Variable Step-size LMS Algorithm Based on Hyperbolic Tangent Function

Li, Long; Zhao, Xuesong

doi:10.1007/s00034-023-02303-8

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the performance of the proposed VSS-Q-Newton algorithm and compare its convergence performance with NLMS, SM-NLMS, Q-Newton, APA, VSS-LMS algorithm [20], and F-Q-Newton [11] in the context of system identification.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…where t is the set-membership error bound. Additionally, in the variable step-size LMS (VSS-LMS) algorithm [20], the step-size is described as On the other hand, the weight update equation of the quasi-Newton (Q-Newton) algorithm is given by [9]…”

Section: Adaptive System Identificationmentioning

confidence: 99%

“…In addition to the aforementioned contributions, various variable step-size adaptive algorithms, as cited in [8], [20]- [22], and others, have been introduced. These algorithms aim both to improve the convergence rate and reduce the steadystate error in comparison to their fixed step-size counterparts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Variable Step-Size Regularization-Based Quasi-Newton Adaptive Filter for System Identification

Bekrani,

Zayyani

2024

IEEE Access

View full text Add to dashboard Cite

The family of least mean square (LMS) based adaptive filtering algorithms suffers from convergence performance limitation due to the sensitivity of such algorithms to the eigenvalue spread of the input correlation matrix. The quasi-Newton family of adaptive filtering algorithms addresses this limitation, but its performance is restricted by the estimation accuracy of the correlation matrix inverse, especially for highly correlated input signals. Furthermore, the convergence rate and the steady-state performance of both LMS and quasi-Newton families are thoroughly depending on their step-sizes. In this paper, a variable stepsize regularized quasi-Newton adaptive algorithm is proposed in the context of system identification. In this algorithm, inspired by the matrix inversion lemma, a modified regularized matrix inverse with a time-varying regularization is computed such that during the convergence, the contribution of matrix inverse in the weight update is reduced, resulting in a more noise-robust algorithm. The paper further provides a convergence analysis of the proposed quasi-Newton algorithm, wherein a variable step-size is proposed to achieve a high initial convergence rate and a low steady-state error in the context of system identification applications.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Adaptive System Identificationmentioning

confidence: 99%