Comparative Analysis of Four Machine Learning Algorithms for Smoke Detection Using SMOTE-Rebalanced Sensor Data
DOI:
10.33395/sinkron.v10i1.15546Keywords:
Smoke Detection; Sensor Data; KNN; Decision Tree; Random Forest; Gradient Boosting; SMOTEAbstract
Smoke detection plays a critical role in preventing fire-related hazards, particularly in intelligent monitoring and early warning systems. Conventional smoke sensors often exhibit limited responsiveness in dynamic environmental conditions, prompting the adoption of IoT-based sensor data combined with machine learning techniques. This study presents a comparative evaluation of four supervised classification algorithms, K-Nearest Neighbors (KNN), Decision Tree, Random Forest, and Gradient Boosting, using the Smoke Detection Dataset from Kaggle. The methodology integrates SMOTE to address class imbalance and Z-score normalization for feature standardization. Hyperparameter tuning was performed using GridSearchCV with 5-fold cross-validation, and model performance was assessed based on accuracy and execution time. Experimental results show that KNN achieved the highest accuracy (98.33%) with the lowest execution time (0.0327 s), whereas Decision Tree recorded the lowest accuracy (84.17%) but remained computationally fast (0.0406 s). Random Forest and Gradient Boosting demonstrated strong predictive capability (97.22% and 96.94%, respectively), but at higher computational costs (1.4338 s and 8.3819 s, respectively). Almost all models achieved perfect scores (1.00) for precision, recall, and F1-score following SMOTE-based balancing, except KNN which obtained slightly lower values (0.99). The findings indicate a trade-off between predictive performance and computational efficiency, suggesting that lightweight models such as KNN are better suited for real-time IoT-based smoke detection. In contrast, ensemble models may be more appropriate for backend analysis. This research contributes an integrated evaluation framework that combines data rebalancing, multi-model benchmarking, and time-based performance analysis, providing practical insights for the development of responsive and scalable early smoke detection systems.
Downloads
References
Alharbi, Fayez, Lahcen Ouarbya, and Jamie A. Ward. 2022. “Comparing Sampling Strategies for Tackling Imbalanced Data in Human Activity Recognition.” Sensors 22(4):1–20. doi: 10.3390/s22041373.
Bhamra, Jaspreet Kaur, Shreyas Anantha Ramaprasad, Siddhant Baldota, Shane Luna, Eugene Zen, Ravi Ramachandra, Harrison Kim, Chris Schmidt, Chris Arends, Jessica Block, Ismael Perez, Daniel Crawl, Ilkay Altintas, Garrison W. Cottrell, and Mai H. Nguyen. 2023. “Multimodal Wildland Fire Smoke Detection.” Remote Sensing 15(11). doi: 10.3390/rs15112790.
Carletti, Vincenzo, Antonio Greco, Alessia Saggese, and Bruno Vento. 2024. “A Smart Visual Sensor for Smoke Detection Based on Deep Neural Networks.” Sensors 24(14):1–17. doi: 10.3390/s24144519.
Deepa, K. R., A. S. Chaitra, K. Jhansi, R. D. Anitha Kumari, P. Ashwini Kumari, and Mallikarjun M. Kodabagi. 2022. “Development of Fire Detection Surveillance Using Machine Learning & IoT.” MysuruCon 2022 - 2022 IEEE 2nd Mysore Sub Section International Conference (February). doi: 10.1109/MysuruCon55714.2022.9972725.
Erkmen, Burcu, and Ahmet Aytuğ Ayrancı. 2024. “IoT-Based Fire Detection: A Comparative Study of Machine Learning Techniques.” Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi 13(4):1298–1307. doi: 10.28948/ngumuh.1444349.
Fulazzaky, Tahira, Asep Saefuddin, and Agus Mohamad Soleh. 2024. “Evaluating Ensemble Learning Techniques for Class Imbalance in Machine Learning: A Comparative Analysis of Balanced Random Forest, SMOTE-RF, SMOTEBoost, and RUSBoost.” Scientific Journal of Informatics 11(4):969–80. doi: 10.15294/sji.v11i4.15937.
Hairani, Hairani, Khurniawan Eko Saputro, and Sofiansyah Fadli. 2020. “K-Means-SMOTE for Handling Class Imbalance in the Classification of Diabetes with C4.5, SVM, and Naive Bayes.” Jurnal Teknologi Dan Sistem Komputer 8(2):89–93. doi: 10.14710/jtsiskom.8.2.2020.89-93.
