Robust spline adaptive filter

Abstract

The invention discloses a robust spline adaptive filter, and belongs to the field of digital filter design. According to the spline adaptive filter, an optimal nonlinear unknown system is approximatedby adopting a spline function, and the resistance to pulse interference is enhanced by adopting a method of performing symbolic operation on error signals. The spline adaptive filter can be used foroccasions where electronic, speech and communication systems are subjected to nonlinear distortion and pulse noise interference.

Description

technical field [0001] The invention discloses a robust spline adaptive filter, which belongs to the field of digital filter design. Background technique [0002] Adaptive filtering has been widely used in the fields of channel equalization, noise elimination, noise control and so on. Many problems of adaptive filtering can be summarized as system identification problems, but in practical applications, there are often nonlinear distortions, and some nonlinear adaptive filters are proposed to solve the problem, such as the Volterra adaptive filter (VAF), Function Link Adaptive Filter (FLAF), Spline Adaptive Filter (SAF) [Scarpiniti M, Comminiello D, Parisi R, Uncini A.Nonlinear spline adaptive filtering, Signal Proceing, 2013, 93(4) :772–783] and so on, where the spline adaptive filter has a control point vector, which can make the spline control point simulate and approach nonlinear distortion through iteration, so that the unknown system can be well estimated. [0003] In...

AI Technical Summary

Problems solved by technology

[0003] In reality, in the actual nonlinear distortion situation, in addition to the interference of additive Gaussian white noise, the instrument or communication equipment sometimes also receives the interference of impulse noise. In this case, the impulse noise will make the sample The filtering effect of the adaptive filter is significantly deteriorated (in the adaptive filter literature, the adaptive filter with the ability to resist pulse interference is called robust), and it is even impossible to estimate the unknown nonlinear system

Images