AN INTELLIGENT MODEL FOR PREDICTING FIRE RISK IN RESIDENTIAL HOUSEHOLDS BASED ON ARTIFICIAL INTELLIGENCE
Keywords:
artificial intelligence, fire risk prediction, residential safety, smart sensors, emergency management, fire prevention.Abstract
Residential fires remain a major threat to human life, property, and public safety. Most conventional fire safety systems are designed to detect fire after ignition, limiting their preventive capabilities. This study proposes an intelligent model for predicting fire risk in residential households based on artificial intelligence. The model integrates data from temperature, smoke, gas, humidity, and electrical sensors to assess fire hazards before ignition occurs. By analyzing multiple risk indicators simultaneously, the proposed approach enables early warning, supports preventive measures, and contributes to reducing fire-related losses. The study highlights the practical potential of artificial intelligence in strengthening residential fire safety and emergency management.
References
1.Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
2.Chen, L., Zhang, X., & Liu, Q. (2023). Internet of Things-based fire monitoring and early warning framework for residential buildings. IEEE Access, 11, 55421–55435.
3.Garcia, M., & Torres, J. (2022). Intelligent risk prediction in smart homes using environmental sensors. Sustainable Cities and Society, 79, Article 103686.
4.International Electrotechnical Commission. (2023). Electrical installations for buildings: Safety requirements. IEC Publications.
5.Kim, S., & Lee, J. (2021). IoT-enabled smart fire monitoring system for residential environments. Sensors, 21(15), Article 5123. https://doi.org/10.3390/s21155123
6.Li, Z., Huang, P., & Xu, T. (2024). Artificial intelligence applications in smart fire prevention systems: A systematic review. Safety Science, 171, Article 106390.
7.Liu, H., & Zhao, Y. (2024). Explainable artificial intelligence for fire risk classification. Engineering Applications of Artificial Intelligence, 128, Article 107561.
8.Ministry of Emergency Situations of the Republic of Uzbekistan. (2024). Annual report on fire safety and emergency statistics in Uzbekistan. Ministry of Emergency Situations Publishing Department.
9.National Fire Protection Association. (2024). Electrical fires report. National Fire Protection Association.
10.Russell, S., & Norvig, P. (2021). Artificial intelligence: A modern approach (4th ed.). Pearson Education.
11.Singh, A., Kumar, R., & Sharma, P. (2023). Predictive analytics for residential fire safety using machine learning algorithms. Journal of Safety Research, 86, 112–125.
12.Wang, X., Chen, Y., & Zhao, L. (2023). Machine learning approaches for fire risk assessment: A comparative study. Expert Systems with Applications, 213, Article 118932.
13.Zhang, Y., Wang, H., & Liu, J. (2022). Deep learning-based fire detection and recognition using convolutional neural networks. Fire Safety Journal, 128, Article 103542.