Adaptive Modeling and Identification of Nonlinear MIMO Channels Using Neural Networks - Adaptive Signal Processing in Wireless Communications - page 146

0.7

0.6

0.5

g 1 ( x )

0.4

NN 1 ( x )

0.3

0.2

0.1

0

0 0.5 1 1.5 2

x

FIgure 5.13 g 1 ( x ) and NN 1 ( x ) (normalized): time-varying case.

0.45

0.4

g 2 ( x )

0.35

0.3

NN 2 ( x )

0.25

0.2

0.15

0.1

0.05

0 0.5 1 1.5 2

x

FIgure 5.14 g 2 ( x ) and NN 2 ( x ) (normalized): time-varying case.

consists of a NN MIMO channel estimator (NNCE) and a ZF V-BLAST (zero-forcing
V-BLAST) detection algorithm [1, 7, 11]. The NNCE performs an online estimation of
the nonlinear MIMO channel. The estimated channel state information (CSI) is pro-
vided to the ZF V-BLAST detection algorithm, which gives an estimation of the trans-
mitted symbols ( Figure 5.16 ).