| 基于信息理论准则的盲源分离方法 |
| |
| 引用本文： | 刘琚,鲁子奕.基于信息理论准则的盲源分离方法[J].应用科学学报,1999,17(2):156-162. |
| |
| 作者姓名： | 刘琚 鲁子奕 |
| |
| 作者单位： | 东南大学，山东大学 |
| |
| 摘 要： | 根据统计独立的假设，利用概率密度函数的Ｅｄｇｅｗｏｒｔｈ展开，得出了基于互信息最小化的目标函数，该函数具有明确的物理意义，它的最小化可以使输出相互独立，仿真实验结果表明所提出的方法可较好地用于盲源分离问题。
|
| 关 键 词： | 互信息 独立信号 盲源分离 信号处理 信息论 |
An Information Theory Based Method for Blind Separation of Sources |
| |
| LIU JU , LU ZIYI HE ZHENYA MEI LIANGMO.An Information Theory Based Method for Blind Separation of Sources[J].Journal of Applied Sciences,1999,17(2):156-162. |
| |
| Authors: | LIU JU LU ZIYI HE ZHENYA MEI LIANGMO |
| |
| Institution: | LIU JU 1,2 LU ZIYI 1 HE ZHENYA 1 MEI LIANGMO 2 1.Department of Radio Engineering,Southeast University,Nanjing 210018 2.Department of Physics,Shandong University,Jinan 250100 |
| |
| Abstract: | Based on the assumption of statistics independent, we proposed an mutual information minimizing object function where Edgeworth expansion is used. This function can be explained clearly and its minimization would make the outputs independent. Computer simulation shows the validity of proposed method. |
| |
| Keywords: | mutual information independent signals blind separation of sources |
| 本文献已被 CNKI 维普 等数据库收录！ |
