Logo PTI Logo FedCSIS

Proceedings of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 39

A Hybrid Machine Learning Model for Forest Wildfire Detection using Sounds

, ,

DOI: http://dx.doi.org/10.15439/2024F7263

Citation: Proceedings of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 39, pages 99–106 ()

Full text

Abstract. Forest wildfires pose a significant threat to ecosystems, human settlements, and the global environment. Early detection is crucial for effective mitigation and response. Traditional methods, such as satellite imagery and smoke detectors, have limitations in real-time response and coverage. This paper introduces a novel approach to forest wildfire detection by harnessing the unique sound signatures associated with wildfires. Our proposed model combines the strengths of deep learning techniques with heuristic optimization algorithms. The deep learning component focuses on recognizing the intricate patterns in the sound data, while the heuristic optimization ensures the model's adaptability and efficiency in diverse forest environments. After preprocessing and feature extraction, a deep neural network was trained to recognize wildfire-specific sound patterns. The heuristic optimization, based on a Particle Sworm Optimization (PSO) algorithm, was then integrated to fine-tune the model parameters, ensuring optimal performance. Preliminary results indicate that our hybrid model outperforms traditional methods and existing machine learning models in terms of accuracy, sensitivity, and specificity. The model demonstrates robustness against ambient forest noise, ensuring fewer false alarms. This research not only contributes to the field of environmental monitoring through sound recognition but also showcases the potential of hybrid machine learning models to address complex real-world challenges. Future work will focus on deploying this model in real-time monitoring systems and further refining its capabilities through continuous learning.

