Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters

Abdul Rahman Elshafei; Azzedine Zerguine; Abdelhafid Bouhraoua

doi:10.1145/1582379.1582446

Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters

Abdul Rahman Elshafei^*, Azzedine Zerguine, Abdelhafid Bouhraoua

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This work proposes a scalable architecture for implementing a mixed-norm LMS-LMF adaptive algorithm using a 16-bit fixedpoint arithmetic representation. The hardware scalability allows flexibility in the choice of selecting the order of the filter without redesigning the hardware. The filter also allows flexibility in using application specific sampling frequencies. The hardware architecture was implemented using a Virtex-4 FPGA ML402 board. A 2nd order prototype was tested through both hardware and software simulations. According to the synthesis and the simulation results obtained, the adaptive filter coefficients would converge in less than 17μs with accuracy greater than 95%.

Original language	English
Title of host publication	Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009
Publisher	Association for Computing Machinery (ACM)
Pages	304-308
Number of pages	5
ISBN (Print)	9781605585697
DOIs	https://doi.org/10.1145/1582379.1582446
State	Published - 2009

Publication series

Name	Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009

Keywords

Adaptive filters
FPGA
LMS-LMF
Scalable architecture

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Software

Access to Document

10.1145/1582379.1582446

Cite this

Elshafei, A. R., Zerguine, A., & Bouhraoua, A. (2009). Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters. In Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009 (pp. 304-308). (Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009). Association for Computing Machinery (ACM). https://doi.org/10.1145/1582379.1582446

Elshafei, Abdul Rahman ; Zerguine, Azzedine ; Bouhraoua, Abdelhafid. / Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters. Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009. Association for Computing Machinery (ACM), 2009. pp. 304-308 (Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009).

@inproceedings{26aab7004de245b2b302f469580b6c1a,

title = "Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters",

abstract = "This work proposes a scalable architecture for implementing a mixed-norm LMS-LMF adaptive algorithm using a 16-bit fixedpoint arithmetic representation. The hardware scalability allows flexibility in the choice of selecting the order of the filter without redesigning the hardware. The filter also allows flexibility in using application specific sampling frequencies. The hardware architecture was implemented using a Virtex-4 FPGA ML402 board. A 2nd order prototype was tested through both hardware and software simulations. According to the synthesis and the simulation results obtained, the adaptive filter coefficients would converge in less than 17μs with accuracy greater than 95\%.",

keywords = "Adaptive filters, FPGA, LMS-LMF, Scalable architecture",

author = "Elshafei, \{Abdul Rahman\} and Azzedine Zerguine and Abdelhafid Bouhraoua",

year = "2009",

doi = "10.1145/1582379.1582446",

language = "English",

isbn = "9781605585697",

series = "Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009",

publisher = "Association for Computing Machinery (ACM)",

pages = "304--308",

booktitle = "Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009",

address = "United States",

}

Elshafei, AR, Zerguine, A & Bouhraoua, A 2009, Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters. in Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009. Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009, Association for Computing Machinery (ACM), pp. 304-308. https://doi.org/10.1145/1582379.1582446

Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters. / Elshafei, Abdul Rahman; Zerguine, Azzedine; Bouhraoua, Abdelhafid.
Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009. Association for Computing Machinery (ACM), 2009. p. 304-308 (Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters

AU - Elshafei, Abdul Rahman

AU - Zerguine, Azzedine

AU - Bouhraoua, Abdelhafid

PY - 2009

Y1 - 2009

N2 - This work proposes a scalable architecture for implementing a mixed-norm LMS-LMF adaptive algorithm using a 16-bit fixedpoint arithmetic representation. The hardware scalability allows flexibility in the choice of selecting the order of the filter without redesigning the hardware. The filter also allows flexibility in using application specific sampling frequencies. The hardware architecture was implemented using a Virtex-4 FPGA ML402 board. A 2nd order prototype was tested through both hardware and software simulations. According to the synthesis and the simulation results obtained, the adaptive filter coefficients would converge in less than 17μs with accuracy greater than 95%.

AB - This work proposes a scalable architecture for implementing a mixed-norm LMS-LMF adaptive algorithm using a 16-bit fixedpoint arithmetic representation. The hardware scalability allows flexibility in the choice of selecting the order of the filter without redesigning the hardware. The filter also allows flexibility in using application specific sampling frequencies. The hardware architecture was implemented using a Virtex-4 FPGA ML402 board. A 2nd order prototype was tested through both hardware and software simulations. According to the synthesis and the simulation results obtained, the adaptive filter coefficients would converge in less than 17μs with accuracy greater than 95%.

KW - Adaptive filters

KW - FPGA

KW - LMS-LMF

KW - Scalable architecture

UR - https://www.scopus.com/pages/publications/70450248552

U2 - 10.1145/1582379.1582446

DO - 10.1145/1582379.1582446

M3 - Conference contribution

AN - SCOPUS:70450248552

SN - 9781605585697

T3 - Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009

SP - 304

EP - 308

BT - Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009

PB - Association for Computing Machinery (ACM)

ER -

Elshafei AR, Zerguine A, Bouhraoua A. Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters. In Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing Conference, IWCMC 2009. Association for Computing Machinery (ACM). 2009. p. 304-308. (Proceedings of the 2009 ACM International Wireless Communications and Mobile Computing, Connecting the World Wirelessly, IWCMC 2009). doi: 10.1145/1582379.1582446

Scalable FPGA implementation for mixed-norm LMS-LMF adaptive filters

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this