Presentation 2011-05-12
On the Convergence Properties of LMS Algorithm in Linear Prediction and System Identification for Sinusoidal Inputs
Yuki SATOMI, Arata KAWAMURA, Youji IIGUNI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is well known that the expectation value of adaptive filter coefficients updated with the LMS algorithm converges for stochastic signals. However, there has not been reported on the convergence analysis of the LMS algorithm for predicting deterministic signals. In this paper, we analyze the convergence of the LMS algorithm for predicting deterministic sinusoidal signals in the both of linear prediction and system identification. Firstly, we show that a coefficient vector updated with the LMS algorithm for predicting sinusoidal signals converges to a certain time-invariant vector. Secondly, we show a sufficient condition of the step-size for convergence. After that, we derive the convergence vector, which depends on the input signal and the initial vector. Finally, we perform computer simulations confirm and the validity of the theoretical convergence value.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) LMS algorithm / Sinusoidal Inputs / System Identification / Linear Predicting
Paper # EA2011-4,SIP2011-4,SP2011-4
Date of Issue

Conference Information
Committee SP
Conference Date 2011/5/5(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the Convergence Properties of LMS Algorithm in Linear Prediction and System Identification for Sinusoidal Inputs
Sub Title (in English)
Keyword(1) LMS algorithm
Keyword(2) Sinusoidal Inputs
Keyword(3) System Identification
Keyword(4) Linear Predicting
1st Author's Name Yuki SATOMI
1st Author's Affiliation Graduate School of Engineering Science, Osaka University()
2nd Author's Name Arata KAWAMURA
2nd Author's Affiliation Graduate School of Engineering Science, Osaka University
3rd Author's Name Youji IIGUNI
3rd Author's Affiliation Graduate School of Engineering Science, Osaka University
Date 2011-05-12
Paper # EA2011-4,SIP2011-4,SP2011-4
Volume (vol) vol.111
Number (no) 28
Page pp.pp.-
#Pages 6
Date of Issue