Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter

S. Ong, S. Choi, C. You, D. Hong

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

A decision feedback recurrent neural equalizer (DFRNE), a nonlinear Infinite Impulse Response (IIR) filter, has already been proposed successfully for the channel equalization problem [1, 2]. In this paper, we introduce a complex version of a DFRNE. Its small size and high performance makes it attractive for channel equalization. We evaluate its performance through computer simulations for various complex channels and derive that its convergence is more stable and robust than that of other equalizers. It is also shown that the complex DFRNE outperforms other equalization schemes when the channel distortion is profound.

Original languageEnglish
Pages57-61
Number of pages5
Publication statusPublished - 1997 Dec 1
EventProceedings of the 1997 IEEE Global Telecommunications Mini-Conference - Phoenix, AZ, USA
Duration: 1997 Nov 31997 Nov 8

Other

OtherProceedings of the 1997 IEEE Global Telecommunications Mini-Conference
CityPhoenix, AZ, USA
Period97/11/397/11/8

Fingerprint

IIR filters
Equalizers
filter
Feedback
computer simulation
decision
Computer simulation

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Global and Planetary Change

Cite this

Ong, S., Choi, S., You, C., & Hong, D. (1997). Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter. 57-61. Paper presented at Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference, Phoenix, AZ, USA, .
Ong, S. ; Choi, S. ; You, C. ; Hong, D. / Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter. Paper presented at Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference, Phoenix, AZ, USA, .5 p.
@conference{48b67858cb4b4e3c8d50490188ff2fa0,
title = "Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter",
abstract = "A decision feedback recurrent neural equalizer (DFRNE), a nonlinear Infinite Impulse Response (IIR) filter, has already been proposed successfully for the channel equalization problem [1, 2]. In this paper, we introduce a complex version of a DFRNE. Its small size and high performance makes it attractive for channel equalization. We evaluate its performance through computer simulations for various complex channels and derive that its convergence is more stable and robust than that of other equalizers. It is also shown that the complex DFRNE outperforms other equalization schemes when the channel distortion is profound.",
author = "S. Ong and S. Choi and C. You and D. Hong",
year = "1997",
month = "12",
day = "1",
language = "English",
pages = "57--61",
note = "Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference ; Conference date: 03-11-1997 Through 08-11-1997",

}

Ong, S, Choi, S, You, C & Hong, D 1997, 'Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter' Paper presented at Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference, Phoenix, AZ, USA, 97/11/3 - 97/11/8, pp. 57-61.

Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter. / Ong, S.; Choi, S.; You, C.; Hong, D.

1997. 57-61 Paper presented at Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference, Phoenix, AZ, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter

AU - Ong, S.

AU - Choi, S.

AU - You, C.

AU - Hong, D.

PY - 1997/12/1

Y1 - 1997/12/1

N2 - A decision feedback recurrent neural equalizer (DFRNE), a nonlinear Infinite Impulse Response (IIR) filter, has already been proposed successfully for the channel equalization problem [1, 2]. In this paper, we introduce a complex version of a DFRNE. Its small size and high performance makes it attractive for channel equalization. We evaluate its performance through computer simulations for various complex channels and derive that its convergence is more stable and robust than that of other equalizers. It is also shown that the complex DFRNE outperforms other equalization schemes when the channel distortion is profound.

AB - A decision feedback recurrent neural equalizer (DFRNE), a nonlinear Infinite Impulse Response (IIR) filter, has already been proposed successfully for the channel equalization problem [1, 2]. In this paper, we introduce a complex version of a DFRNE. Its small size and high performance makes it attractive for channel equalization. We evaluate its performance through computer simulations for various complex channels and derive that its convergence is more stable and robust than that of other equalizers. It is also shown that the complex DFRNE outperforms other equalization schemes when the channel distortion is profound.

UR - http://www.scopus.com/inward/record.url?scp=0031342638&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031342638&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0031342638

SP - 57

EP - 61

ER -

Ong S, Choi S, You C, Hong D. Complex version of a decision feedback recurrent neural equalizer as an infinite impulse response filter. 1997. Paper presented at Proceedings of the 1997 IEEE Global Telecommunications Mini-Conference, Phoenix, AZ, USA, .