Symmetric RBF classifier for nonlinear detection in multiple-antenna aided systems
Symmetric RBF classifier for nonlinear detection in multiple-antenna aided systems
In this paper, we propose a powerful symmetric radial basis function (RBF) classifier for nonlinear detection in the so-called “overloaded” multiple-antenna-aided communication systems. By exploiting the inherent symmetry property of the optimal Bayesian detector, the proposed symmetric RBF classifier is capable of approaching the optimal classification performance using noisy training data. The classifier construction process is robust to the choice of the RBF width and is computationally efficient. The proposed solution is capable of providing a signal-tonoise ratio (SNR) gain in excess of 8 dB against the powerful linear minimum bit error rate (BER) benchmark, when supporting four users with the aid of two receive antennas or seven users with four receive antenna elements. Index Terms—Classification, multiple-antenna system, orthogonal forward selection, radial basis function (RBF), symmetry.
737-745
Chen, S.
ac405529-3375-471a-8257-bda5c0d10e53
Wolfgang, A.
e87811dd-7028-4ac3-90cc-62003ff22202
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Hanzo, L.
66e7266f-3066-4fc0-8391-e000acce71a1
May 2008
Chen, S.
ac405529-3375-471a-8257-bda5c0d10e53
Wolfgang, A.
e87811dd-7028-4ac3-90cc-62003ff22202
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Hanzo, L.
66e7266f-3066-4fc0-8391-e000acce71a1
Chen, S., Wolfgang, A., Harris, C.J. and Hanzo, L.
(2008)
Symmetric RBF classifier for nonlinear detection in multiple-antenna aided systems.
IEEE Transactions on Neural Networks, 19 (5), .
Abstract
In this paper, we propose a powerful symmetric radial basis function (RBF) classifier for nonlinear detection in the so-called “overloaded” multiple-antenna-aided communication systems. By exploiting the inherent symmetry property of the optimal Bayesian detector, the proposed symmetric RBF classifier is capable of approaching the optimal classification performance using noisy training data. The classifier construction process is robust to the choice of the RBF width and is computationally efficient. The proposed solution is capable of providing a signal-tonoise ratio (SNR) gain in excess of 8 dB against the powerful linear minimum bit error rate (BER) benchmark, when supporting four users with the aid of two receive antennas or seven users with four receive antenna elements. Index Terms—Classification, multiple-antenna system, orthogonal forward selection, radial basis function (RBF), symmetry.
Text
04469943.pdf
- Version of Record
More information
Published date: May 2008
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 265664
URI: http://eprints.soton.ac.uk/id/eprint/265664
PURE UUID: f0f8a276-0753-433e-8641-87d01ec06b51
Catalogue record
Date deposited: 02 May 2008 08:37
Last modified: 31 Jul 2019 00:53
Export record
Contributors
Author:
S. Chen
Author:
A. Wolfgang
Author:
C.J. Harris
Author:
L. Hanzo
University divisions
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics