A MCSVM-based high-efficiency events-discrimination method for ADMZI-distributed infrared fiber vibration sensor

This paper presents a multi-class support vector machine (MCSVM) based high-efficiency events discrimination method for asymmetric dual Mach-Zehnder interferometers (ADMZI) distributed infrared fiber vibration sensor. This method combined empirical mode decomposition (EMD), kurtosis characteristics with MCSVM, which can improve the recognition rate effectively. Filed experimental results demonstrate that the proposed method can discriminate four common invasive events (climbing the fence, knocking the cable, cutting the fence, and waggling the fence) with an average recognition rate above 90.9%, which can satisfy actual application requirements.

[1]  Elena Simona Lohan,et al.  Analysis of Kurtosis-Based LOS/NLOS Identification Using Indoor MIMO Channel Measurement , 2013, IEEE Transactions on Vehicular Technology.

[2]  J. Juarez,et al.  Distributed fiber-optic intrusion sensor system , 2005, Journal of Lightwave Technology.

[3]  Xiang Zhong,et al.  [Spectra and influences of Rayleigh and stimulated Brillouin scattering in fiber-optic distributed disturbance sensor]. , 2011, Guang pu xue yu guang pu fen xi = Guang pu.

[4]  J. de Vries.  A low cost fence impact classification system with neural networks , 2004, 2004 IEEE Africon. 7th Africon Conference in Africa (IEEE Cat. No.04CH37590).

[5]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[6]  X. Bao,et al.  Distributed optical fiber vibration sensor based on spectrum analysis of Polarization-OTDR system. , 2008, Optics express.

[7]  Lijing Li,et al.  Fiber-optic intrinsic distributed acoustic emission sensor for large structure health monitoring. , 2009, Optics letters.

[8]  Theodore Berger,et al.  Intelligent fence intrusion detection system: detection of intentional fence breaching and recognition of fence climbing , 2008, 2008 IEEE Conference on Technologies for Homeland Security.

[9]  Tao Wang,et al.  A Modified Empirical Mode Decomposition Algorithm in TDLAS for Gas Detection , 2014, IEEE Photonics Journal.

[10]  Kun Liu,et al.  Long-Range Distributed Fiber Vibration Sensor Using an Asymmetric Dual Mach–Zehnder Interferometers , 2016, Journal of Lightwave Technology.

[11]  Zhe Shen,et al.  An Improved Positioning Algorithm With High Precision for Dual Mach–Zehnder Interferometry Disturbance Sensing System , 2015, Journal of Lightwave Technology.

[12]  Tommy Geisler,et al.  Limits of applicability of polarization sensitive reflectometry. , 2011, Optics express.

[13]  A J Rogers,et al.  Polarization-optical time domain reflectometry: a technique for the measurement of field distributions. , 1981, Applied optics.

[14]  Min Zhang,et al.  Positioning Error Prediction Theory for Dual Mach–Zehnder Interferometric Vibration Sensor , 2011, Journal of Lightwave Technology.

[15]  Darryll J. Pines,et al.  Structural health monitoring using empirical mode decomposition and the Hilbert phase , 2006 .

[16]  Xiao-Hua Yu,et al.  An adaptive filtering approach for electrocardiogram (ECG) signal noise reduction using neural networks , 2013, Neurocomputing.

[17]  X. Bao,et al.  High Sensitivity Distributed Vibration Sensor Based on Polarization-Maintaining Configurations of Phase-OTDR , 2011, IEEE Photonics Technology Letters.

[18]  Xiaoyi Bao,et al.  Distributed Vibration Sensor Based on Coherent Detection of Phase-OTDR , 2010, Journal of Lightwave Technology.

[19]  Kun Liu,et al.  Long-range vibration sensor based on correlation analysis of optical frequency-domain reflectometry signals. , 2012, Optics express.