Complex-valued radial basic function network, Part I: Network architecture and learning algorithms

Chen, Sheng; McLaughlin, Stephen; Mulgrew, Bernard

doi:10.1016/0165-1684(94)90187-2

Cited by 125 publications

(61 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be seen that the optimal Bayesian decision variable (9) takes the structure of a complex-valued RBF network [17] with a Gaussian RBF function. The state subsets X…”

Section: Optimal Bayesian Beamforming Solutionmentioning

confidence: 99%

“…This study extends nonlinear beamforming to quadrature phase shift keying (QPSK) systems. For QPSK systems the optimal Bayesian detection solution can be expressed as a complexvalued radial basis function network [17], [18]. We further exploit the inherent symmetry of the optimal nonlinear beamforming solution and propose a SRBF network for adaptively implementing the Bayesian beamforming solution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nonlinear Beamforming for Multiple-Antenna Assisted QPSK Wireless Systems

Chen

Hanzo

Tan

2008

2008 IEEE International Conference on Communications

Self Cite

View full text Add to dashboard Cite

Abstract-A nonlinear beamforming aided detector is proposed for multiple-antenna assisted quadrature phase shift keying systems. By exploiting the inherent symmetry of the optimal Bayesian detection solution, a symmetric radial basis function (SRBF) detector is developed which is capable of approaching the optimal Bayesian performance using channel-impaired training data. In the uplink case, adaptive nonlinear beamforming can be implemented effectively by estimating the channel matrix based on the least squares channel estimate. Adaptive implementation of nonlinear beamforming in the downlink case by contrast is much more challenging, and we adopt a cluster-variation enhanced clustering algorithm to directly identify the SRBF centre vectors required for realising the optimal Bayesian detector.

show abstract

“…It can be seen that the optimal Bayesian decision variable (9) takes the structure of a complex-valued RBF network [17] with a Gaussian RBF function. The state subsets X…”

Section: Optimal Bayesian Beamforming Solutionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Nonlinear Beamforming for Multiple-Antenna Assisted QPSK Wireless Systems

Chen

Hanzo

Tan

2008

2008 IEEE International Conference on Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…The inverse of Hammerstein system's static nonlinear function based on B-spline neural network was introduced in [56], and this is described in below for completeness for solving (20).…”

Section: Inversion Of Ofdm Hammerstein Channel's Static Nonlinear mentioning

confidence: 99%

Nonlinear Equalization of Hammerstein OFDM Systems

Hong

Chen

Gong

et al. 2014

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

“…To further exploit the structure of the optimal Bayesian solution (18), the complex-valued RBF weights are set to Note that the standard complex-valued RBF network [28], [29] Fig. 2.…”

Section: Symmetric Radial Basis Function Networkmentioning

confidence: 99%

“…This study extends nonlinear beamforming to wireless systems that employ the complex-valued quadrature phase-shift keying (QPSK) modulation scheme. For QPSK systems, the optimal Bayesian detection solution can be expressed as a complex-valued radial basis function (RBF) network [28], [29]. We further exploit the inherent symmetry of the optimal nonlinear beamforming solution and propose a novel complex-valued SRBF network for adaptively implementing the Bayesian beamforming solution.…”

Section: Introductionmentioning

confidence: 99%

Symmetric Complex-Valued RBF Receiver for Multiple-Antenna-Aided Wireless Systems

Chen

Hanzo

Tan

2008

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-A nonlinear beamforming assisted detector is proposed for multiple-antenna-aided wireless systems employing complex-valued quadrature phase shift-keying modulation. By exploiting the inherent symmetry of the optimal Bayesian detection solution, a novel complex-valued symmetric radial basis function (SRBF)-network-based detector is developed, which is capable of approaching the optimal Bayesian performance using channel-impaired training data. In the uplink case, adaptive nonlinear beamforming can be efficiently implemented by estimating the system's channel matrix based on the least squares channel estimate. Adaptive implementation of nonlinear beamforming in the downlink case by contrast is much more challenging, and we adopt a cluster-variation enhanced clustering algorithm to directly identify the SRBF center vectors required for realizing the optimal Bayesian detector. A simulation example is included to demonstrate the achievable performance improvement by the proposed adaptive nonlinear beamforming solution over the theoretical linear minimum bit error rate beamforming benchmark.Index Terms-Beamforming, complex-valued radial basis function (RBF) network, multiple-antenna wireless system, symmetry, unsupervised clustering.

show abstract

Complex-valued radial basic function network, Part I: Network architecture and learning algorithms

Cited by 125 publications

References 19 publications

Nonlinear Beamforming for Multiple-Antenna Assisted QPSK Wireless Systems

Nonlinear Beamforming for Multiple-Antenna Assisted QPSK Wireless Systems

Nonlinear Equalization of Hammerstein OFDM Systems

Symmetric Complex-Valued RBF Receiver for Multiple-Antenna-Aided Wireless Systems

Contact Info

Product

Resources

About