|
|
论文:2015,Vol:33,Issue(3):484-488 |
|
|
引用本文： |
|
|
黄兴利, 慕德俊, 肖磊, 焦利涛. 仿射投影算法收敛特性随机统计特性的研究[J]. 西北工业大学学报 |
|
|
Huang Xingli, Mu Dejun, Xiao Lei, Jiao Litao. A Statistical Analysis of Convergence of Affine Projection Algorithm[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 仿射投影算法收敛特性随机统计特性的研究 |
|
| 黄兴利1,2, 慕德俊1, 肖磊1,2, 焦利涛1 |
|
1. 西北工业大学 自动化学院, 陕西 西安 710072;
2. 温州大学 商学院, 浙江 温州 325035 |
| 摘要: |
| 仿射投影算法利用多个输入向量估计自适应滤波器的迭代方向,获得了比较快的收敛速度。在不考虑系统测量噪声的条件下,参数迭代步长等于1,仿射投影算法获得了最快的收敛速度。在此条件下,研究了仿射投影算法收敛性的随机统计特性,分析了仿射投影算法权值误差和权值均方误差的递归迭代方程,获得了仿射投影算法稳定状态的误差。 |
| 关键词:
自适应滤波
仿射投影算法
均方误差
系统辨识
|
|
| A Statistical Analysis of Convergence of Affine Projection Algorithm |
|
| Huang Xingli1,2, Mu Dejun1, Xiao Lei1,2, Jiao Litao1 |
|
1. Department of Automatic Control, Northwestern Ploytechnical University, Xi'an 710072, China;
2. School of Business, Wenzhou University, Wenzhou 325035, China |
| Abstract: |
| Using the multiple input vectors, the affine projection (AP) algorithm estimates the iteration direction of the adaptive filter. The AP algorithm obtains better convergence behavior. When the step-size equals to one, the AP algorithm realizes the fastest convergence under the measurement-noise free condition. In this condition, we analyze the statistical stochastic convergence behavior of the AP algorithm. The deterministic recursive equations are derived for the mean weight error and for the mean-square error (MSE). The stability of MSE is also obtained for the AP algorithm. |
| Key words:
adaptive filtering
algorithms
autocorrelation
calculations
convergence of numerical methods
eigenvalues and eigenfunctions
errors
estimation
identification(control systems)
iterative methods
least squares approximations
mathematical models
mean square error
measurements
probability
stability
statistical methods
stochastic models
vectors
white noise
affine projection(AP) algorithm
|
|
| 收稿日期: 2015-01-12
修回日期:
|
| DOI: |
| 基金项目: 浙江省自然科学基金(LY14F020030)资助 |
| 通讯作者:
Email： |
| 作者简介: 黄兴利(1981—),西北工业大学博士研究生,主要从事嵌入式系统研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Ozeki K, Umeda T. An Adaptive Filtering Algorithm Using an Orthogonal Projection to an Affine Subspace and Its Properties[J]. Electronics and Communications in Japan, 1984, 67(5): 19-27
[2] Pupp M. A Family of Adaptive Filter Algorithms with Decorrelating Properties[J]. IEEE Trans on Signal Process, 1998, 46(3): 771-775
[3] Sjmd Almeida, Jcm Bermudez, Nj Bershad. A Statistical Analysis of the Affine Projection Algorithm for Unity Step Size and Autoregressive Inputs[J]. IEEE Trans on Circuits Syst I——Fundam Theory Appl, 2005, 52(7): 1394-1405
[4] Sjmd Almeida, Jcm Bermudez, Nj Bershad. A Stochastic Model for a Pseudo Affine Projection Algorithm[J]. IEEE Trans on Signal Process. 2009, 57(1): 107-118
[5] Sankaran S G, Beex A A. Convergence Behavior of Affine Projection Algorithms[J]. IEEE Trans on Signal Process, 2000, 48(4): 1086-1096
[6] Tk Paul, Ogunfunmi T. On the Convergence Behavior of the Affine Projection Algorithm for Adaptive Filters[J]. IEEE Trans on Circuits Syst I——Fundam Theory Appl, 2011, 58(8): 1813-1826
[7] Se Kim, Jw Lee, Wj Song, A Theory on the Convergence Behavior of the Affine Projection Algorithm[J]. IEEE Trans on Signal Process, 2011, 59(12): 6233-6239
[8] Dtm Slock. On the Convergence Behavior of the LMS and the Normalized LMS Algorithms[J]. IEEE Trans on Signal Process, 1993, 41(9): 2811-2825 |
|
|
|
|
|
|
|
