Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neural networks
Abstract
This paper reports on the use of machine learning to delineate data harnessed by fiber-optic distributed acoustic sensors (DAS) using fiber with enhanced Rayleigh backscattering to recognize vibration events induced by human locomotion. The DAS used in this work is based on homodyne phase-sensitive optical time-domain reflectometry (φ-OTDR). The signal-to-noise ratio (SNR) of the DAS was enhanced using femtosecond laser-induced artificial Rayleigh scattering centers in single-mode fiber cores. Both supervised and unsupervised machine-learning algorithms were explored to identify people and specific events that produce acoustic signals. Using convolutional deep neural networks, the supervised machine learning scheme achieved over 76.25% accuracy in recognizing human identities. Conversely, the unsupervised machine learning scheme achieved over 77.65% accuracy in recognizing events and human identities through acoustic signals. Through integrated efforts on both sensor device innovation and machine learning data analytics, this paper shows that the DAS technique can be an effective security technology to detect and to identify highly similar acoustic events with high spatial resolution and high accuracies.
- Authors:
- Publication Date:
- Research Org.:
- Idaho National Laboratory (INL), Idaho Falls, ID (United States); National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1730962
- Alternate Identifier(s):
- OSTI ID: 1816801; OSTI ID: 2222440
- Report Number(s):
- INL/JOU-20-57461-Revision-0
Journal ID: ISSN 2045-2322; 21014; PII: 77147
- Grant/Contract Number:
- FE00029063; AC07-05ID14517; 89243318CFE000003
- Resource Type:
- Published Article
- Journal Name:
- Scientific Reports
- Additional Journal Information:
- Journal Name: Scientific Reports Journal Volume: 10 Journal Issue: 1; Journal ID: ISSN 2045-2322
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United Kingdom
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; 98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION; Rayleigh enhancement; distributed acoustic sensing; phase-sensitive optical time-domain reflectometry; artificial intelligence; deep neural networks
Citation Formats
Peng, Zhaoqiang, Wen, Hongqiao, Jian, Jianan, Gribok, Andrei, Wang, Mohan, Huang, Sheng, Liu, Hu, Mao, Zhi-Hong, and Chen, Kevin P. Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neural networks. United Kingdom: N. p., 2020.
Web. doi:10.1038/s41598-020-77147-2.
Peng, Zhaoqiang, Wen, Hongqiao, Jian, Jianan, Gribok, Andrei, Wang, Mohan, Huang, Sheng, Liu, Hu, Mao, Zhi-Hong, & Chen, Kevin P. Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neural networks. United Kingdom. https://doi.org/10.1038/s41598-020-77147-2
Peng, Zhaoqiang, Wen, Hongqiao, Jian, Jianan, Gribok, Andrei, Wang, Mohan, Huang, Sheng, Liu, Hu, Mao, Zhi-Hong, and Chen, Kevin P. Thu .
"Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neural networks". United Kingdom. https://doi.org/10.1038/s41598-020-77147-2.
@article{osti_1730962,
title = {Identifications and classifications of human locomotion using Rayleigh-enhanced distributed fiber acoustic sensors with deep neural networks},
author = {Peng, Zhaoqiang and Wen, Hongqiao and Jian, Jianan and Gribok, Andrei and Wang, Mohan and Huang, Sheng and Liu, Hu and Mao, Zhi-Hong and Chen, Kevin P.},
abstractNote = {This paper reports on the use of machine learning to delineate data harnessed by fiber-optic distributed acoustic sensors (DAS) using fiber with enhanced Rayleigh backscattering to recognize vibration events induced by human locomotion. The DAS used in this work is based on homodyne phase-sensitive optical time-domain reflectometry (φ-OTDR). The signal-to-noise ratio (SNR) of the DAS was enhanced using femtosecond laser-induced artificial Rayleigh scattering centers in single-mode fiber cores. Both supervised and unsupervised machine-learning algorithms were explored to identify people and specific events that produce acoustic signals. Using convolutional deep neural networks, the supervised machine learning scheme achieved over 76.25% accuracy in recognizing human identities. Conversely, the unsupervised machine learning scheme achieved over 77.65% accuracy in recognizing events and human identities through acoustic signals. Through integrated efforts on both sensor device innovation and machine learning data analytics, this paper shows that the DAS technique can be an effective security technology to detect and to identify highly similar acoustic events with high spatial resolution and high accuracies.},
doi = {10.1038/s41598-020-77147-2},
journal = {Scientific Reports},
number = 1,
volume = 10,
place = {United Kingdom},
year = {Thu Dec 03 00:00:00 EST 2020},
month = {Thu Dec 03 00:00:00 EST 2020}
}
https://doi.org/10.1038/s41598-020-77147-2
Works referenced in this record:
A Novel Fiber Optic Based Surveillance System for Prevention of Pipeline Integrity Threats
journal, February 2017
- Tejedor, Javier; Macias-Guarasa, Javier; Martins, Hugo
- Sensors, Vol. 17, Issue 2
Real-time activity identification in a smart FBG-based fiber-optic perimeter intrusion detection system
conference, October 2012
- Wu, Huijuan; Lu, Xianglin; Li, Shanshan
- OFS2012 22nd International Conference on Optical Fiber Sensor, SPIE Proceedings
FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing
journal, September 2017
- Pan, Shijia; Yu, Tong; Mirshekari, Mostafa
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 1, Issue 3
Feasibility study of the automated detection and localization of underground tunnel excavation using Brillouin optical time domain reflectometer
conference, May 2009
- Klar, Assaf; Linker, Raphael
- SPIE Defense, Security, and Sensing, SPIE Proceedings
Long Fiber-Optic Perimeter Sensor: Signature Analysis
conference, January 2007
- Madsen, Christi; Bae, Taehan; Atkins, Robert
- Conference on Lasers and Electro-Optics/Quantum Electronics and Laser Science Conference and Photonic Applications Systems Technologies
A Sagnac interferometer sensor system for intrusion detection and localization
conference, August 2004
- McAulay, Alastair D.; Wang, Jian
- Defense and Security, SPIE Proceedings
Rayleigh scatter based order of magnitude increase in distributed temperature and strain sensing by simple UV exposure of optical fibre
journal, June 2015
- Loranger, Sébastien; Gagné, Mathieu; Lambin-Iezzi, Victor
- Scientific Reports, Vol. 5, Issue 1
Recognition of a Phase-Sensitivity OTDR Sensing System Based on Morphologic Feature Extraction
journal, June 2015
- Sun, Qian; Feng, Hao; Yan, Xueying
- Sensors, Vol. 15, Issue 7
Real Field Deployment of a Smart Fiber-Optic Surveillance System for Pipeline Integrity Threat Detection: Architectural Issues and Blind Field Test Results
journal, February 2018
- Tejedor, Javier; Ahlen, Carl H.; Gonzalez-Herraez, Miguel
- Journal of Lightwave Technology, Vol. 36, Issue 4
Wavelet Denoising Method for Improving Detection Performance of Distributed Vibration Sensor
journal, April 2012
- Qin, Zengguang; Chen, Liang; Bao, Xiaoyi
- IEEE Photonics Technology Letters, Vol. 24, Issue 7
Blue Rose perimeter defense and security system
conference, May 2006
- Blackmon, F.; Pollock, J.
