Hybrid Feature Extraction-Based Intrusion Discrimination in Optical Fiber Perimeter Security System

This paper proposes a hybrid feature extraction-based intrusion discrimination scheme for an optical fiber perimeter security system, which concurrently possesses high classification rate and high efficiency. The high classification rate lies in two aspects: On one hand, plentiful contents (including bandwidth segmentation in frequency domain, kurtosis in statistics, and the zero-crossing rate in time domain) are incorporated into the proposed hybrid feature vector; on the other hand, a configurable filter bank is adopted to reduce the intercoupling between features in the hybrid vector. The high efficiency also arises for two reasons: For one thing, the configurable filter bank works in a pipeline stream; for another, an efficient support vector machine is employed to classify hybrid vectors. Experiments demonstrated that the proposed scheme can accurately identify four common intrusions (fence climbing, knocking the cable, waggling, and fence cutting) with an average recognition rate higher than 94%. Moreover, the recognition efficiency is also high.

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

[2]  Moo K. Chung,et al.  Spatially augmented LPboosting for AD classification with evaluations on the ADNI dataset , 2009, NeuroImage.

[3]  Kun Liu,et al.  Event Discrimination of Fiber Disturbance Based on Filter Bank in DMZI Sensing System , 2016, IEEE Photonics Journal.

[4]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[5]  B. Eftekharnejad,et al.  The application of spectral kurtosis on Acoustic Emission and vibrations from a defective bearing , 2011 .

[6]  Kun Liu,et al.  Configurable Filter-Based Endpoint Detection in DMZI Vibration System , 2014, IEEE Photonics Technology Letters.

[7]  Deming Liu,et al.  Distributed fiber-optic vibration sensor using a ring Mach-Zehnder interferometer , 2008 .

[8]  Seedahmed S. Mahmoud,et al.  Real-time Distributed Fiber Optic Sensor for Security Systems: Performance, Event Classification and Nuisance Mitigation , 2012 .

[9]  Min Zhang,et al.  Positioning method for dual Mach-Zehnder interferometric submarine cable security system , 2010, Defense + Commercial Sensing.

[10]  Qizhen Sun,et al.  Distributed fiber-optic sensor with a ring Mach-Zehnder interferometer , 2007, SPIE/OSA/IEEE Asia Communications and Photonics.

[11]  Ayhan Demiriz,et al.  Linear Programming Boosting via Column Generation , 2002, Machine Learning.

[12]  J. Antoni.  The spectral kurtosis: a useful tool for characterising non-stationary signals , 2006 .

[13]  Yi He,et al.  Distributed disturbance sensor based on a novel Mach-Zehnder interferometer with a fiber-loop , 2006, Advanced Laser Technologies.

[14]  Kun Liu,et al.  A High-Efficiency Multiple Events Discrimination Method in Optical Fiber Perimeter Security System , 2015, Journal of Lightwave Technology.

[15]  Roger F. Dwyer,et al.  Detection of non-Gaussian signals by frequency domain Kurtosis estimation , 1983, ICASSP.

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

[17]  Lihui Jiang,et al.  Identification Technique for the Intrusion of Airport Enclosure Based on Double Mach-Zehnder Interferometer , 2012, J. Comput..

[18]  Alberto Bellini,et al.  Detection of Generalized-Roughness Bearing Fault by Spectral-Kurtosis Energy of Vibration or Current Signals , 2009, IEEE Transactions on Industrial Electronics.

[19]  Yan Zhou,et al.  Study on the distributed optical fiber sensing technology for pipeline leakage protection , 2006, Advanced Laser Technologies.

[20]  Wei Sun,et al.  Security Event Classification Method for Fiber-optic Perimeter Security System Based on Optimized Incremental Support Vector Machine , 2014, CCPR.

[21]  Francisco Herrera,et al.  An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes , 2011, Pattern Recognit..