A Multi-Sensor Fire Detection Method based on Trend Predictive BiLSTM Networks
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Artificial intelligence techniques have improved fire-detection methods; however, false alarms still occur. Conventional methodsdetect fires using current sensors, which can lead to detection errors due to temporary environmental changes or noise. Thus, fire-detection methods must include a trend analysis of past information. We propose a deep-learning-based fire detection method using multisensor data and Kendall's tau. The proposed system used a BiLSTM model to predict fires using pre-processed multi-sensor data andextracted trend information. Kendall's tau indicates the trend of a time-series data as a score; therefore, it is easy to obtain a target pattern. The experimental results showed that the proposed system with trend values recorded an accuracy of 99.93% for BiLSTM and GRUmodels in a 20-tap moving average filter and 40% fire threshold. Thus, the proposed trend approach is more accurate than that of conventional approaches.
Abstract
Artificial intelligence techniques have improved fire-detection methods; however, false alarms still occur. Conventional methodsdetect fires using current sensors, which can lead to detection errors due to temporary environmental changes or noise. Thus, fire-detection methods must include a trend analysis of past information. We propose a deep-learning-based fire detection method using multisensor data and Kendall's tau. The proposed system used a BiLSTM model to predict fires using pre-processed multi-sensor data andextracted trend information. Kendall's tau indicates the trend of a time-series data as a score; therefore, it is easy to obtain a target pattern. The experimental results showed that the proposed system with trend values recorded an accuracy of 99.93% for BiLSTM and GRUmodels in a 20-tap moving average filter and 40% fire threshold. Thus, the proposed trend approach is more accurate than that of conventional approaches.
참고문헌 (11)
- B. Sarwar, "An intelligent fire warning application using IoT and an adaptive neuro-fuzzy inference system", Sens., 19(14), pp.3150(1)~3150(18) (2019)
- L. Han, "A new method of mixed gas identification based on a convolutional neural network for time series classification", Sens., 19(9), pp.1960(1)~1960(23) (2019)
- S. Saponara, "Real-time video fire", smoke detection based on CNN in antifire surveillance systems, 2021, pp.18, 889~900
- P. Li, "Image fire detection algorithms based on convolutional neural networks", Case Stud. Therm. Eng., 19, pp.100625~ (2020)
- K. Yan, "Feature selection and analysis on correlated gas sensor data with recursive feature elimination", Sens. Actuators B Chem., 212, pp.353~363 (2015)
- B. S. Freeman, "Forecasting air quality time series using deep learning", J. Air Waste Manag. Assoc., 68(8), pp.866~886 (2018)
- L. Xiong, "Improved support vector regression recursive feature elimination based on intragroup representative feature sampling(IRFS-SVR-RFE)for processing correlated gas sensor data", Sens. Actuators B Chem., 419, pp.136395~ (2024)
- M. Nakip, "Recurrent trend predictive neural network for multi-sensor fire detection", IEEE Access, 9, pp.84204~84216 (2021)
- L. Wu, "Multi-sensor data fusion algorithm for indoor fire early warning based on BP neural network", Inf., 12(2), pp.59(1)~59(12) (2021)
- S. Kim, "LSTM-based early fire detection system using small amount data", J. Semicond. Display Technol., 23(1), pp.110~116 (2024)
- W. Xu, "Spectrum sensing for cognitive radio based on Kendall's tau in the presence of non-Gaussian impulsive noise", Digit. Signal Process., 123, pp.103443~ (2022)