Fuzzy-Logic Adapted for LMS Algorithm Based on q-Gradient

This paper studies the system identification problem using the q-least mean square (qLMS) algorithm. Particularly, the fuzzy-logic scheme is considered here. The proposed fuzzy-logic trained-qLMS (FLT-qLMS) algorithm is developed based on fuzzy-logic adapted, which averts the q value selection probl...

Full description

Saved in:
Bibliographic Details
Published inChinese Control Conference pp. 2914 - 2917
Main Authors Lu, Lu, Yang, Xiaomin
Format Conference Proceeding
LanguageEnglish
Published Technical Committee on Control Theory, Chinese Association of Automation 26.07.2021
Subjects
Adaptation models
Adaptive filtering
Filtering
Filtering algorithms
Fuzzy-logic
Kernel
q-gradient
Simulation
System identification
Training
Online AccessGet full text
ISSN1934-1768
DOI10.23919/CCC52363.2021.9549718

Cover

More Information
Summary:This paper studies the system identification problem using the q-least mean square (qLMS) algorithm. Particularly, the fuzzy-logic scheme is considered here. The proposed fuzzy-logic trained-qLMS (FLT-qLMS) algorithm is developed based on fuzzy-logic adapted, which averts the q value selection problem in practical applications. However, the performance of FLTqLMS is subjected to the conflicted requirement of fixed step size. To completely devoid of parameter selection problem, a new fuzzy-logic scheme is further developed for online adjusting q value and step size simultaneously, resulting in enhanced FLT-qLMS (EFLT-qLMS) algorithm. Extensive simulations indicate the refined performance of the proposed algorithms in the context of system identification.
ISSN:1934-1768
DOI:10.23919/CCC52363.2021.9549718