Study on a Convex Combination of Two Fractional Order Adaptive Filters

This paper presents a method of convex combination of two different fractional order adaptive filters. The basic idea of fractional order least-mean-square (FOLMS) algorithm is to apply fractional order gradient method (FOGM) to conventional least-mean-square (LMS) algorithm. The advantage of the FO...

Full description

Saved in:
Bibliographic Details
Published in2022 8th International Conference on Control Science and Systems Engineering (ICCSSE) pp. 46 - 51
Main Authors Lu, Jiajie, Wang, Yong
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.07.2022
Subjects
convex combination
fractional order adaptive filter
LMS
Online AccessGet full text
DOI10.1109/ICCSSE55346.2022.10079765

Cover

More Information
Summary:This paper presents a method of convex combination of two different fractional order adaptive filters. The basic idea of fractional order least-mean-square (FOLMS) algorithm is to apply fractional order gradient method (FOGM) to conventional least-mean-square (LMS) algorithm. The advantage of the FOLMS algorithm is to obtain the desired convergence speed or accuracy by adjusting the fractional order, but there is a contradiction between the accuracy and speed. Therefore, a convex combination strategy is considered, which can combine both convergence accuracy and rapidity; namely, the overall filter has faster convergence speed in non-stationary scenarios, and better convergence accuracy in stationary scenarios. The effectiveness and advantages of the algorithm are verified by illustrative simulations.
DOI:10.1109/ICCSSE55346.2022.10079765