首页 | 本学科首页   官方微博 | 高级检索  
   检索      

基于非负矩阵分解的电磁超声系统优化研究
引用本文:韩德来,陈鹏,蔡强富,刘美全.基于非负矩阵分解的电磁超声系统优化研究[J].军械工程学院学报,2013(5):35-39.
作者姓名:韩德来  陈鹏  蔡强富  刘美全
作者单位:军械工程学院无人机工程系,河北石家庄050003
摘    要:针对孤立脉冲群电磁超声系统信号特征容易被噪声淹没的问题,提出基于改进的非负矩阵分解(INMF)优选特征的支持向量机(SVM)方法.首先,用3种不同的方法提取高维特征;其次,用NMF方法实现特征降维,并保证降维结果的唯一性,避免对特征的直接选择;最后,应用支持向量机方法对降维特征进行分类.对孤立脉冲群电磁超声系统采集的4种信号特征进行提取、选择和分类,实验结果表明:INMF方法能有效提取微弱信号的特征,减少运算量,提高电磁超声系统特征采集的准确率.

关 键 词:电磁超声  非负矩阵分解  特征提取  特征选择  支持向量机

Optimization of Eelectromagnetic Acoustic System Based on NMF Method
HAN De-lai,CHEN Peng,CAI Qiang-fu,LIU Mei-quan.Optimization of Eelectromagnetic Acoustic System Based on NMF Method[J].Journal of Ordnance Engineering College,2013(5):35-39.
Authors:HAN De-lai  CHEN Peng  CAI Qiang-fu  LIU Mei-quan
Institution:(Unmanned Aerial System Engineering Department,Ordnance Engineering College,Shijiazhuang 050003,China)
Abstract:A characteristics optimized method based on improved non-negative matrix factorization (NMF) and support vector machine (SVM) is proposed to solve the problem that the characteris-tic in the signal of isolated impulse cluster electromagnetic acoustic system is easily overwhelmed by the noise. First, high-dimensional feature is extracted in three ways; second, an improved NMF method achieves dimension reduction and ensures the uniqueness results in dimensionality reduc-tion,avoiding the direct selection of the characteristics; finally, the SVM methods is used for characteristics identification and feature classification. Results show that the INMF method ex-tracts the weak signal characteristics effectively and improves the feature extraction accuracy rate in electromagnetic acoustic system.
Keywords:electromagnetic acoustic  non-negative matrix factorization  feature extraction  featureselection  support vector machine
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号