Forest fire smoke recognition based on convolutional neural network

Abstract

Traditional fire smoke detection methods mostly rely on manual algorithm extraction and sensor detection; however, these methods are slow and expensive to achieve discrimination. We proposed an improved convolutional neural network (CNN) to achieve fast analysis. The improved CNN can be used to liberate manpower. The network does not require complicated manual feature extraction to identify forest fire smoke. First, to alleviate the computational pressure and speed up the discrimination efficiency, kernel principal component analysis was performed on the experimental data set. To improve the robustness of the CNN and to avoid overfitting, optimization strategies were applied in multi-convolution kernels and batch normalization to improve loss functions. The experimental analysis shows that the CNN proposed in this study can learn the feature information automatically for smoke images in the early stages of fire automatically with a high recognition rate. As a result, the improved CNN enriches the theory of smoke discrimination in the early stages of a forest fire.

Keywords

Forest fire smoke / Convolutional neural network / Image classification / Kernel principal component analysis

References

[1] Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK. Medical image analysis using convolutional neural networks: a review. J Med Syst, 2018 42 11 226

[2] Cirean D, Meier U, Masci J, Schmidhuber J. Multi-column deep neural network for traffic sign classification. Neural Netw, 2012, 32: 333-338.

[3] Deng W, Fang Y, Xu Z, Hu J. Facial landmark localization by enhanced convolutional neural network. Neurocomputing, 2018, 273: 222-229.

[4] Ding J, Chen B, Liu H, Huang M. Convolutional neural network with data augmentation for sar target recognition. IEEE Geoence Remote Sens Lett, 2016, 13(3): 364-368.

[5] Gursel S, Ehsan A. Host-based misuse intrusion detection using PCA feature extraction and kNN classification algorithms. Intell Data Anal, 2018, 22(5): 1101-1114.

[6] Hussein Harith A. Face recognition system based on kernel principle component analysis and fuzzy-support vector machine. Tikrit J Pure Sci, 2018, 23(1): 134-138.

[7] Ignatov A. Convolutional neural networks: an overview and application in radiology. Appl Soft Comput, 2018, 62: 915-992.

[8] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst, 2012, 25(2): 1097-1105.

[9] Matlani P, Shrivastava M. An efficient algorithm proposed for smoke detection in video using hybridfeature selection techniques. Eng Technolo Appl Sci Res, 2019, 9(2): 3939-3944.

[10] Ozer I, Ozer Z, Findik O. Noise robust sound event classification with convolutional neural network. Neurocomputing, 2018, 272: 505-512.

[11] Pandya B, Cosma G, Alani AA, Taherkhani A, Bharadi V, Mcginnity TM (2018) Fingerprint classification using a deep convolutional neural network. International Conference on Information Management. IEEE.

[12] Poria S, Cambria E, Gelbukh A. Aspect extraction for opinion mining with a deep convolutional neural network. Knowl Based Syst, 2016, 108: 42-49.

[13] Prema CE, Vinsley SS, Suresh S. Multi feature analysis of smoke in YUV color space for early forest fire detection. Fire Technol, 2016, 52(5): 1319-1342.

[14] Rocco I, Relja A, Sivic J. Convolutional neural network architecture for geometric matching. IEEE Trans Pattern Anal Mach Intell, 2019, 41(11): 2553-2567.

[15] Shafar MZ, Wirayuda TAB, Sthevanie F. Early smoke detection on video using wavelet energy. Indones J Comput (Indo-JC), 2017, 2(2): 79-90.

[16] Shiokawa Y, Date Y, Kikuchi J. Application of kernel principal component analysis and computational machine learning to exploration of metabolites strongly associated with diet. Sci Rep, 2018 8 1 3426

[17] Widodo A, Yang BS. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process, 2007, 21(6): 2560-2574.

[18] Yuan F. Video-based smoke detection with histogram sequence of LBP and LBPV pyramids. Fire Saf J, 2011, 46(3): 132-139.