The problem of constructing an adaptive multiuser detector (MUD) is considered for direct-sequence code-division multiple-access (DS-CDMA) signals transmitted through multipath channels. The emerging learning technique, called support vector machines (SVM), is proposed as a method of obtaining a nonlinear MUD from a relatively small training data block. Computer simulation is used to study this SVM MUD, and the results show that it can closely match the performance of the optimal Bayesian one-shot detector. Comparisons with an adaptive radial basis function (RBF) MUD trained by an unsupervised clustering algorithm are discussed. Keywords: DS-CDMA, multiuser interference, multiuser detector, linear MMSE detector, optimal one-shot detector, support vector machines, unsupervised clustering. 1
|
4514
|
Statistical Learning Theory
– Vapnik
- 1998
|
|
1103
|
A Tutorial on Support Vector Machines for Pattern Recognition
– Burges
- 1998
|
|
536
|
An Introduction to Support Vector Machines
– Cristianini, Shawe-Taylor
- 2000
|
|
533
|
Multirate Systems and Filter Banks
– Vaidyanathan
- 1993
|
|
516
|
Multiuser Detection
– Verdú
- 1998
|
|
495
|
Training of Support Vector Machine using Sequential Minimal Optimization
– Platt
- 1999
|
|
303
|
Minimum probability of error for asynchronous Gaussian multiple-access channels
– Verdú
- 1986
|
|
215
|
MMSE interference suppression for direct-sequence spread-spectrum CDMA
– Madhow, Honig
- 1994
|
|
184
|
Making large-scale support vector machine learning practical
– Joachims
- 1998
|
|
125
|
A family of sub-optimum detectors for coherent multiuser communications
– Xie, Short, et al.
- 1990
|
|
101
|
Multi-user detection for DS-CDMA communications
– Moshavi
- 1996
|
|
89
|
Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Functions Classifiers
– Schölkopf, Sung, et al.
- 1997
|
|
86
|
Probability of error in MMSE multiuser detection
– Poor, Verdù
- 1997
|
|
53
|
An adaptive direct-sequence code-division multiple-access receiver for multiuser interference rejection
– Miller
- 1995
|
|
46
|
A fast iterative nearest point algorithm for support vector machine classifier design (Tech
– Keerthi, Shevade, et al.
- 1999
|
|
34
|
A clustering technique for digital communications channel 169 equalization using radial basis function networks
– Chen, Mulgrew, et al.
- 1993
|
|
28
|
CDMA for Wireless Personal Communications
– Prasad
- 1996
|
|
26
|
The support vector method of function estimation
– Vapnik
- 1998
|
|
22
|
Adaptive Minimum-BER Linear Multiuser Detection for DS-CDMA
– Chen, Samingan, et al.
- 2001
|
|
20
|
Neural networks for multiuser detection in code-division multiple-access comARTICLE
– Aazhang, Paris, et al.
- 1992
|
|
19
|
Neural network techniques for adaptive multiuser demodulation
– Mitra, Poor
- 1994
|
|
18
|
Bayesian decision feedback equaliser for overcoming co-channel interference
– Chen, McLaughlin, et al.
- 1996
|
|
17
|
Approximate minimum bit-error rate multiuser detection
– Yeh, Lopes, et al.
- 1998
|
|
15
|
Adaptive detection for DSCDMA
– Woodward, Vucetic
- 1998
|
|
15
|
Decision feedback equalizer design using support vector machines
– Chen, Gunn, et al.
- 2000
|
|
15
|
Support Vector Machine Techniques for Nonlinear Equalization
– Sebald, James
- 2000
|
|
13
|
On adaptive minimum probability of error linear filter receivers for DS-CDMA channels
– Psaromiligkos, Batalama, et al.
- 1999
|
|
13
|
Nonlinear signal processing for adaptive equalisation and multi-user detection, in
– Mulgrew
- 1998
|
|
12
|
Gradient estimation for sensitivity analysis and adaptive multiuser interference rejection in code-division multi-access systems
– Mandayam, Aazhang
- 1997
|
|
9
|
Constrained minimum-BER multiuser detection
– Wang, Lu, et al.
- 1999
|
|
9
|
Radial Basis Function Receivers for DS-CDMA
– Cruickshank
- 1996
|
|
6
|
Volterra based receivers for DS-CDMA
– Tanner, Cruickshank
- 1997
|
|
6
|
Sample Selection Via Clustering to Construct Support Vector-Like Classifiers
– Lyhyaoui, Martinez, et al.
- 1999
|
|
5
|
The application of support vector machines with Gaussian kernels for overcoming co-channel interference
– Albu, Martinez
- 1999
|
|
5
|
Nonlinear time series modelling and prediction using Gaussian RBF networks with enhanced clustering and RLS learning
– Chen
- 1995
|
|
1
|
Alarcon-Diana and A. Artes-Rodr iguez, \SVC-based equalizer for burst TDMA transmission
– Perez-Cruz, Navia-Vazquez, et al.
- 2000
|
|
1
|
Optimal adaptive -means algorithm with dynamic adjustment of learning rate
– Chinrungrueng, Sequin
- 1995
|
|
