Presentation 2008-04-17
A Study on Adaptive Recursive Filter Based on Lagrange-White's Algorithm
Masaki KOBAYASHI, Chi WANG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new adaptive recursive filter that has innovated the Lagrange multiplier method into the adaptive White's algorithm. The adaptive White's algorithm is known as a typical algorithm of the adaptive recursive filter in which the cost function is the output error. This algorithm is a recursive algorithm in which the gradient concerning the tap coefficient of the cost function is calculated almost accurately. However, this adaptive recursive filter has the problem that the plural local minimums exist even if the degree of the adaptive filter is greater than the degree of unknown system (exact model) and the input signal is a white signal. The purpose of this paper is to give a solution of this problem. The adaptive algorithm that minimizes the mean square value of the output error under the condition of the equality of the output power of the adaptive filter and the unknown system can converge to the optimum value when the Lagrange multiplier is zero. It is also verified that the local minimum can be avoided by the numerical simulation compared with the White's algorithm. In addition, the influence of the near end noise is considered.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Local Minimum / Convergence Value / Lagrange Multiplier / Output Error / Adaptive Recursive Filter
Paper # SIP2008-12,IE2008-12
Date of Issue

Conference Information
Committee SIP
Conference Date 2008/4/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Signal Processing (SIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Adaptive Recursive Filter Based on Lagrange-White's Algorithm
Sub Title (in English)
Keyword(1) Local Minimum
Keyword(2) Convergence Value
Keyword(3) Lagrange Multiplier
Keyword(4) Output Error
Keyword(5) Adaptive Recursive Filter
1st Author's Name Masaki KOBAYASHI
1st Author's Affiliation Faculty of Engineering, Chubu University()
2nd Author's Name Chi WANG
2nd Author's Affiliation Faculty of Engineering, Chubu University
Date 2008-04-17
Paper # SIP2008-12,IE2008-12
Volume (vol) vol.108
Number (no) 3
Page pp.pp.-
#Pages 6
Date of Issue