We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Nonlinear spline prioritization optimization adaptive filter with arctangent-exponential hyperbolic cosine.
- Authors
Guo, Wenyan; Zhi, Yongfeng; Feng, Kai
- Abstract
This paper presents a new spline prioritization optimization adaptive filter with arctangent-exponential hyperbolic cosine (SPOAF-ARC-EHC) to solve the high steady-state error in colored and/or impulsive noise environments. Different from the traditional spline adaptive filtering algorithm, the weight update of the spline prioritization optimization adaptive filter (SPOAF) is only based on the linear error, and the update of the spline control points is based on the error of the whole system. To improve the robustness of the proposed SPOAF algorithm, the linear part and the nonlinear part use independent cost functions. More specifically, we utilize the arctangent function (ARC) as the cost function for the linear part and the exponential hyperbolic cosine as the loss function for the nonlinear part. Through simulation, it is shown that the proposed algorithm significantly reduces the steady-state error compared with the existing algorithms in a colored and/or impulsive noise environment.
- Subjects
ADAPTIVE filters; COST functions; SPLINES; COSINE function; NONLINEAR functions
- Publication
Nonlinear Dynamics, 2022, Vol 110, Issue 1, p611
- ISSN
0924-090X
- Publication type
Article
- DOI
10.1007/s11071-022-07636-8