Robust variable-parameter sparse self-adaptive filter

Abstract

The invention discloses a robust variable-parameter sparse self-adaptive filter, and belongs to the field of digital filter designing. The filter mainly utilizes a time-varying step size parameter anda regularization parameter controlling zero attractor intensity to increase convergence speed of the self-adaptive filter and reduce steady-state misadjustment thereof. Compared with a traditional symbol filter, the robust variable-parameter sparse self-adaptive filter disclosed by the invention has better convergence performance when input is a white signal and influences of impulse noises exist. The robust variable-parameter sparse self-adaptive filter disclosed by the invention can be applied to the fields of electronics and communication equipment of echo cancellation, noise cancellers, signal enhancement and interference pulses and the like.

Description

technical field [0001] The invention discloses a robust variable parameter sparse adaptive filter, which belongs to the field of digital filter design. Background technique [0002] The traditional least mean square filter (LMS) and normalized least mean square filter (NLMS) have a wide range of applications in adaptive filters, such as adaptive echo cancellation, active noise control and adaptive noise cancellation. [0003] Convergence speed, steady-state misadjustment and anti-pulse interference ability are three important performance indicators of adaptive filter. The level of steady-state misalignment determines the accuracy that the adaptive filter can achieve in approaching the unknown system, and the speed of convergence determines the time it takes for the adaptive filter to approach the unknown system. The ability to resist pulse interference determines the robustness of the adaptive filter. Stickiness, these three indicators affect the quality of signal processin...

AI Technical Summary

Problems solved by technology

In addition, in some applications, the unknown system estimated by the adaptive filter may be sparse, and the use of SE-LMS or VSSA adaptive filter cannot take full advantage of its sparse characteristics to speed up the convergence

Images