Handoko, Chanavaro Bayu, and Christian Sri Kusuma Aditya. 2025. “Penerapan Teknik SMOTE Dalam Mengatasi Imbalance Data Penyakit Diabetes Menggunakan Algoritma ANN.” Smart Comp: Jurnalnya Orang Pintar Komputer 14(1):13–20. doi: 10.30591/smartcomp.v14i1.7045.
He, Luhao, Yongzhang Zhou, Lei Liu, Yuqing Zhang, and Jianhua Ma. 2025. “Research and Application of Deep Learning Object Detection Methods for Forest Fire Smoke Recognition.” Scientific Reports 15(1):1–20. doi: 10.1038/s41598-025-98086-w.
Jamal, Muhammad Hassan, Abdulwahab Alazeb, Shahid Allah Bakhsh, Wadii Boulila, Syed Aziz Shah, Aizaz Ahmad Khattak, and Muhammad Shahbaz Khan. 2025. “Optimizing Fire Safety: Reducing False Alarms Using Advanced Machine Learning Techniques.” ArXiv Preprint ArXiv:2503.09960 1–12.
Julian, James, Annastya Bagas Dewantara, and Fitri Wahyuni. 2024. “Design of Smoke Detection System Using Deep Learning and Sensor Fusion with Recursive Feature Elimination Cross-Validation.” IAES International Journal of Artificial Intelligence 13(2):1658–67. doi: 10.11591/ijai.v13.i2.pp1658-1667.
Li, Xihao, Gui Zhang, Sanqing Tan, Zhigao Yang, and Xin Wu. 2023. “Forest Fire Smoke Detection Research Based on the Random Forest Algorithm and Sub-Pixel Mapping Method.” Forests 14(3). doi: 10.3390/f14030485.
Liu, Jixue, Jiuyong Li, Stefan Peters, and Liang Zhao. 2024. “A Transformer Boosted UNet for Smoke Segmentation in Complex Backgrounds in Multispectral LandSat Imagery.” Remote Sensing Applications: Society and Environment 36:1–17. doi: 10.1016/j.rsase.2024.101283.
Rajoli, Hossein, Sahand Khoshdel, Fatemeh Afghah, and Xiaolong Ma. 2024. “FlameFinder: Illuminating Obscured Fire Through Smoke With Attentive Deep Metric Learning.” IEEE Transactions on Geoscience and Remote Sensing 62(Dml):1–11. doi: 10.1109/TGRS.2024.3440880.
Syukron, Muhamad, Rukun Santoso, and Tatik Widiharih. 2020. “Perbandingan Metode Smote Random Forest Dan Smote Xgboost Untuk Klasifikasi Tingkat Penyakit Hepatitis C Pada Imbalance Class Data.” Jurnal Gaussian 9(3):227–36. doi: 10.14710/j.gauss.v9i3.28915.
Talukder, Md Alamin, Selina Sharmin, Md Ashraf Uddin, Md Manowarul Islam, and Sunil Aryal. 2024. “MLSTL-WSN: Machine Learning-Based Intrusion Detection Using SMOTETomek in WSNs.” International Journal of Information Security 23(3):2139–58. doi: 10.1007/s10207-024-00833-z.
Tao, Wu, Fan Honghui, Zhu HongJin, You CongZhe, Zhou HongYan, and Huang XianZhen. 2021. “Intrusion Detection System Combined Enhanced Random Forest With Smote Algorithm.” EURASIP Journal on Advances in Signal Processing 1–30.
Vasconcelos, Rodrigo N., Washington J. S. Franca Rocha, Diego P. Costa, Soltan G. Duverger, Mariana M. M. d. Santana, Elaine C. B. Cambui, Jefferson Ferreira-Ferreira, Mariana Oliveira, Leonardo da Silva Barbosa, and Carlos Leandro Cordeiro. 2024. “Fire Detection with Deep Learning: A Comprehensive Review.” Land 13(10). doi: 10.3390/land13101696.
Wang, Ming, Liangcun Jiang, Peng Yue, Dayu Yu, and Tianyu Tuo. 2023. “FASDD: An Open-Access 100,000-Level Flame and Smoke Detection Dataset for Deep Learning in Fire Detection.” Earth System Science Data Discussions 00103(November):1–26.
Zhang, Ziyang, Lingye Tan, and Tiong Lee Kong Robert. 2024. “An Improved Fire and Smoke Detection Method Based on YOLOv8n for Smart Factories.” Sensors 24(15). doi: 10.3390/s24154786.
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2025 Marcus Liecero, Robet, Jackri Hendrik
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
Muhammad Khoiruddin harahap
