A LMS algorithm with stochastic momentum factor

A stochastic momentum factor least-mean-square algorithm (SMLMS) is proposed. The SMLMS algorithm considers the momentum factor alpha k as a stochastic attenuation factor so as to provide a better error bursting compensation and a small misadjustment for an adaptive filter. It is feasible to implement the SMLMS algorithm in a DSP (digital signal processing) chip or hardware with only a slight increase in computation over the MLMS and the LMS algorithms. Computer simulation results on the application of the SMLMS algorithm to adaptive FIR (finite impulse response) and IIR (infinite impulse response) filters are presented.<
>