Share Email Print

Optical Engineering

Improved wavelet packet classification algorithm for vibrational intrusions in distributed fiber-optic monitoring systems
Author(s): Bingjie Wang; Shaohua Pi; Qi Sun; Bo Jia
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An improved classification algorithm that considers multiscale wavelet packet Shannon entropy is proposed. Decomposition coefficients at all levels are obtained to build the initial Shannon entropy feature vector. After subtracting the Shannon entropy map of the background signal, components of the strongest discriminating power in the initial feature vector are picked out to rebuild the Shannon entropy feature vector, which is transferred to radial basis function (RBF) neural network for classification. Four types of man-made vibrational intrusion signals are recorded based on a modified Sagnac interferometer. The performance of the improved classification algorithm has been evaluated by the classification experiments via RBF neural network under different diffusion coefficients. An 85% classification accuracy rate is achieved, which is higher than the other common algorithms. The classification results show that this improved classification algorithm can be used to classify vibrational intrusion signals in an automatic real-time monitoring system.

Paper Details

Date Published: 20 May 2015
PDF: 6 pages
Opt. Eng. 54(5) 055104 doi: 10.1117/1.OE.54.5.055104
Published in: Optical Engineering Volume 54, Issue 5
Show Author Affiliations
Bingjie Wang, Fudan Univ. (China)
Shaohua Pi, Fudan Univ. (China)
Qi Sun, Fudan Univ. (China)
Bo Jia, Fudan Univ. (China)

© SPIE. Terms of Use
Back to Top