TY - GEN
T1 - Compressed-domain Data Classification for Distributed Acoustic Sensing System
AU - Shen, Xingliang
AU - Li, Jialong
AU - Wu, Zhengting
AU - Dang, Hong
AU - Chen, Jinna
AU - Shao, Liyang
AU - Liu, Huanhuan
AU - Shum, Perry Ping
AU - Wu, Huan
AU - Zhu, Kun
AU - Li, Yujia
AU - Zheng, Hua
AU - Lu, Chao
N1 - Funding Information:
ACKNOWLEDGMENT This project is supported from Stable Support Program for Higher Education Institutions from Shenzhen Science, Technology Innovation Commission (20200925162216001); Special Funds for the Major Fields of Colleges and Universities by the Department of Education of Guangdong Province (2021ZDZX1023); Guangdong Basic and Applied Basic Research Foundation (2021B1515120013); Open Fund of State Key Laboratory of Information Photonics and Optical Communications (Beijing University of Posts and Telecommunications, No. IPOC2020A002), Natural Science Foundation of Guangdong Province (No. 2022A1515011434). The Open Projects Foundation of State Key Laboratory of Optical Fiber and Cable Manufacture Technology (No. SKLD2105)
Publisher Copyright:
© 2022 IEEE.
PY - 2022/11
Y1 - 2022/11
N2 - One of the challenges in distributed acoustic sensing (DAS) system is how to transmit, store, and process massive streams of data. In this work, we propose a novel classification method in compressed-domain for DAS system Our method compresses the signal to reduce the data size and classify the different vibration events using compressed signal directly. We experimentally verified that 90% classification accuracy can be achieved on a four-class classification task with only 30% of original data size. Classification accuracy under different SNRs and measurement ratios are also investigated in this work.
AB - One of the challenges in distributed acoustic sensing (DAS) system is how to transmit, store, and process massive streams of data. In this work, we propose a novel classification method in compressed-domain for DAS system Our method compresses the signal to reduce the data size and classify the different vibration events using compressed signal directly. We experimentally verified that 90% classification accuracy can be achieved on a four-class classification task with only 30% of original data size. Classification accuracy under different SNRs and measurement ratios are also investigated in this work.
KW - Compressive Sensing
KW - DAS
KW - Distributed Acoustic Sensing
KW - Distributed Fibre sensing
UR - http://www.scopus.com/inward/record.url?scp=85153853576&partnerID=8YFLogxK
U2 - 10.1109/ACP55869.2022.10088818
DO - 10.1109/ACP55869.2022.10088818
M3 - Conference article published in proceeding or book
AN - SCOPUS:85153853576
T3 - Asia Communications and Photonics Conference, ACP
SP - 108
EP - 110
BT - 2022 Asia Communications and Photonics Conference, ACP 2022 and International Conference on Information Photonics and Optical Communications, IPOC 2022
PB - Optica Publishing Group (formerly OSA)
T2 - 2022 Asia Communications and Photonics Conference, ACP 2022 and International Conference on Information Photonics and Optical Communications, IPOC 2022
Y2 - 5 November 2022 through 8 November 2022
ER -