A multiuser detection method based on support vector machine

Author

Yang, Tao ; Xie, Jian-Ying

Author_Institution

Sch. of Electron. & Inf., Shanghai Jiao Tong Univ., China

Volume

1

fYear

2002

fDate

2002

Firstpage

373

Abstract

In this paper, a multi-user detector based on a Support Vector Machine (SVM) is proposed, which divides the receiving vector into two classes, +1 and -1, to attain detection. Differing from the MMSE detector, the SVM method can find an optimal hyperplane to separate the +1 and -1 from the training data. Simulation results show that under the Rayleigh channel, this detector can achieve a relatively low BER in comparison with the minimum mean square error (MMSE) detector.

Keywords

Rayleigh channels; adaptive signal detection; code division multiple access; error statistics; learning automata; multiuser detection; CDMA technology; Rayleigh channel; SVM method; adaptive nonlinear MUD; minimum mean square error detector; multiuser detection method; optimal hyperplane; receiving vector; relatively low BER; simulation results; support vector machine; training data; Bit error rate; Detection algorithms; Detectors; Multiaccess communication; Multiuser detection; Rayleigh channels; Risk management; Support vector machine classification; Support vector machines; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on

Print_ISBN

0-7803-7508-4

Type

conf

DOI

10.1109/ICMLC.2002.1176777

Filename

1176777