| 全光纤安防系统模式识别混合编程的实现 |
| |
| 引用本文： | 赵杰,丁吉,万遂人,孙小菡.全光纤安防系统模式识别混合编程的实现[J].东南大学学报(自然科学版),2011,41(1):41-46. |
| |
| 作者姓名： | 赵杰 丁吉 万遂人 孙小菡 |
| |
| 作者单位： | 东南大学生物科学与医学工程学院;东南大学电子科学与工程学院; |
| |
| 摘 要： | 介绍了宽域全光纤监控预警系统及光纤扰动信号模式识别算法.利用小波包分解对信号进行分解与重构,并提取各频段内信号分量能量谱作为特征向量;应用综合考虑观测数据和确定性先验知识的BVC-RBF神经网络实现信号分类,提高了网络的泛化能力.利用Matlab引擎、动态链接库(DLL)、组件对象模型(COM)3种混合编程方法将Mat...
|
| 关 键 词： | 光纤扰动信号 模式识别 小波包分解 BVC-RBF网络 混合编程 |
Implementation of pattern recognition in all fiber security monitoring system using mixed programming |
| |
| Zhao Jie,Ding Ji,Wan Suiren,Sun Xiaohan.Implementation of pattern recognition in all fiber security monitoring system using mixed programming[J].Journal of Southeast University(Natural Science Edition),2011,41(1):41-46. |
| |
| Authors: | Zhao Jie Ding Ji Wan Suiren Sun Xiaohan |
| |
| Institution: | Zhao Jie1 Ding Ji1 Wan Suiren1 Sun Xiaohan2(1School of Biological Science and Medical Engineering,Southeast University,Nanjing 210096,China)(2School of Electronic Science and Engineering,China) |
| |
| Abstract: | An all fiber security monitoring system and pattern recognition algorithm on fiber disturbance signal is presented.As a method of analyzing and reconstructing signal wavelet packet is adopted to extract feature vector.Classification is realized by BVC-RBF(boundary value constraints-radial basis function) neural network,which improves generalization by considering deterministic prior knowledge besides observational data.Pattern recognition algorithm is developed with Matlab and integrated into the applicatio... |
| |
| Keywords: | fiber disturbance signal pattern recognition wavelet packet neural network mixed programming |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
