An AI Enabled Predictive Fire Safety System Based on IoT and Embedded Intelligence
Keywords:
Fire Safety; IoT; Machine Learning; Embedded Systems; Predictive DetectionAbstract
This paper presents an AI-enabled predictive fire safety system based on Internet of Things (IoT) and embedded intelligence. The proposed system integrates multiple environmental sensors with an Arduino-based platform to enable early fire risk prediction and automated response. Real-time sensor data are transmitted to the ThingSpeak cloud platform, where machine learning models, including Linear Regression and Decision Tree classifiers, are applied for fire risk analysis. Based on prediction outcomes, the system activates alarms, controls suppression mechanisms, and sends emergency notifications via GSM. Experimental results from 100 controlled test scenarios validate the system's performance, achieving a predictive accuracy of approximately 92%. The integration of predictive logic successfully reduced false alarms by nearly 30% compared to traditional threshold-based systems, while maintaining an end-to-end response time of 2–3 seconds. The proposed system offers a cost-effective and scalable solution for smart fire safety applications.
References
[1] H. Alqourabah, A. Muneer, and S. M. Fati, “A smart fire detection system using iot technology with automatic water sprinkler.,” International Journal of Electrical & Computer Engineering (2088-8708), vol. 11, no. 4, 2021.
[2] M. M. Islam, N. Fatme, M. A. M. Hossain, and M. F. Haque, “Fireeye: An iot-based fire alarm and detection system for enhanced safety,” in Federated Deep Learning for Healthcare, pp. 160–169, CRC Press, 2024.
[3] Y. Bouzeraa, N. Bouchemal, S. Djaaboub, G. Hristov, and P. Zahariev, “Machine learning-based wildfire susceptibility mapping: A gisintegrated predictive framework,” Applied Sciences, vol. 15, no. 22, p. 12188, 2025.
[4] T. Khan, “A smart fire detector iot system with extinguisher class recommendation using deep learning,” IoT, vol. 4, no. 4, pp. 558–581, 2023.
[5] U. Dampage, L. Bandaranayake, R. Wanasinghe, K. Kottahachchi, and B. Jayasanka, “Forest fire detection system using wireless sensor networks and machine learning,” Scientific reports, vol. 12, no. 1, p. 46, 2022.
[6] J. Villa, F. Garc´ıa, R. Jover, V. Mart´ınez, and J. M. Armingol, “Intelligent infrastructure for traffic monitoring based on deep learning and edge computing,” Journal of Advanced Transportation, vol. 2024, no. 1, p. 3679014, 2024.
[7] R. Sowah, K. O. Ampadu, A. Ofoli, K. Koumadi, G. A. Mills, and J. Nortey, “Design and implementation of a fire detection and control system for automobiles using fuzzy logic,” in 2016 IEEE industry applications society annual meeting, pp. 1–8, IEEE, 2016.
[8] B. M. Yudistira, S. Widyasmoro, A. R. Ramadhan, and A. D. Muhammad, “Development of intelligent fire detection system using multisensor verification and machine learning-based visual camera integration for multi-floor building applications,” in 2025 5th International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), pp. 466–471, IEEE, 2025.
[9] Q. Liu, H. Chen, and D. Lin, “Research and optimization of a multilevel fire detection framework based on deep learning and classical pattern recognition techniques,” Scientific Reports, vol. 15, no. 1, p. 20364, 2025.
[10] L. Mu, Y. Yang, B. Wang, Y. Zhang, N. Feng, and X. Xie, “Edge computing-based real-time forest fire detection using uav thermal and color images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 6760–6771, 2025.
