| 基于估计概率密度函数的独立分量分析方法 |
| |
| 引用本文： | 李大辉,王永红.基于估计概率密度函数的独立分量分析方法[J].齐齐哈尔大学学报(自然科学版),2007,23(3):20-23. |
| |
| 作者姓名： | 李大辉 王永红 |
| |
| 作者单位： | 1. 齐齐哈尔大学计算机与控制工程学院,黑龙江,齐齐哈尔,161006
2. 中国网通黑龙江通讯公司,哈尔滨,150001 |
| |
| 摘 要： | 利用混合高斯模型，给出了估计概率密度函数算法，并利用高斯混合模型法获得了对分离矩阵的梯度学习算法，给出了一种迭代概率密度估计的独立分量分析学习算法．这种块处理方法可实现超、亚高斯混合信源的情况．最后在仿真实验过程中验证了该算法具有较高的稳定度和精确度。
|
| 关 键 词： | 独立分量分析 高斯混合模型 概率密度 |
| 文章编号： | 1007-984X（2007）03-0020-04 |
| 修稿时间： | 2006-11-30 |
A method of independent component analysis based on the estimation function for the probability density |
| |
| LI Da-hui,WANG Yong-hong.A method of independent component analysis based on the estimation function for the probability density[J].Journal of Qiqihar University(Natural Science Edition),2007,23(3):20-23. |
| |
| Authors: | LI Da-hui WANG Yong-hong |
| |
| Institution: | 1.Qiqihar University computer Science and control Engineering Institute, HeiLongjiangQiqihar 161006, China; 2.Heilongjiang Communaication Company,China Network Communiacaiton Group, Harbin 150001, China |
| |
| Abstract: | The paper uses the Gaussian mixture model, the first ,giving an algorithm for approximating the probability density of the data, and a stochastic gradient method is given to separate the independent components, the seeond, makes an iterative method for estimating the pdf of data, which can perform the separation of mixed sub-Gaussian and super-Gaussian sources, the end, To improved the accuracy and stability of the algorithm, the performance of the method is shown by computer simulations. |
| |
| Keywords: | independent component analysis Gaussian mixture modeling probability density |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
