Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

LSTM-based Early Fire Detection System using Small Amount Data

  • Seonhwa Kim (Smart Network Research Center, Korea Electronics Technology Institute) ;
  • Kwangjae Lee (Department of Information Security Engineering, Sangmyung University)
  • Received : 2024.03.15
  • Accepted : 2024.03.20
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Despite the continuous advancement of science and technology, fire accidents continue to occur without decreasing over time, so there is a constant need for a system that can accurately detect fires at an early stage. However, because most existing fire detection systems detect fire in the early stage of combustion when smoke is generated, rapid fire prevention actions may be delayed. Therefore we propose an early fire detection system that can perform early fire detection at a reasonable cost using LSTM, a deep learning model based on multi-gas sensors with high selectivity in the early stage of decomposition rather than the smoke generation stage. This system combines multiple gas sensors to achieve faster detection speeds than traditional sensors. In addition, through window sliding techniques and model light-weighting, the false alarm rate is low while maintaining the same high accuracy as existing deep learning. This shows that the proposed fire early detection system is a meaningful research in the disaster and engineering fields.

Keywords

References

  1. Wong, Cynthia A., "Advances in labor analgesia." International journal of women's health, 2010, pp. 139-154.
  2. The World Fire Statistics for 2019. https://www.ctif.org/sites/default/files/2021-06/CTIF_Report26_KOREA.pdf (07.06.2021).
  3. Nazir, Amril, et al., "Early fire detection: a new indoor laboratory dataset and data distribution analysis," Fire, vol. 5, no. 1, 2022.
  4. GAUR, Anshul, et al., "Fire sensing technologies: A review," IEEE Sensors Journal, vol. 19, no. 9, 2019, pp. 3191-3202.
  5. Muhammad, Khan, et al., "Convolutional neural networks based fire detection in surveillance videos," IEEE Access, vol. 6, 2018, pp. 18174-18183.
  6. Li, Pu, and Wangda Zhao, "Image fire detection algorithms based on convolutional neural networks," Case Studies in Thermal Engineering, vol. 19, 2020, 100625.
  7. T. H. Lee, C.-S. Park, "Real-Time Fire Detection Method Using YOLOv8," Journal of the Semiconductor & Display Technology, vol. 22, no. 2, 2023.
  8. I.-H. Park, et al., "Deep-learning based In-situ Monitoring and Prediction System for the Organic Light Emitting Diode," Journal of the Semiconductor & Display Technology, vol. 19, no. 4, 2020, pp. 126-129.
  9. H. Ahn, Y.-H Lee, "A Research of CNN-based Object Detection for Multiple Object Tracking in Image : A Research of CNN-based Object Detection for Multiple Object Tracking in Image," Journal of the Semiconductor & Display Technology, vol. 18, no. 3, 2019, pp. 110-114.
  10. Y.-H. Lee, Y. Kim, "Comparison of CNN and YOLO for Object Detection," Journal of the Semiconductor & Display Technology, vol. 19, no. 1, 2020, pp. 85-92.
  11. Fonollosa, Jordi, Ana Solorzano, and Santiago Marco, "Chemical sensor systems and associated algorithms for fire detection: A review," Sensors, vol. 18, no. 2, 2018, 553.
  12. Wu, Lesong, Lan Chen, and Xiaoran Hao, "Multi-sensor data fusion algorithm for indoor fire early warning based on BP neural network," Information, vol. 12, no. 2, 2021, 59.
  13. Saeed, Faisal, et al., "Convolutional neural network based early fire detection," Multimedia Tools and Applications, vol. 79, no. 13, 2020, pp. 9083-9099.
  14. Vorwerk, Pascal, et al., "Classification in Early Fire Detection Using Multi-Sensor Nodes-A Transfer Learning Approach," Sensors, vol. 24, no. 5, 2024, 1428.
  15. K. N. Kim, "Principles and applications of gas sensors," Monthly Instrumentation Technology, 2004.
  16. D. Sarangi, et al., "Characterization studies of diamond-like carbon films grown using a saddle-field fast-atom-beam source," Journal of Vacuum Science & Technology A: Vacuum, Surfaces, and Films, vol. 18, no. 5, 2000, pp. 2302-2311.
  17. Batzill, Matthias, "Surface science studies of gas sensing materials: SnO2," Sensors, vol. 6, no. 10, 2006, pp. 1345-1366.
  18. H.-W. Jang, "Development trends of semiconductor gas sensors," Electrical & Electronic Materials, vol. 24, no. 1, 2011, pp. 34-42.
  19. Y. B. Yahmed, et al., "ADAPTIVE SLIDING WINDOW ALGORITHM FOR WEATHER DATA SEGMENTATION," Journal of Theoretical & Applied Information Technology, vol. 80, no. 2, 2015.
  20. K. Lee, et al., "Highly sensitive sensors based on metal-oxide nanocolumns for fire detection," Sensors, vol. 17, no. 2, 2017, 303.
  21. B. J. Kang, H.-C. Cho, "Development of a Deep Learning Prediction Model to Recognize Dangerous Situations in a Gas-use Environment," Journal of the Semiconductor & Display Technology, vol. 21, no. 1, 2022, pp. 132-135.
  22. M. J. Kim, et al., "Study on the Failure Diagnosis of Robot Joints Using Machine Learning," Journal of the Semiconductor & Display Technology, vol. 22, no. 4, 2023, pp. 113-118.