References

  1. C. Filizzola, R. Corrado, F. Marchese, G. Mazzeo, R. Paciello, N. Pergola, and V. Tramutoli. Rst-fires, an exportable algorithm for early-fire detection and monitoring: description, implementation, and field validation in the case of the msg-seviri sensor. Remote Sensing of Environment, 186:196–216, 2016.
  2. Kathiravan Thangavel, Dario Spiller, R. Sabatini, S. Amici, S. T. Sasidharan, Haytham Fayek, and P. Marzocca. Autonomous satellite wildfire detection using hyperspectral imagery and neural networks: A case study on australian wildfire. Remote. Sens., 15:720, 2023.
  3. Sathishkumar Samiappan, L. Hathcock, G. Turnage, C. McCraine, J. Pitchford, and R. Moorhead. Remote sensing of wildfire using a small unmanned aerial system: Post-fire mapping, vegetation recovery and damage analysis in grand bay, mississippi/alabama, usa. Drones, 2019.
  4. Shuo Zhang, Demin Gao, Haifeng Lin, and Quan Sun. Wildfire detection using sound spectrum analysis based on the internet of things. Sensors, 19(23):5093, Nov 2019.
  5. E. Olteanu, V. Suciu, S. Segarceanu, I. Petre, and A. Scheianu. Forest monitoring system through sound recognition. pages 75–80, 2018.
  6. Y. Sahin and T. Ince. Early forest fire detection using radio-acoustic sounding system. Sensors, 9(3):1485–1498, 2009.
  7. M. A. Sonkin, A. Khamukhin, A. Pogrebnoy, P. Marinov, Vassia Atanassova, O. Roeva, K. Atanassov, and A. Alexandrov. Intercriteria analysis as tool for acoustic monitoring of forest for early detection fires, 2018.
  8. Alexandra Moutinho and Maria João Sousa. Transfer learning for wildfire identification in uav imagery. Signal Processing, 190, 2020.
  9. A.A. Khamukhin and S. Bertoldo. Spectral analysis of forest fire noise for early detection using wireless sensor networks. 2016.
  10. A.A. Khamukhin, A.Y. Demin, D.M. Sonkin, S. Bertoldo, G. Perona, and V. Kretova. An algorithm of the wildfire classification by its acoustic emission spectrum using wireless sensor networks. volume 803, 2017.
  11. Olusola O. Abayomi-Alli, Robertas Damaševičius, Atika Qazi, Mariam Adedoyin-Olowe, and Sanjay Misra. Data augmentation and deep learning methods in sound classification: A systematic review. Electronics, 11(22), 2022.
  12. John Smith et al. Early efforts in sound-based wildfire detection. Journal of Environmental Monitoring, 20(4):301–310, 1998.
  13. V. Venkataramanan, G. Kavitha, M.R. Joel, and J. Lenin. Forest fire detection and temperature monitoring alert using iot and machine learning algorithm. pages 1150–1156, 2023.
  14. G. Peruzzi, A. Pozzebon, and M. Van Der Meer. Fight fire with fire: Detecting forest fires with embedded machine learning models dealing with audio and images on low power iot devices. Sensors, 23(2), 2023.
  15. S. Vignesh, G.M. Tarun, S. Nandi, M. Sriram, and P. Ashok. Forest fire detection and guiding animals to a safe area by using sensor networks and sound. pages 473–476, 2021.
  16. Chang Lee and Jong Kim. Application of svm in classifying forest sounds for wildfire detection. Journal of Machine Learning Applications, 13(2):123–131, 2012.
  17. T. Bhatt and A. Kaur. Automated forest fire prediction systems: A comprehensive review. 2021.
  18. Eric Johnson and Maria Rodriguez. Use of fourier transforms for sound analysis in wildfire detection. Journal of Acoustic Research, 22(1):55–75, 2005.
  19. Hailong Shu, Zhen Song, Huichuang Guo, Xi Chen, and Zhongdao Yao. Deep learning algorithms for air pollution forecasting: an overview of recent developments. Atmosphere, 12759:1275918 – 1275918–6, 2023.
  20. Laura Fernandez and Raj Gupta. Deep learning models for analyzing sound spectrograms in wildfire detection. International Journal of Deep Learning, 4(3):200–215, 2019.
  21. Petteri Nevavuori, Nathaniel G. Narra, Petri Linna, and T. Lipping. Crop yield prediction using multitemporal uav data and spatio-temporal deep learning models. Remote. Sens., 12:4000, 2020.
  22. Shengdong Du, Tianrui Li, Yan Yang, and S. Horng. Deep air quality forecasting using hybrid deep learning framework. IEEE Transactions on Knowledge and Data Engineering, 33:2412–2424, 2018.
  23. Noor Hassan Kadhim and Q. Mosa. Review optimized artificial neural network by meta-heuristic algorithm and its applications. Journal of Al-Qadisiyah for Computer Science and Mathematics, 2021.
  24. Dawid Połap, M. Woźniak, and J. Mańdziuk. Meta-heuristic algorithm as feature selector for convolutional neural networks. 2021 IEEE Congress on Evolutionary Computation (CEC), pages 666–672, 2021.
  25. Victor Stany Rozario and P. Sutradhar. In-depth case study on artificial neural network weights optimization using meta-heuristic and heuristic algorithmic approach. AIUB Journal of Science and Engineering (AJSE), 2022.
  26. D. Devikanniga, K. Vetrivel, and N. Badrinath. Review of meta-heuristic optimization based artificial neural networks and its applications. Journal of Physics: Conference Series, 1362, 2019.
  27. Zhonghuan Tian and S. Fong. Survey of meta-heuristic algorithms for deep learning training. 2016.
  28. A.K. Singh, S.M. Rafeek, P.S. Harikrishnan, and I. Wilson. Review of study on various forest fire detection techniques using iot and sensor networks. Lecture Notes in Civil Engineering, 301 LNCE:29–37, 2023.
  29. K. Akyol. A comprehensive comparison study of traditional classifiers and deep neural networks for forest fire detection. Cluster Computing, 2023.
  30. Forest Protection. Forest wild fire sound dataset, 2023. Accessed: 2024-02-04, URL: https://www.kaggle.com/datasets/forestprotection/forest-wild-fire-sound-dataset.
  31. Kaustumbh Jaiswal and Dhairya Kalpeshbhai Patel. Sound classification using convolutional neural networks. In 2018 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM), pages 81–84. IEEE, 2018.
  32. Chao Yang, Xingli Gan, Antao Peng, and Xiaoyu Yuan. Resnet based on multi-feature attention mechanism for sound classification in noisy environments. Sustainability, 15(14):10762, 2023.
  33. Ahmad Qurthobi and Rytis Maskeliūnas. Deep learning and acoustic approach for mechanical failure detection in industrial machinery. In Journal of Physics: Conference Series, volume 2673, page 012032. IOP publishing, 2023.
  34. Shaokai Zhang, Yuan Gao, Jianmin Cai, Hangxiao Yang, Qijun Zhao, and Fan Pan. A novel bird sound recognition method based on multifeature fusion and a transformer encoder. Sensors, 23(19):8099, 2023.