J4 ›› 2011, Vol. 28 ›› Issue (2): 183-190.

• 第二届全国光学青年学术论坛论文选登 • 上一篇    下一篇

基于Mach-Zehnder 干涉仪的光纤入侵行为识别系统

陶沛琳1,2, 延凤平1,2, 刘鹏1,2, 彭万敬1,2, 李琦1,2, 冯亭1,2   

  1. 1 北京交通大学光波技术研究所, 北京 100044;
    2 全光网络与现代通信网教育部重点实验室, 北京 100044
  • 出版日期:2011-03-28 发布日期:2011-03-03
  • 通讯作者: 延凤平(1966-),博士,教授,博导,主要从事光通信,全光网络,新型特种光纤及光纤器件,光纤传感,无线通信等方面的研究。
  • 作者简介:陶沛琳(1984—),女,博士研究生。E-mail: 07111040@bjtu.edu.cn
  • 基金资助:

    中央高校基本科研业务费专项资金资助(2009YJS015)

Fiber-optic intrusion recognition system based on Mach-Zehnder interferometer

TAO Pei-lin1,2, YAN Feng-ping1,2, LIU Peng1,2, PENG Wan-jing1,2, LI Qi1,2, FENG Ting1,2   

  1. 1 Institute of Lightwave Technology, Beijing Jiaotong University, Beijing 100044, China;
     2 Key Laboratory of All Optical Network & Advanced Telecommunication Network of Ministry of Education, Beijing Jiaotong University, Beijing  100044, China
  • Published:2011-03-28 Online:2011-03-03

摘要:

为实现高精度识别功能,基于Mach-Zehnder光纤传感器建立光纤入侵行为识别系统。引入多元回归统计原理,建立常用信号特征参量与设定因变量之间的多元回归方程。通过逐步引入校验方法,验证回归模型的显著性校验,实现特征的优化选取。利用选取的有效特征,构造基于感知准则的入侵行为识别系统。实验证明基于多元统计原理的入侵行为识别系统具有良好的识别准确率,且识别准确率达到83.33%。

关键词: 光电子学, 识别系统, Mach-Zehnder 干涉仪, 多元回归, 感知准则, 入侵

Abstract:

Based on Mach-Zehnder interferometer, the fiber-optic intrusion recognition system was established to realize high precision recognition system. By introducing the principle of multiple regression statistics, the multiple regression equations between signal characteristics parameters and dependent variable were set up. Optimal selection of characteristic was realized by the administration of a significance test on the regression model with method of gradually introducing. Classifier was designed based on perception with optimizing characteristic to establish fiber-optic intrusion recognition system. The test results indicate that the recognition system based on multiple regression has accuracy of identification is 83.33%.

Key words: optoelectronics, recognition system, Mach-Zehnder interferometer, multiple regression, perception criterion

中图分类号: