IoT-based fire detection: A comparative study of machine learning techniques

Abstract

Fires that cannot be detected quickly become uncontrollable. The fires that start to spread uncontrollably pose a significant danger to humans and natural life. Especially in public and crowded areas, fires can lead to possible loss of life and massive property damage. Because of this, it is necessary to detect fires as accurately and quickly as possible. Smoke detectors used with Internet of Things (IoT) technology can exchange data with each other. In this study, data collected from two different types of IoT-based smoke detectors were processed using machine learning algorithms. The k-Nearest Neighbor (k-NN), Multilayer Perceptron (MLP), Radial Basis Function (RBF) Network, Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF), and Logistic Model Tree (LMT) algorithms were used. The data obtained from the smoke detectors were processed using machine learning algorithms to create a highly successful model design. The aim of the study is to design an artificial intelligence-based system that enables the early detection of fires occurring both indoors and outdoors.

Keywords

• Machine Learning
• Fire Detection System
• IoT-Based Systems
• K-Fold Cross Validation

IoT-tabanlı yangın tespiti: Makine öğrenmesi tekniklerinin karşılaştırmalı çalışması

Öz

Hızlı bir şekilde tespit edilemeyen yangınlar kontrolsüz hale gelmektedir. Kontrolsüz biçimde yayılmaya başlayan yangınlar ise insan hayatına ve doğal yaşama büyük tehlike oluşturmaktadır. Özellikle halka açık ve kalabalık olan alanlarda başlayan yangınların olası can kayıplarına ve büyük maddi hasarlara yol açtığı görülmektedir. Bu nedenle yangınları mümkün olduğunca doğru ve hızlı bir şekilde tespit etmek büyük önem taşımaktadır. Nesnelerin İnterneti (IoT) teknolojisi ile birlikte kullanılan duman detektörleri birbirlerine veri akışı gerçekleştirebilmektedir. Bu çalışmada IoT-Tabanlı iki farklı tür duman detektöründen toplanan veriler makine öğrenmesi algoritmaları kullanarak işlenmiştir. Çok Katmanlı Algılayıcı (MLP), K-En Yakın Komşu (K-NN), Radyal Tabanlı Fonksiyon (RBF) Ağları, Naive Bayes (NB), Karar Ağacı (DT), Rastgele Orman (RF) ve Lojistik Model Ağacı (LMT) algoritmaları kullanılmıştır. Duman detektörlerinden elde edilen veriler makine öğrenmesi algoritmalarında işlenerek yüksek başarıya sahip bir model tasarımı sağlanmıştır. Çalışma sonucunda hem kapalı alanlarda hem de dış mekanlarda oluşan yangınların erken tespitinin mümkün olacağı bir sistem tasarımı hedeflenmektedir.

Anahtar Kelimeler

• Makine Öğrenmesi
• Yangın Tespit Sistemi
• IoT-Tabanlı Sistemler
• K-Katlı Çapraz Doğrulama

Kaynakça

1. K. Mehta, S. Sharma, and D. Mishra, Internet-of-Things enabled forest fire detection system, 2021 Fifth International Conference on I-SMAC (IoT in Social Mobile Analytics and Cloud), pp. 20-23, Palladam, India, 2021.
2. J. Lu, J. Guo, Z. Jian, X. Xu, Optimal Allocation of Fire Extinguishing Equipment for a Power Grid Under Widespread Fire Disasters, IEEE Access, vol.6, pp. 6382-6389, 2018. https://doi.org/10.1109/ACCESS.20 17.2788893.
3. Y. Hirohara, T. Ishida, N. Uchida and Y. Shibata, Proposal of a Disaster Information Cloud System for Disaster Prevention and Reduction, WAINA 2017, pp. 664-667, 2017.
4. Ö. Doğan, O. Şahin, and E. Karaaslan, Digital twin based disaster management system proposal: DT-DMS. Journal of Emerging Computer Technologies, 1(2), 25-30, 2021.
5. E. N. Soysal, H. Gürkan, and E. Yavşan, IoT Band: A wearable sensor system to track vital data and location of missing or earthquake victims. International Journal of Computational and Experimental Science and Engineering, 9(3), 213-218, 2023. https://doi.org/10 .22 399/ijcesen.1317040.
6. J. Qiu, J. Wang, T. He, B. Chen and X. Chen, Research on intelligent fire rating evaluation and rapid rescue plan optimization strategy, 2020 International Conference on Urban Engineering and Management Science (ICUEMS), pp. 446-453, 2020.
7. K. Muhammad, J. Ahmad, Z. Lv, P. Bellavista, P. Yang, and S. W. Baik, Efficient deep CNN-based fire detection and localization in video surveillance applications. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(7), 1419-1434, 2018. https://doi.org/10.1109/TSMC.2018.2830099.
8. A. Sungheetha and R. Sharma, Real time monitoring and fire detection using internet of things and cloud based drones. Journal of Soft Computing Paradigm (JSCP), 2(03), 168-174, 2020. https://doi.org/10.36548 /jscp.2020.3.004.

