An optic-fiber fence intrusion recognition system using the optimized curve fitting model based on the SVM method

The Perimeter Intrusion Detection System (PIDS) has been widely used in many fields since the development of optic-fiber interferometers and intrusion signal recognition models. However, common signal recognition models, such as Support Vector Machines (SVM) and Back Propagation Neural Networks (BPNN), do not perform well in classifying fiber intrusion signals due to the diversity of intrusion signals and the sensitivity of the fiber. In this paper, an optic-fiber based perimeter intrusion detection and recognition system that uses Sagnac interferometers and the optimized curve fitting model is proposed. Experiments on real perimeter intrusions are performed. Comparisons are carried out among our model and the SVM, BPNN models, which prove that our model is more accurate and robust.

[1]  Hwang-Ki Min,et al.  Abnormal Signal Detection in Gas Pipes Using Neural Networks , 2007, IECON 2007 - 33rd Annual Conference of the IEEE Industrial Electronics Society.

[2]  Seedahmed S. Mahmoud,et al.  Performance investigation of real-time fiber optic perimeter intrusion detection systems using event classification , 2010, 44th Annual 2010 IEEE International Carnahan Conference on Security Technology.

[3]  J. Blake,et al.  In-line Sagnac interferometer current sensor , 1995 .

[4]  V. Tiwari.  MFCC and its applications in speaker recognition , 2010 .

[5]  Paris Smaragdis,et al.  Hidden Markov and Gaussian mixture models for automatic call classification. , 2009, The Journal of the Acoustical Society of America.

[6]  Jie Zhu,et al.  Robust intrusion detection and recognition via sparse representation , 2013 .

[7]  Jie Zhu.  Research on Classification of Fiber Intrusion Signal Based on Supported Vector Machines , 2014 .

[8]  Nikos Fakotakis,et al.  Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task , 2007 .

[9]  Gary Allwood,et al.  Optical Fiber Sensors in Physical Intrusion Detection Systems: A Review , 2016, IEEE Sensors Journal.

[10]  Ye Wei,et al.  Distributed fiber-optic sensing using double-loop Sagnac interferometer , 2014, 2014 9th IEEE Conference on Industrial Electronics and Applications.

[11]  Jie Zhu,et al.  An optic-fiber fence intrusion recognition system using mixture Gaussian hidden Markov models , 2017, IEICE Electron. Express.

[12]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[13]  C. Burrus,et al.  Noise reduction using an undecimated discrete wavelet transform , 1996, IEEE Signal Processing Letters.

[14]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[15]  Nitin Trivedi,et al.  Speech Recognition by Wavelet Analysis , 2011 .

[16]  N.S. Nehe,et al.  New feature extraction methods using DWT and LPC for isolated word recognition , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[17]  Alastair D. McAulay,et al.  A Sagnac interferometer sensor system for intrusion detection and localization , 2004, SPIE Defense + Commercial Sensing.