| 改进的高阶收敛FastICA算法 |
| |
| 引用本文： | 季策,胡祥楠,朱丽春,张志伟.改进的高阶收敛FastICA算法[J].东北大学学报(自然科学版),2011,32(10):1390-1393. |
| |
| 作者姓名： | 季策 胡祥楠 朱丽春 张志伟 |
| |
| 作者单位： | 1. 东北大学信息科学与工程学院,辽宁沈阳,110819
2. 中国科学院国家天文台,北京,100012 |
| |
| 基金项目： | 国家自然科学基金资助项目(10878017) |
| |
| 摘 要： | 高阶收敛的FastICA具有形式简单、收敛速度快的特点,但其对初始值的选择比较敏感,若初始值选择不当很容易影响收敛的效果,甚至造成不收敛的结果.针对这一问题,采用最速下降法对三阶和五阶收敛的FastICA算法进行改进.首先,应用最速下降法求出初值,再用高阶收敛的FastICA算法求出最优解.语音信号的分离实验表明:改进后的算法对混合信号进行了较好的分离,并且有效地克服了初值敏感性的问题.
|
| 关 键 词： | 独立分量分析 牛顿迭代法 FastICA 最速下降法 初值敏感性 |
Improved Higher Order Convergent FastICA Algorithm |
| |
| JI Ce,HU Xiang-nan,ZHU Li-chun,ZHANG Zhi-wei.Improved Higher Order Convergent FastICA Algorithm[J].Journal of Northeastern University(Natural Science),2011,32(10):1390-1393. |
| |
| Authors: | JI Ce HU Xiang-nan ZHU Li-chun ZHANG Zhi-wei |
| |
| Institution: | JI Ce,HU Xiang-nan,ZHU Li-chun,ZHANG Zhi-wei(1.School of Information Science & Engineering,Northeastern University,Shenyang 110819,China,2.National Astronomical Observatories,Chinese Academy of Sciences,Beijing 100012,China.) |
| |
| Abstract: | High order FastICA algorithms have the advantages of simple form and fast convergence rate.However,they are sensitive to their initial values affecting convergence effect and even resulting in inconvergence if the initial values are not chosen appropriately.To solve the problem,the FastICA algorithms of the third and fifth order convergence were improved with the steepest descent method.First,the initial values were calculated with the steepest descent method.Then,the optimal solution was calculated with th... |
| |
| Keywords: | independent component analysis Newton's iteration method FastICA steepest descent method initial value sensitivity |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《东北大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《东北大学学报(自然科学版)》下载免费的PDF全文 |
|
