Translator Disclaimer
Paper
12 March 2020 Pattern recognition of fiber disturbance based on support vector machine in polarization optical time domain reflectometry
Author Affiliations +
Proceedings Volume 11436, 2019 International Conference on Optical Instruments and Technology: Optical Sensors and Applications; 114360Y (2020) https://doi.org/10.1117/12.2551736
Event: 2019 International Conference on Optical Instruments and Technology, 2019, Beijing, China
Abstract
Aiming at improving the signal processing capability of polarization optical time domain reflectometry (POTDR), a recognition method mainly based on the feature extraction and supported vector machine (SVM) is proposed. Apart from locating the certain place of interruptions, this method can help us identify different kinds of intrusion events. Firstly, we preprocess the signal by using an average filter and setting a proper threshold for it. Secondly, the signal is transformed into various kinds of time-domain features and frequency-domain features for the subsequent classification. Finally, the SVM of the system is trained with initial signals so it can discriminate events represented by new signal accurately. Our experiment results show the effectiveness of this method, and it can work well with high accuracy, fast response speed and low cost.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Menghao Li, Jing Gu, Xiaosong Luo, Bohang Xiong, Jingzeng Li, Feng Wang, and Rongrong Dou "Pattern recognition of fiber disturbance based on support vector machine in polarization optical time domain reflectometry", Proc. SPIE 11436, 2019 International Conference on Optical Instruments and Technology: Optical Sensors and Applications, 114360Y (12 March 2020); https://doi.org/10.1117/12.2551736
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top