Block-adaptive kernel-based CDMA multiuser detection
Block-adaptive kernel-based CDMA multiuser detection
The paper investigates the application of a recently introduced learning technique, referred to as the relevance vector machine (RVM) to construct a block-adaptive kernel-based nonlinear multiuser detector (MUD) for direct-sequence code-division multiple-access (DSCDMA) signals transmitted through multipath channels. It is demonstrated that the RVM MUD is capable of closely matching the performance of the optimal Bayesian one-shot detector, with the aid of a significantly more sparse kernel representation than that required by the state-of-the-art support vector machine (SVM) technique.
682-686
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Hanzo, Lajos
66e7266f-3066-4fc0-8391-e000acce71a1
28 April 2002
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Hanzo, Lajos
66e7266f-3066-4fc0-8391-e000acce71a1
Chen, Sheng and Hanzo, Lajos
(2002)
Block-adaptive kernel-based CDMA multiuser detection.
In 2002 IEEE International Conference on Communications: Conference Proceedings. ICC 2002.
IEEE.
.
(doi:10.1109/ICC.2002.996943).
Record type:
Conference or Workshop Item
(Paper)
Abstract
The paper investigates the application of a recently introduced learning technique, referred to as the relevance vector machine (RVM) to construct a block-adaptive kernel-based nonlinear multiuser detector (MUD) for direct-sequence code-division multiple-access (DSCDMA) signals transmitted through multipath channels. It is demonstrated that the RVM MUD is capable of closely matching the performance of the optimal Bayesian one-shot detector, with the aid of a significantly more sparse kernel representation than that required by the state-of-the-art support vector machine (SVM) technique.
Text
ICC2002
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Published date: 28 April 2002
Venue - Dates:
ICC 2002: 2002 IEEE International Conference on Communications, New York, New York, United States, 2002-04-28 - 2002-05-02
Identifiers
Local EPrints ID: 454146
URI: http://eprints.soton.ac.uk/id/eprint/454146
PURE UUID: 7c9ad7db-0132-4d26-b896-a0bbcd7e23d2
Catalogue record
Date deposited: 01 Feb 2022 17:43
Last modified: 18 Mar 2024 02:36
Export record
Altmetrics
Contributors
Author:
Sheng Chen
Author:
Lajos Hanzo
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