| 一种基于ICA的盲源分离定点迭代算法 |
| |
| 引用本文： | 李鸿燕,马建芬,李灯熬,王华奎.一种基于ICA的盲源分离定点迭代算法[J].太原理工大学学报,2007,38(1):35-37,41. |
| |
| 作者姓名： | 李鸿燕 马建芬 李灯熬 王华奎 |
| |
| 作者单位： | 太原理工大学,信息工程学院,山西,太原,030024 |
| |
| 基金项目： | 山西省高校科技开发基金 |
| |
| 摘 要： | 介绍了一种基于ICA的定点速代算法，并给出算法的模型、步骤和仿真结果。该算法以峰度作为独立性判决准则，在迭代过程中，使用定点算法，快速有效地分离出任意分布的非高斯独立源信号。实验表明，与传统的基于随机梯度的ICA算法相比，谊算法具有收敛速度快，无需动态参数的优点，是一种高效可靠的盲信号分离算法。
|
| 关 键 词： | 盲源分离 定点算法 |
| 文章编号： | 1007-9432（2007）01-0035-03 |
| 收稿时间： | 2006-03-13 |
| 修稿时间： | 2006-03-13 |
A Fixed-point Blind Source Separation Iterative Algorithm Based on ICA |
| |
| LI Hong-yan,MA Jian-fen,LI Deng-ao,WANG Hua-kui.A Fixed-point Blind Source Separation Iterative Algorithm Based on ICA[J].Journal of Taiyuan University of Technology,2007,38(1):35-37,41. |
| |
| Authors: | LI Hong-yan MA Jian-fen LI Deng-ao WANG Hua-kui |
| |
| Institution: | College of Information Engineering of TUT , Taiyuan 030024,China |
| |
| Abstract: | This paper introduces a fixed-point learning algorithm based on ICA(Independent Component Analysis),the model and process of this algorithm and simulation results are presented.Here we adopted kurtosis as the estimation rule of independence.The results of the experiment show that comparing with traditional ICA algorithm based on random grads,this algorithm has many advantages such as fast convergence and needless any dynamic parameter and so on.The algorithm is a highly efficient and reliable method in blind signal separation. |
| |
| Keywords: | ICA |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
