Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)

<Previous Article In Volume
Next Article In Volume>

Sustainable Fire Detection in Smart Cities Using ResNet101V2 and Optimized Gradient-Boosting Method

Authors
Akshat Gaurav1, *, Brij B. Gupta2, Nadia Nedjah3, Kwok Tai Chui4
1Ronin Institute, Montclair, NJ, USA
2Department of Computer Science and Information Engineering, Asia University, Taichung, 413, Taiwan
3State University of Rio de Janeiro, Rio de Janeiro, Brazil
4Hong Kong Metropolitan University, Hong Kong SAR, China
*Corresponding author. Email: akshat.gaurav@ieee.org
Corresponding Author
Akshat Gaurav
Available Online 26 May 2025.
DOI
10.2991/978-94-6463-716-8_64How to use a DOI?
Keywords
FFire Detection; Sustainability; Smart Cities; ResNet101V2; Gradient Boosting; Sea-Horse Optimization
Abstract

Fire detection is a critical component in ensuring the safety of smart cities, where timely and accurate identification of fire incidents can prevent widespread damage. In this context, this work provides a sustainable and updated fire detection system for smart cities utilizing ResNet101V2 for feature extraction and Gradient Boosting enhanced using the Sea-Horse Optimization (Sea HO) method. With a precision of 0.96 and a recall of 0.95, it attained a better accuracy of 95\% than often used models such CatBoost, XGBoost, and SVM. Hyperparameter tuning was greatly aided by SeaHO, thereby improving the performance and resilience of the model. With minimum false alarms and great fire detection accuracy, the suggested method is perfect for real-time fire detection and guarantees safety in metropolitan surroundings.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
Series
Advances in Intelligent Systems Research
Publication Date
26 May 2025
ISBN
978-94-6463-716-8
ISSN
1951-6851
DOI
10.2991/978-94-6463-716-8_64How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Akshat Gaurav
AU  - Brij B. Gupta
AU  - Nadia Nedjah
AU  - Kwok Tai Chui
PY  - 2025
DA  - 2025/05/26
TI  - Sustainable Fire Detection in Smart Cities Using ResNet101V2 and Optimized Gradient-Boosting Method
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 866
EP  - 878
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_64
DO  - 10.2991/978-94-6463-716-8_64
ID  - Gaurav2025
ER  -