Presentation 2007-03-05
FPGA Implementation of On-line ICA Algorithms
Song-Ju KIM, Ken UMENO, Ryo TAKAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We evaluate a performance of the EASI (Equivariant Adaptive Separation via Independence) algorithm, which is a basic algorithm among various on-line ICA (Independent Component Analysis) algorithms, using the original source signals generated by Chebyshev map. We confirmed that the EASI algorithm can recover a hundred of chaotic signals successfully. We found that the EASI algorithm in fixed-point (16-bit) arithmetic can also recover the chaotic signals successfully as well as the algorithm in floating-point arithmetic. We report the FPGA (Field Programmable Gate Arrays) implementation results of this algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Independent Component Analysis / BSS / EASI / MLE / FPGA / Chaos
Paper # CAS2006-84,SIP2006-185,CS2006-101
Date of Issue

Conference Information
Committee CS
Conference Date 2007/2/26(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 Communication Systems (CS)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) FPGA Implementation of On-line ICA Algorithms
Sub Title (in English)
Keyword(1) Independent Component Analysis
Keyword(2) BSS
Keyword(3) EASI
Keyword(4) MLE
Keyword(5) FPGA
Keyword(6) Chaos
1st Author's Name Song-Ju KIM
1st Author's Affiliation National Institute of Information and Communications Technology()
2nd Author's Name Ken UMENO
2nd Author's Affiliation National Institute of Information and Communications Technology
3rd Author's Name Ryo TAKAHASHI
3rd Author's Affiliation National Institute of Information and Communications Technology
Date 2007-03-05
Paper # CAS2006-84,SIP2006-185,CS2006-101
Volume (vol) vol.106
Number (no) 571
Page pp.pp.-
#Pages 6
Date of Issue