A Hybrid Deep Learning Model for Robust and Real-Time Fire Detection

Fire outbreaks pose serious threats to human life, property, and infrastructure, while conventional detection
systems often suffer from false alarms and reduced performance under challenging environmental conditions.
This study proposes a hybrid deep learning-based fire detection model that integrates ResNet50 and MobileViT
for effective spatial and contextual feature extraction. YOLOv8 is employed to detect fire and smoke using
adaptive confidence thresholds, improving detection reliability under varying conditions. To further enhance
robustness, multimodal sensor fusion incorporating infrared, thermal, gas, and temperature sensors is
implemented, with Kalman filtering applied to reduce sensor noise and improve measurement stability.
Generative Adversarial Networks (GANs) are also used to generate synthetic fire scenarios to address limitations
associated with insufficient training data. The proposed system is designed for real-time deployment on edge
computing platforms, including Raspberry Pi and Jetson Nano, while LoRaWAN enables long-range alert
transmission in low-connectivity environments. Experimental results demonstrate an accuracy of 97.6% and
precision of 96.1%, indicating the effectiveness of the proposed approach for reliable real-time fire detection. The
system offers potential applications in residential, industrial, and other high-risk environments.

Avazov, K., Hyun, A. E., Sami, A. A., Khaitov, A., Abdusalomov, A. B., & Cho, Y. I. (2023). Forest fire detection
and notification method based on AI and IoT approaches. Future Internet, 15(2), 61.
https://doi.org/10.3390/fi15020061
Frizzi, S., Bouchouicha, M., Ginoux, J.-M., Moreau, E., & Sayadi, M. (2021). Convolutional neural network for smoke
and fire semantic segmentation. IET Image Processing, 15(3), 634–647.
https://doi.org/10.1049/ipr2.12046
Gaur, A., Singh, A., Kumar, A., Kulkarni, K. S., Lala, S., Kapoor, K., Srivastava, V., Kumar, A., &
Mukhopadhyay, S. C. (2019). Fire sensing technologies: A review. IEEE Sensors Journal, 19(9), 31913202. Journal
Gocmen, R., Cibuk, M., & Akin, E. (2024). Comparative analysis of deep learning algorithms in fire detection.
Balkan of Electrical https://doi.org/10.17694/bajece.1533966
& Computer Engineering, 12(3), 255–261.
Hanif, M. K. M. (2023). AI-driven transformation in fire safety: A comprehensive study on AI-integrated fire
alarm and detection systems. International Journal of Science and Research (IJSR), 12(8), 125–126.
https://doi.org/10.21275/SR23727132310
Karishma, S., Suresh, K., Sireesha, B., & Hussain, S. A. (2019). AI-based fire detection and control system.
Journal of Engineering Science Publications, 10(11), 456–463. http://jespublication.com/
Kumar, R., Kumar, A., & Saikia, P. (2022). Deforestation and forests degradation impacts on the environment. In
Environmental degradation: Challenges and strategies for mitigation (pp. 19–46). Springer International
Publishing.
Lee, H., Chung, J. H., Chung, H., Kim, J. H., Yoo, Y., Lim, G. H., & Ruy, W. S. (2024). AI-enhanced fire detection
and suppression system for autonomous ships. International Journal of Naval Architecture and Ocean
Engineering, 16, 100628. https://doi.org/10.1016/j.ijnaoe.2024.100628
Marandi, A. K. (2018). Artificial intelligence (AI) fire detection system: A review. Journal of Emerging
Technologies and Innovative Research (JETIR), 5(9), 234–239. https://www.jetir.org/
Raihan, A. (2023). A review of the global climate change impacts, adaptation strategies, and mitigation options
in the socio-economic and environmental sectors. Journal of Environmental Science and Economics,
2(3), 36–58.
Remmelzwaal, L. (2023). An AI-based early fire detection system utilizing HD cameras and real-time image
analysis. Artificial Intelligence and Applications, XX(XX), 1–5.
Sathishkumar, V. E., Cho, J., Subramanian, M., & Naren, O. S. (2023). Forest fire and smoke detection using
deep learning-based learning without forgetting. Fire Ecology, 19(9). https://doi.org/10.1186/s42408
022-00165-0
Sinchai, A., Pumanee, P., & Lomwong, R. (2024, November). Enhanced fire detection using deep learning and
heat signatures. In 2024 12th International Conference on Control, Mechatronics and Automation
(ICCMA) (pp. 261–266). IEEE.
Surabhi, K. S., & Babu, A. (2024). Fire detection using AI. International Journal for Multidisciplinary Research
(IJFMR), 6(5), 1–8. https://www.ijfmr.com/
Vasconcelos, R. N., Franca Rocha, W. J., Costa, D. P., Duverger, S. G., Santana, M. M. D., Cambui, E. C., &
Cordeiro, C. L. (2024). Fire detection with deep learning: A comprehensive review. Land, 13(10), 1696.
Yang, S., Huang, Q., & Yu, M. (2024). Advancements in remote sensing for active fire detection: A review of
datasets and methods. Science of the Total Environment, 173273.