Presentation 1996/10/18
Convergence Characteristics of the Parallel-form LRS Algorithm of Adaptive Digital Filters
Yukihiro NAKAMURA, Masayuki KAWAMATA, Tatsuo HIGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes the parallel-form LRS algorithm of adaptive digital filters. It is an adaptive algorithm which makes a random search on a specific surface by several numbers of digital filters. Each filter has different advantages such as (1) reduction of the time constant and (2) reduction of the residual error, according to the value of variance of its random vector. Since the proposed algorithm has these advantages simultaneously, it can overcome the tradeoff between time constant and residual error of the traditional LRS algorithm. In this paper, it is shown by system identification that the parallel LRS can reduce simultaneously the time constant and the residual error of adaptive FIR digital filters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) variance of random vector / tradeoff / parallel-form LRS algorithm
Paper # DSP96-95,ICD96-150
Date of Issue

Conference Information
Committee DSP
Conference Date 1996/10/18(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 Digital Signal Processing (DSP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Convergence Characteristics of the Parallel-form LRS Algorithm of Adaptive Digital Filters
Sub Title (in English)
Keyword(1) variance of random vector
Keyword(2) tradeoff
Keyword(3) parallel-form LRS algorithm
1st Author's Name Yukihiro NAKAMURA
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Masayuki KAWAMATA
2nd Author's Affiliation Graduate School of Engineering, Tohoku University
3rd Author's Name Tatsuo HIGUCHI
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University
Date 1996/10/18
Paper # DSP96-95,ICD96-150
Volume (vol) vol.96
Number (no) 301
Page pp.pp.-
#Pages 7
Date of Issue