Acta Photonica Sinica, Volume. 50, Issue 9, 0906003(2021)
Optical Fiber Perimeter Intrusion Pattern Recognition Based on 1D-CNN
Fig. 1. Schematic diagram of line-based Sagnac interference structure
Fig. 2. The intervention signal
Fig. 3. Structure of convolution neural network
Fig. 4. Schematic diagram of the experiment system
Fig. 5. Six types of demodulated signal and their power spectrum
Fig. 6. Six kernels after training
Fig. 7. Mel filters
Fig. 8. Features extracted by MFCC method
Fig. 9. Cutting signal after convolution
Fig. 10. Branch tapping signal after convolution
Fig. 11. Cutting features after batch normalized
Fig. 12. Branch tapping features after batch normalized
|
Get Citation
Copy Citation Text
Houdan YU, Qiushi MI, Dong ZHAO, Qian XIAO. Optical Fiber Perimeter Intrusion Pattern Recognition Based on 1D-CNN[J]. Acta Photonica Sinica, 2021, 50(9): 0906003
Category: Fiber Optics and Optical Communications
Received: Jan. 22, 2021
Accepted: Mar. 25, 2021
Published Online: Oct. 22, 2021
The Author Email: XIAO Qian (ychunww@163.com)