Maximum Eigenvalue-based detection in fiber-optic distributed acoustic sensors applications

被引:0
|
作者
Masued, Nagat [1 ]
Ozkan, Erkan [1 ]
Erkorkmaz, Tayfun [1 ]
机构
[1] SAMM Teknol AS, Gebze Organize Sanayi Bolgesi GOSB, Ihsandede Cd 800,Sok 802, TR-41400 Gebze, Turkey
关键词
Anomaly Detection; Convolutions Neural Networks; Distributed Acoustic Sensing; Maximum Eigenvalue;
D O I
10.1117/12.2638479
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Anomaly detection in large-scale time-series data acquired by Fiber Optic Distributed Acoustic Sensors (DAS) used for perimeter security and pipeline monitoring is a critical problem in machine learning. However, because of the vast amounts of data to process, it can be time and energy intensive. This study looks at how to reduce detection time and computing costs for this use case. In order to distinguish the acoustic event of interest from the noise and establish a binary detection threshold, we employ a Maximum Eigenvalue Detection (MED) approach in conjunction with a Random Matrix Theory (RMT) precept, namely the Tracy-Widom limit. A pipeline of signal processing techniques is used to assist the algorithm, beginning with applying a Moving Average (MA) filter to remove amplitude swings on the signal, which is represented by a data matrix, and then subsampling it to obtain uncorrelated signals among the subsequent columns to reduce the number of data processed. As a result, we can detect events of interest in less time. Following that, low-pass filtering is employed to eliminate low-frequency coefficients induced by various sorts of environmental and seismic events. Following normalization, the MED method is used to each of the Wishart matrices, which are generated by segmenting the data stream into equal small sub-matrices. RMT is used to set a threshold with a false alarm rate of 0.01 (FAR). The data columns matching to the selected MED values are then injected into a Convolutions Neural Network (CNN) to capture and detect the event of interest. When compared to using solely the CNN, the optimal results from our approach, MED followed by a CNN anomaly detection process, demonstrate a faster detection rate for events in security application.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Advances in Fiber-optic Distributed Acoustic Sensors
    He, Zuyuan
    Liu, Qingwen
    Chen, Dian
    [J]. 23RD OPTO-ELECTRONICS AND COMMUNICATIONS CONFERENCE (OECC2018), 2018,
  • [2] Listen with Fiber-optic Distributed Acoustic Sensors
    Liu, Q.
    Chen, D.
    He, Z.
    [J]. OPTICS, PHOTONICS AND LASERS (OPAL 2019), 2019, : 77 - 79
  • [3] Distributed Fiber-Optic Sensors for Vibration Detection
    Liu, Xin
    Jin, Baoquan
    Bai, Qing
    Wang, Yu
    Wang, Dong
    Wang, Yuncai
    [J]. SENSORS, 2016, 16 (08)
  • [4] Fiber-optic distributed acoustic sensors (DAS) and applications in railway perimeter security
    He, Zuyuan
    Liu, Qingwen
    Fan, Xinyu
    Chen, Dian
    Wang, Shuai
    Yang, Guangyao
    [J]. ADVANCED SENSOR SYSTEMS AND APPLICATIONS VIII, 2018, 10821
  • [5] FIBER-OPTIC ACOUSTIC SENSORS
    LYAMSHEV, LM
    SMIRNOV, YY
    [J]. SOVIET PHYSICS ACOUSTICS-USSR, 1983, 29 (03): : 169 - 181
  • [6] FIBER-OPTIC ACOUSTIC SENSORS
    MUNIR, Q
    WEBER, HP
    [J]. HELVETICA PHYSICA ACTA, 1984, 57 (04): : 526 - 527
  • [7] Advanced fiber-optic acoustic sensors
    Teixeira J.G.V.
    Leite I.T.
    Silva S.
    Frazão O.
    [J]. Photonic Sensors, 2014, 4 (3) : 198 - 208
  • [8] Broadband Fiber-Optic Acoustic Sensors
    Wei, Heming
    Gong, Zhe
    Wu, Wenjing
    Che, Jiawei
    Zhang, Liang
    Pang, Fufei
    Wang, Tingyun
    [J]. JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (12) : 4033 - 4041
  • [9] Stretchable distributed fiber-optic sensors
    Bai, Hedan
    Li, Shuo
    Barreiros, Jose
    Tu, Yaqi
    Pollock, Clifford R.
    Shepherd, Robert F.
    [J]. SCIENCE, 2020, 370 (6518) : 848 - +
  • [10] DISTRIBUTED FIBER-OPTIC SENSOR FOR DETECTION AND LOCALIZATION OF ACOUSTIC VIBRATIONS
    Sifta, Radim
    Munster, Petr
    Sysel, Petr
    Horvath, Tomas
    Novotny, Vit
    Krajsa, Ondrej
    Filka, Miloslav
    [J]. METROLOGY AND MEASUREMENT SYSTEMS, 2015, 22 (01) : 111 - 118