Abstract:
Efficient Blind Source Separation for Next Generation Wireless
Networks
Independent component analysis (ICA) is a signal processing technique for separating
statistically independent and non-Gaussian mixed source signals. It has its applications
in different areas e.g., wireless communication, speech and biomedical signal processing,
vibration analysis, and machinery fault diagnosis. In wireless co
well as in quasi static wireless channels, even for smaller data block lengths. Simulation
results show that the proposed transceiver system improves the un-mixing performance
of the batch ICA algorithms in highly time varying channels. Then, we propose a
generalized framework called the modified Infomax algorithm that improves the separation
performance of the batch ICA algorithms for reduced lengths of the transmitted data
blocks in wireless MIMO systems. Finally, we propose a hardware design of the mixing
model for the ICA algorithms. The proposed model represents unity mixing, scaled
mixing and ill-conditioned mixing. The proposed model may serve as a test bench
for evaluating the performance of the ICA algorithms. Simulation results obtained are
such that the unity mixing provides excellent performance of the batch ICA algorithms,
while the scaled mixing provides good performance and the ill-conditioned mixing gives
worse performance of the algorithms
