作者： L. Hanzo , S. Chen , C. J. Harris , A. Wolfgang
DOI:
关键词: Detector 、 Algorithm 、 Artificial neural network 、 Radial basis function 、 Kernel density estimation 、 Beamforming 、 Bit error rate 、 Signal-to-noise ratio 、 Computer science 、 Radial basis function network 、 Stochastic approximation
摘要: A powerful symmetrical radial basis function (RBF) aided detector is proposed for nonlinear detection in so-called rank-deficient multiple-antenna assisted beamforming systems. By exploiting the inherent symmetry of optimal Bayesian solution, RBF becomes capable approaching performance using channel-impaired training data. novel least bit error algorithm derived adaptive based on a stochastic approximation to Parzen window estimation output's probability density function. The solution providing signal-to-noise ratio gain excess 8 dB against theoretical linear minimum rate benchmark, when supporting four users with aid two receive antennas or seven employing antenna elements.