Radial basis function network assisted single-user channel estimation by using a linear minimum mean square error detector under impulsive noise

Abstract

This paper proposes a novel robust channel estimator for direct-sequence code-division multiple-access systems with time-varying multipath fading channels under impulsive noise. The channel estimation approach presented is based on the linear single-user minimum mean square error criteria and uses a radial basis function network to eliminate the effect of impulsive noise. A threshold mechanism is also developed to eliminate the disadvantage of the proposed estimator under Gaussian noise. Simulation results clearly show that the proposed estimator eliminates the effect of impulsive noise and improves the performance of channel estimation under impulsive noise.