9. A. F. Önal, B. Ulver, A. Durusoy, and Erkmen, B., Intelligent wireless sensor networks for early fire warning system. Electrica, 2020. https://doi.10.26650 /electrica.2019.19019.
10. T. Çelik, H. Özkaramanlı, and H. Demirel, Fire and smoke detection without sensors: Image processing based approach, 2007 15th European Signal Processing Conference, pp. 1794-1798, 2007.
11. F. M. A. Hossain, Y. Zhang, C. Yuan, and C. Y. Su, Wildfire flame and smoke detection using static image features and artificial neural network, 2019 1st International Conference on Industrial Artificial Intelligence (IAI), pp. 1-6, 2019.
12. K. Chen, Y. Cheng, H. Bai, C. Mou and Y. Zhang, Research on image fire detection based on support vector machine, 2019 9th International Conference on Fire Science and Fire Protection Engineering (ICFSFPE), pp. 1-7, 2019.
13. N. A. Mwedzi, N. I. Nwulu and S. L. Gbadamosi, Machine learning applications for fire detection in a residential building, 2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS), pp. 1-4, 2019.
14. N. Chowdhury, D. R. Mushfiq and A. E. Chowdhury, Computer vision and smoke sensor based fire detection system, 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), pp. 1-5, 2019.
15. M. Nakıp and C. Güzeliş, Multi-sensor fire detector based on trend predictive neural network, 2019 11th International Conference on Electrical and Electronics Engineering (ELECO), pp. 600-604, 2019.
16. M. Nakip, C. Güzelíş and O. Yildiz, Recurrent Trend predictive neural network for multi-sensor fire detection, in IEEE Access, vol. 9, pp. 84204-84216, 2021. https://doi.org/10.1109/ACCESS.2021.3087736.
17. Kaggle. Smoke Detection Dataset. Available from: https://www.kaggle.com/datasets/deepcontractor/smoke-detection-dataset September 04, 2022.
18. A. A. Ayrancı, S. Atay and T. Yıldırım, Speaker accent recognition using machine learning algorithms, 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), pp. 1-6, Istanbul, Turkey, 2020. https://doi.org/10.1109/ASYU50717.20 20.9259902.
19. J. D. Rodriguez, A. Perez and J. A. Lozano, Sensitivity analysis of k-fold cross validation in prediction error estimation in IEEE transactions on pattern analysis and machine intelligence, vol. 32, no. 3, 569-575, 2010. https://doi.10.1109/10.1109/TPAMI.2009.187.
20. F. Murtagh, Multilayer perceptrons for classification and regression, Neurocomputing, 2(5-6), 183-197, 1991.
21. M. K. Alsmadi, K. B. Omar, S. A. Noah and I. Almarashdah, performance comparison of multi-layer perceptron (back propagation, delta rule and perceptron) algorithms in neural networks, 2009 IEEE International Advance Computing Conference, pp. 296-299, Patiala, India, 2009.
22. T. Cover and P. Hart, Nearest neighbor pattern classification, in IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21-27, January 1967. https://doi.10.1109/TIT.1967.1053964.
23. J. Moody and C. J. Darken, Fast learning in networks of locally-tuned processing units, Neural computation, vol. 1, no. 2, pp. 281-294, 1989. https://doi.10.1162/ neco.1989.1.2.281.
24. R. Irina. An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence, vol. 3, no. 22, pp. 41-46, 2001.
25. S. R. Safavian, and D. Landgrebe, A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics, 21(3), 660-674, 1991. https://doi.org/10.1109/21.97458.
26. L. Breiman, Random forests. Machine learning, 45(1), 2001. https://doi.org/10.1109/COMST.2015.2494502.
27. H. Han, X. Guo, and H. Yu, Variable selection using mean decrease accuracy and mean decrease gini based on random forest. In 2016 7th IEEE international conference on software engineering and service science, pp. 219-224, 2016.
28. D. L. Gupta, A. K. Malviya, and S. Satyendra, Performance analysis of classification tree learning algorithms. International Journal of Computer Applications, 2012. https://doi.org/10.1007/978-3-319-03844-5_9.
29. J. D. Rodriguez, A. Perez, and J. A. Lozano, Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE transactions on pattern analysis and machine intelligence, 32(3), 569-575, 2009. https://doi. org/ 10.1109/TPAMI.2009.187.
30. S. Garcia, A. Fernández, J. Luengo, and F. Herrera, A study of statistical techniques and performance measures for genetics-based machine learning: accuracy and interpretability. Soft Computing, 13, 959-977, 2009. https://doi.org/10.1007/s00500-008-0392-y.
31. T. Chai, and R. R. Draxler, Root mean square error (RMSE) or mean absolute error (MAE) Arguments against avoiding RMSE in the literature. Geoscientific model development, 7(3), 1247-1250, 2014. https://doi .org /10.5194/gmd-7-1247-2014.