Presentation 2005-01-21
A Synchronized Learning Algorithm for Lattice Predictor Based Nonlinear Adaptive Filter
Hiroaki KASHIMOTO, Kenji NAKAYAMA, Akihiro HIRANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The adaptive Volterra filters (AVF) can represent general nonlinearity. However, its convergence speed is very slow. In order to solve this problem, techniques of whitening the input signal have been proposed. Among them, the lattice prediction error filter is useful. The lattice predictor based AVF (Lattice-AVF) has some problem. Updating the reflection coefficients and the filter coefficients is asynchronous, causing poor convergence properties. In order to solve this problem, the synchronized learning algorithm has been proposed for the linear adaptive filters. In this paper, a new synchronized learning algorithm is proposed for the nonlinear part of the Lattice-AVF. Its usefulness is confirmed though simulation using nonstationary colored signals.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive filters / Nonlinear / Volterra filters / Lattice predictor
Paper # SIP2004-110
Date of Issue

Conference Information
Committee SIP
Conference Date 2005/1/14(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 Synchronized Learning Algorithm for Lattice Predictor Based Nonlinear Adaptive Filter
Sub Title (in English)
Keyword(1) Adaptive filters
Keyword(2) Nonlinear
Keyword(3) Volterra filters
Keyword(4) Lattice predictor
1st Author's Name Hiroaki KASHIMOTO
1st Author's Affiliation Division of Electronics and Computer Science Graduate School of Natural Science and Technology, Kanazawa Univ.()
2nd Author's Name Kenji NAKAYAMA
2nd Author's Affiliation Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology, Kanazawa Univ.
3rd Author's Name Akihiro HIRANO
3rd Author's Affiliation Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology, Kanazawa Univ.
Date 2005-01-21
Paper # SIP2004-110
Volume (vol) vol.104
Number (no) 559
Page pp.pp.-
#Pages 6
Date of Issue