Convergence Performance Evaluation of MSF-Based LMS Adaptive Algorithm

• Published in: 2019 16th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) pp. 597 - 600
• Main Authors: Vanamadi, Ravi, Kar, Asutosh, Burra, Srikanth, Anand, Ankita, Majhi, Banshidar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2019
• Subjects: Adaptive algorithms; adaptive filter; Adaptive filters; Convergence; Filtering algorithms; Finite impulse response filters; Information technology; least mean square (LMS); mean convergence (MC); mean-square conver-gence (MSC); multiple sub-filters (MSF); Performance evaluation; Signal to noise ratio; Simulation; Telecommunications
• DOI: 10.1109/ECTI-CON47248.2019.8955136

This article analyzes the mean convergence (MC), and the mean square convergence (MSC) of a least mean square (LMS) multiple sub-filter (MSF) based adaptive filter for correlated Gaussian data under an independent assumption. In this analysis, it is assumed that the impulse response of the unknown system length is equal to the length of the finite impulse response (FIR) LMS adaptive filter. This research work suggests improving the MC and MSC of the adaptive filter, by replacing the fixed tap-length single long filter into a fixed tap-length multiple sub-filters/bank of sub-filters. The computer experimental simulation results illustrate to support the derived analysis.