Improved recognition of Sub-nyquist sampled cyclic Features using graph filter-bank Denoiser

In virtual antenna array based cognitive femtocell system, most of the research works have utilized conventional Nyquist rate sampling at the receiver side to recover the desired signal-of-interest (SOI). In this work, modulated wideband converter (MWC) based sub-Nyquist sampling technique is used to capture multi-band filtered OFDM signal by the femto-cell receiver. The compressive cyclostationary features of the received signal are processed by a graph filter-bank and a deep auto-encoder respectively. Computer simulation results show that the cyclic feature classification performance of the proposed method is better than that of only deep auto-encoder, under frequency selective Rayleigh fading channel andadditive white Gaussian noise (AWGN). © 2020 IEEE.

Cognitiveradio; Deep auto-encoder; Filtered OFDM; Graph filter-bank; Sub-Nyquist sampling Antenna arrays; Channel coding; Fading channels; Femtocell; Filter banks; Frequency selective fading; Learning systems; Rayleigh fading; Signal encoding; Signal receivers; Signal sampling; White noise; Feature classification; Femtocell systems; Modulated wideband converters (MWC); Received signals; Sub-Nyquist sampling; Under frequencies; Virtual antenna arrays; White Gaussian Noise; Gaussian noise (electronic)

VIVO