- Defense and Security Symposium, SPIE Proceedings
Spectrum Analysis and Convolutional Neural Network for Automatic Modulation Recognition
journal, June 2019
- Zeng, Yuan; Zhang, Meng; Han, Fei
- IEEE Wireless Communications Letters, Vol. 8, Issue 3
Fiber optic intrusion sensing based on coherent optical time domain reflectometry
conference, June 2007
- Vdovenko, V. S.; Gorshkov, B. G.
- SPIE Proceedings
Unattended ground sensor based on fiber BRAGG grating technology
conference, May 2005
- Zhang, Yan; Li, Sanguo; Yin, Zhifan
- Defense and Security, SPIE Proceedings
Spectrum Analysis of EEG Signals Using CNN to Model Patient’s Consciousness Level Based on Anesthesiologists’ Experience
journal, January 2019
- Liu, Quan; Cai, Jifa; Fan, Shou-Zen
- IEEE Access, Vol. 7
Perimeter security system based on fiber optic disturbance sensor
conference, January 2008
- Lan, Tian; Zhang, Chunxi; Li, Lijing
- Advanced Sensor Systems and Applications III, Proceedings of SPIE
Indoor Person Identification through Footstep Induced Structural Vibration
conference, January 2015
- Pan, Shijia; Wang, Ningning; Qian, Yuqiu
- Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications - HotMobile '15
Multiple-Octave-Spanning Vibration Sensing Based on Simultaneous Vector Demodulation of 499 Fizeau Interference Signals from Identical Ultra-Weak Fiber Bragg Gratings Over 2.5 km
journal, January 2018
- Li, Yi; Qian, Li; Zhou, Ciming
- Sensors, Vol. 18, Issue 2
Advances in Fiber-optic Distributed Acoustic Sensors
conference, July 2018
- He, Zuyuan; Liu, Qingwen; Chen, Dian
- 2018 23rd Opto-Electronics and Communications Conference (OECC)
High-temperature capabilities and limitations of fiber grating sensors
conference, September 1994
- Morey, William W.; Meltz, Gerald; Weiss, Joseph M.
- 10th Optical Fibre Sensors Conference, SPIE Proceedings
Multiplexable high-temperature stable and low-loss intrinsic Fabry-Perot in-fiber sensors through nanograting engineering
journal, January 2020
- Wang, Mohan; Yang, Yang; Huang, Sheng
- Optics Express, Vol. 28, Issue 14
128km fully-distributed high-sensitivity fiber-optic intrusion sensor with 15m spatial resolution
conference, January 2014
- Peng, Fei; Peng, Zheng-Pu; Jia, Xin-Hong
- Optical Fiber Communication Conference
Multi-scale wavelet decomposition and its application in distributed optical fiber fences
conference, July 2015
- Wu, Huijuan; Zhang, Linqiang; Qian, Ya
- Fifth Asia Pacific Optical Sensors Conference, SPIE Proceedings
Polarization discrimination in a phase-sensitive optical time-domain reflectometer intrusion-sensor system
journal, January 2005
- Juarez, Juan C.; Taylor, Henry F.
- Optics Letters, Vol. 30, Issue 24
Improved demodulation scheme for fiber optic interferometers using an asymmetric 3×3 coupler
journal, January 1997
- Zhiqiang Zhao, ; Demokan, M. S.; MacAlpine, M.
- Journal of Lightwave Technology, Vol. 15, Issue 11
Distributed Optical Fiber Sensors with Ultrafast Laser Enhanced Rayleigh Backscattering Profiles for Real-Time Monitoring of Solid Oxide Fuel Cell Operations
journal, August 2017
- Yan, Aidong; Huang, Sheng; Li, Shuo
- Scientific Reports, Vol. 7, Issue 1
A symmetric 3x3 coupler based demodulator for fiber optic interferometric sensors
conference, December 1991
- Brown, David A.
- Fiber Optic and Laser Sensors IX
Distributed OTDR-interferometric sensing network with identical ultra-weak fiber Bragg gratings
journal, January 2015
- Wang, Chen; Shang, Ying; Liu, Xiao-Hui
- Optics Express, Vol. 23, Issue 22