors was analyzed, and it was found that the main factor in the occurrence of fires is the condition of the facilities inside apartment houses. The findings of this study are expected to be used as an important guide for identifying property damage by fire and the factors determining the occurrence of fires in Korea, enabling the evaluation of their spatial distribution and the application of corrective measures to reduce possible damage by urban fires.
Corresponding author: Hwan Hee YooThis work is licensed under a Creative Commons Attribution 4.0 International License. Cite this article Min Song Seo, Ever Enrique Castillo-Osorio, and Hwan Hee Yoo, Fire Risk Prediction Analysis Using Machine Learning Techniques, Sens. Mater., Vol. 35, No. 9, 2023, p. 3241-3256. |