FPGA realization of a radial basis function based nonlinear channel equalizer

Po-Yueh Chen, Hungming Tsai, Cheng Jian Lin, Chiyung Lee

Research output: Contribution to journal › Article

3 Citations (Scopus)

Abstract

In this paper we propose a radial basis function (RBF) neural network for nonlinear time-invariant channel equalizer. The RBF network model has a three-layer structure which is comprised of an input layer, a hidden layer and an output layer. The learning algorithm consists of unsupervised learning and supervised learning. The unsupervised learning mainly adjusts the weight among input layer and hidden layer. The supervised learning adjusts the weight among output layer and hidden layer. We will implement RBF by using FPGA. Computer simulation results show that the bit error rates of the RBF equalize using software and hardware implements are close to that of the optimal equalizer.

Original languageEnglish
Pages (from-to)320-325
Number of pages6
JournalLecture Notes in Computer Science
Volume3498
Issue numberIII
Publication statusPublished - 2005 Sep 26

Fingerprint

Equalizer
Equalizers
Radial Functions
Field Programmable Gate Array
Basis Functions
Field programmable gate arrays (FPGA)
Unsupervised learning
Supervised learning
Radial basis function networks
Bit error rate
Learning algorithms
Unsupervised Learning
Supervised Learning
Neural networks
Hardware
Computer simulation
Radial Basis Function Network
Radial Basis Function Neural Network
Output
Network Model

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Chen, Po-Yueh ; Tsai, Hungming ; Lin, Cheng Jian ; Lee, Chiyung. / FPGA realization of a radial basis function based nonlinear channel equalizer. In: Lecture Notes in Computer Science. 2005 ; Vol. 3498, No. III. pp. 320-325.
@article{967d045edd8d4b649288f163fac20e29,
title = "FPGA realization of a radial basis function based nonlinear channel equalizer",
abstract = "In this paper we propose a radial basis function (RBF) neural network for nonlinear time-invariant channel equalizer. The RBF network model has a three-layer structure which is comprised of an input layer, a hidden layer and an output layer. The learning algorithm consists of unsupervised learning and supervised learning. The unsupervised learning mainly adjusts the weight among input layer and hidden layer. The supervised learning adjusts the weight among output layer and hidden layer. We will implement RBF by using FPGA. Computer simulation results show that the bit error rates of the RBF equalize using software and hardware implements are close to that of the optimal equalizer.",
author = "Po-Yueh Chen and Hungming Tsai and Lin, {Cheng Jian} and Chiyung Lee",
year = "2005",
month = "9",
day = "26",
language = "English",
volume = "3498",
pages = "320--325",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
number = "III",

}

Chen, P-Y, Tsai, H, Lin, CJ & Lee, C 2005, 'FPGA realization of a radial basis function based nonlinear channel equalizer', Lecture Notes in Computer Science, vol. 3498, no. III, pp. 320-325.

FPGA realization of a radial basis function based nonlinear channel equalizer. / Chen, Po-Yueh; Tsai, Hungming; Lin, Cheng Jian; Lee, Chiyung.

In: Lecture Notes in Computer Science, Vol. 3498, No. III, 26.09.2005, p. 320-325.

Research output: Contribution to journal › Article

TY - JOUR

T1 - FPGA realization of a radial basis function based nonlinear channel equalizer

AU - Chen, Po-Yueh

AU - Tsai, Hungming

AU - Lin, Cheng Jian

AU - Lee, Chiyung

PY - 2005/9/26

Y1 - 2005/9/26

N2 - In this paper we propose a radial basis function (RBF) neural network for nonlinear time-invariant channel equalizer. The RBF network model has a three-layer structure which is comprised of an input layer, a hidden layer and an output layer. The learning algorithm consists of unsupervised learning and supervised learning. The unsupervised learning mainly adjusts the weight among input layer and hidden layer. The supervised learning adjusts the weight among output layer and hidden layer. We will implement RBF by using FPGA. Computer simulation results show that the bit error rates of the RBF equalize using software and hardware implements are close to that of the optimal equalizer.

AB - In this paper we propose a radial basis function (RBF) neural network for nonlinear time-invariant channel equalizer. The RBF network model has a three-layer structure which is comprised of an input layer, a hidden layer and an output layer. The learning algorithm consists of unsupervised learning and supervised learning. The unsupervised learning mainly adjusts the weight among input layer and hidden layer. The supervised learning adjusts the weight among output layer and hidden layer. We will implement RBF by using FPGA. Computer simulation results show that the bit error rates of the RBF equalize using software and hardware implements are close to that of the optimal equalizer.

UR - http://www.scopus.com/inward/record.url?scp=24944472563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24944472563&partnerID=8YFLogxK

M3 - Article

VL - 3498

SP - 320

EP - 325

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - III

ER -

Chen P-Y, Tsai H, Lin CJ, Lee C. FPGA realization of a radial basis function based nonlinear channel equalizer. Lecture Notes in Computer Science. 2005 Sep 26;3498(III):320-325.

Access to Document