Fire Smoke Identification Based on Genetic Algorithm Optimizing BP Neural Network
Keywords:
Genetic Algorithm, BP Neural Network, Home Fire Recognition, Intelligent Recognition SystemAbstract
With the continuous improvement of people's living standards, the frequency of home fires is increasing. This paper proposes a method for identifying smoke-type fires involving image processing of monitoring screens. Suspected smoke areas are roughly identified based on the gray value of images. Then the local binary variance and the relative energy of high and low frequencies in suspected smoke areas are extracted using the LBP algorithm and wavelet transform algorithm. Using the collected fire smoke images, extract corresponding feature data using the algorithm in this article, and manually calibrate the fire label to obtain the corresponding training data. BP neural network is employed in this paper for smoke and fire recognition. However, under limited training data, the recognition results using only the neural network are poor, with experimental results showing a prediction accuracy of only 64.5% for the pure BP neural network. Given this situation, this paper utilizes a genetic algorithm to optimize the internal topology of the BP neural network. By encoding the weight thresholds of the network structure into binary code as population individuals of the genetic algorithm and performing continuous iterative optimization, experimental results demonstrate that the prediction accuracy of fire recognition by the optimized BP neural network is improved to 94%.
Downloads
References
S. Calderara, P. Piccinini, and R. Cucchiara, “Vision based smoke detection system using image energy and color information,” Machine Vision and Applications, vol. 22, no. 4, pp. 705–719, 2011.
A. L. P. De Ocampo, "Haar-CNN Cascade for Facial Expression Recognition," 2023 International Electrical Engineering Congress (iEECON), Krabi, Thailand, 2023, pp. 89-92, doi: 10.1109/iEECON56657.2023.10126902.
H. Kim, D. Ryu, and J. Park, “Smoke detection using GMM and adaboost,” International Journal of Computer and Communication Engineering, vol. 3, no. 2, pp. 123, 2014.
F. Yuan, Z. Fang, S. Wu, et al., “Real-time image smoke detection using staircase searching-based dual threshold AdaBoost and dynamic analysis,” IET Image Processing, vol. 9, no. 10, pp. 849–856, 2015.Fig. 23. Comparison Plot of Predicted and Actual Values
Y. Q. Zhao, Q. J. Li, and Z. Gu, “Early smoke detection of forest fire video using CS Adaboost algorithm,” Optik - International Journal for Light and Electron Optics, vol. 126, no. 19, pp. 2121–2124, 2015.
S. Ye, Z. Bai, H. Chen, et al., “An effective algorithm to detect both smoke and flame using color and wavelet analysis,” Pattern Recognition and Image Analysis, vol. 27, no. 1, pp. 131–138, 2017.
S. Frizzi, R. Kaabi, M. Bouchouicha, et al., Convolutional neural network for video fire and smoke detection, 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, 2016, pp. 877–882.
K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition, IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016, pp. 770–778.
C. Yuan, Z. Liu, and Y. Zhang, “Learning-based smoke detection for unmanned aerial vehicles applied to forest fire surveillance,” Journal of Intelligent & Robotic Systems, vol. 93, no. 1, pp. 337–349, 2019.
J. Zeng, Z. Lin, C. Qi, et al., “An Improved Object Detection Method Based On Deep Convolution Neural Network For Smoke Detection,” 2018 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 1, 2018, pp. 184–189.
Y. Lee and J. Shim, “False positive decremented research for fire and smoke detection in surveillance camera using spatial and temporal features based on deep learning,” Electronics, vol. 8, no. 10, pp. 1167, 2019.
S. Majid, F. Alenezi, S. Masood, et al., “Attention based CNN model for fire detection and localization in real-world images,” Expert Systems With Applications, vol. 189, pp. 116114, 2022.
Z. Ke, “A New Image Filtering Algorithm for Impulse Noise,” Fire Control and Command Control, 2011.
J. Li, K. Wang, and D. D. Zhang, “A new equation of saturation in RGB-to-HSI conversion for more rapidity of computing,” IEEE, 2002.
E. Welch, R. Moorhead, and J. K. Owens, “Image processing using the HSI color space,” Southeastcon '91, IEEE Proceedings of IEEE, 1991.
M. J. Thurley and V. Danell, “Fast Morphological Image Processing Open-Source Extensions for GPU Processing With CUDA,” IEEE Journal of Selected Topics in Signal Processing, vol. 6, no. 7, pp. 849-855, 2012.
W. H. Alobaidi, et al., “Face detection based on probability of amplitude distribution of local binary patterns algorithm,” IEEE, 2018.
X. P. Zeng, et al., “The Research of Using BP Neural Network in Prediction of Woods Fire Insurance Grade,” Journal of Chongqing University (Natural Science Edition), vol. 28, no. 1, pp. 73-76, 2005.
J. Zhou, W. Ma, and J. Miao, “Fire Risk Assessment of Transmission Line Based on BP Neural Network,” International Journal of Smart Home, vol. 8, no. 3, pp. 119-130, 2014.
C. Rocha, et al., “Calibration of Forest Fire Risk Combined Index - ICRIF,” 3rd EJIL - LAETA Young Researchers Meeting, 2015.
M. A. Matos, et al., “A Genetic Algorithm for Forest Firefighting Optimization,” International Conference on Computational Science and Its Applications, Springer, Cham, 2022.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
