Home > Papers

 
 
A Novel Partial-Update NLMS Algorithms with Filter Length Gradient Descent
ZhuFengchao 1,Gao Feifei 2 *
1.Departmentofautomation,UniversityofTsinghua；TheSecondArtilleryEngineeringUniversityTheSecondArtilleryEngineeringUniversity
2. Department of automation, University of Tsinghua, Beijing 100084
*Correspondence author
#Submitted by
Subject:
Funding: 高等学校博士学科点专项科研基金新教师类资助课题 （No.20110002120059）
Opened online:31 March 2014
Accepted by: none
Citation: ZhuFengchao,Gao Feifei.A Novel Partial-Update NLMS Algorithms with Filter Length Gradient Descent[OL]. [31 March 2014] http://en.paper.edu.cn/en_releasepaper/content/4590694
 
 
This paper presents a novel partial-update normalized least-mean square (PU-NLMS) algorithmwhose coefficients are updated with a new gradient descent function of the squared estimation error where both the full-update estimation error and the filter length error are contained.Compared with other partial-update NLMS algorithms or even with the full-update NLMS algorithm, the proposed algorithm has better convergence performance.It is worth noting that the proposed algorithm also possesses an effective complexity reduction which is an important characteristic of the conventional partial-update NLMS algorithms that update only part of the filter coefficients. Simulation results verify that the new partial-update algorithm is reasonable and effective.
Keywords:Partial update NLMS algorithm, gradient descent function, estimation error, filter length error
 
 
 

For this paper
  • ● PDF (0B)
  • ● Revision 0 　　
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags
Add yours

Related Papers
  • Other similar papers

Statistics
PDF Downloaded 176
Bookmarked 0
Recommend 5
Comments Array
Submit your papers