A $k$ -Nearest Neighbor Algorithm-Based Near Category Support Vector Machine Method for Event Identification of $\varphi$ -OTDR

In order to reduce the nuisance alarm rate (NAR) for the phase-sensitive optical time-domain reflectometer (<inline-formula> <tex-math notation="LaTeX">$\varphi $ </tex-math></inline-formula>-OTDR), we propose an event identification method based on the near category support vector machines (NC-SVM), which extends the current binary SVM classifier to multi-class problems by using k-nearest neighbor (kNN) algorithm. Five kinds of disturbance events, including watering, climbing, knocking, pressing, and false disturbance event, can be effectively identified for 25.05 km long <inline-formula> <tex-math notation="LaTeX">$\varphi $ </tex-math></inline-formula>-OTDR system. The experimental results demonstrate that the average identification rate of five disturbance events exceeds 94%, the identification time is 0.55s, and the NAR is 5.62%. Compared with the one against one multi-class SVM classifier, our proposed method has the distinguished advantage of higher identification rate, shorter identification time, and lower NAR.

[1]  Yan Feng,et al.  Combination of Phase-Sensitive OTDR and Michelson Interferometer for Nuisance Alarm Rate Reducing and Event Identification , 2016, IEEE Photonics Journal.

[2]  Huchuan Lu,et al.  Spectral-spatial K-Nearest Neighbor approach for hyperspectral image classification , 2018, Multimedia Tools and Applications.

[3]  Jiangang Lu,et al.  Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in φ-OTDR , 2018 .

[4]  Ming Bao,et al.  Pattern recognition based on enhanced multifeature parameters for vibration events in φ‐OTDR distributed optical fiber sensing system , 2017 .

[5]  K. Loparo,et al.  Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling : A method for bearing prognostics , 2007 .

[6]  Lu Liu,et al.  An oil and gas pipeline pre-warning system based on Φ-OTDR , 2014, Other Conferences.

[7]  S. Martin-Lopez,et al.  Early detection of pipeline integrity threats using a smart fiber optic surveillance system: the PIT-STOP project , 2015, International Conference on Optical Fibre Sensors.

[8]  Chris H. Q. Ding,et al.  Multi-class protein fold recognition using support vector machines and neural networks , 2001, Bioinform..

[9]  Danwei Wang,et al.  Application of BW-ELM model on traffic sign recognition , 2014, Neurocomputing.

[10]  Madan Gopal,et al.  A comparison study on multiple binary-class SVM methods for unilabel text categorization , 2010, Pattern Recognit. Lett..

[11]  Keith Harman,et al.  A novel long-range perimeter security sensor based on hybrid michelson and Mach-Zehnder interferometers , 2016, 2016 IEEE International Carnahan Conference on Security Technology (ICCST).

[12]  Qian Sun,et al.  Recognition of a Phase-Sensitivity OTDR Sensing System Based on Morphologic Feature Extraction , 2015, Sensors.

[13]  Huijuan Wu,et al.  Feature extraction and identification in distributed optical-fiber vibration sensing system for oil pipeline safety monitoring , 2017, Photonic Sensors.

[14]  Érick O. Rodrigues,et al.  Combining Minkowski and Cheyshev: New distance proposal and survey of distance metrics using k-nearest neighbours classifier , 2018, Pattern Recognit. Lett..

[15]  Ming-Yang Su,et al.  Using clustering to improve the KNN-based classifiers for online anomaly network traffic identification , 2011, J. Netw. Comput. Appl..

[16]  Bernhard Wilhelm Roth,et al.  Structural Health Monitoring Using Textile Reinforcement Structures with Integrated Optical Fiber Sensors , 2017, Sensors.

[17]  Yage Zhan,et al.  A high performance distributed sensor system with multi-intrusions simultaneous detection capability based on phase sensitive OTDR , 2015 .

[18]  Zuyuan He,et al.  Practical Pattern Recognition System for Distributed Optical Fiber Intrusion Monitoring System Based on Phase-Sensitive Coherent OTDR , 2015 .

[19]  Hongnan Li,et al.  Pipeline corrosion and leakage monitoring based on the distributed optical fiber sensing technology , 2018, Measurement.

[20]  Pedro Corredera,et al.  Distributed Vibration Sensing Over 125 km With Enhanced SNR Using Phi-OTDR Over a URFL Cavity , 2015, Journal of Lightwave Technology.

[21]  Cesare Svelto,et al.  Runways ground monitoring system by phase-sensitive optical-fiber OTDR , 2017, 2017 IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace).

[22]  Mohamed Elhoseny,et al.  Recognizing human activity in mobile crowdsensing environment using optimized k-NN algorithm , 2018, Expert Syst. Appl..

[23]  Hugo F. Martins,et al.  Toward Prevention of Pipeline Integrity Threats Using a Smart Fiber-Optic Surveillance System , 2016, Journal of Lightwave Technology.

[24]  Philip S. Yu,et al.  Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[25]  Xiaohan Sun,et al.  Vibration pattern recognition and classification in OTDR based distributed optical-fiber vibration sensing system , 2014, Smart Structures.

[26]  Yunjiang Rao,et al.  A novel intrusion signal processing method for phase-sensitive optical time-domain reflectometry (Φ-OTDR) , 2014, Other Conferences.

[27]  Dong Wang,et al.  Real-time distributed oil/gas pipeline security pre warning system based on Φ-OTDR , 2017, 2017 Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL).

[28]  Qinghua Hu,et al.  Neighborhood classifiers , 2008, Expert Syst. Appl..