The Extended Feature LMS Algorithm: Exploiting Hidden Sparsity for Systems with Unknown Spectrum

Yazdanpanah, Hamed; Apolinario, J.A.

doi:10.1007/s00034-020-01461-3

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the feature LMS (F-LMS) algorithm is proposed to outperform the classical LMS algorithm by exploiting hidden sparsity in some systems, such as lowpass, highpass, and bandpass systems. [8][9][10] However, the proposed F-LMS algorithm has two drawbacks: (i) its application is restricted to some particular systems, such as lowpass, highpass, and bandpass systems; (ii) we do require some a priori knowledge about the spectral characteristics of unknown system, otherwise its performance can be inferior to the conventional LMS algorithm. Therefore, we should avoid using the F-LMS algorithm for an arbitrary system or when we do not have a priori information about the spectral characteristics of the system.…”

Section: Introductionmentioning

confidence: 99%

Improved feature least mean square algorithm

Yazdanpanah

2022

Adaptive Control & Signal

Self Cite

View full text Add to dashboard Cite

In this paper, we propose the improved feature least-mean-square (IF-LMS) algorithm to exploit hidden sparsity in unknown systems. Recently, the feature least-mean-square (F-LMS) algorithm has been introduced, but its application is limited to particular systems since it uses predetermined feature matrices. However, the proposed IF-LMS algorithm utilizes the stochastic gradient descent (SGD) method to learn feature matrices; thus, it can be used in any system that the classical LMS algorithm is applicable. Hence, by employing a learnable feature matrix, the IF-LMS algorithm has a vast application area as compared to the F-LMS algorithm. Moreover, mathematically, we discuss some parameters of the IF-LMS algorithm. Simulation results, in synthetic and real-life scenarios, demonstrate that the IF-LMS algorithm has superior filtering accuracy to the well-known LMS algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%