LMS algorithm derivatives used in real-time filtering of ECG signals: A study case on performance evaluation

Abstract

The paper presents two derivatives of the Least Mean Square (LMS) algorithm, which can be utilized in real-time processing of the electrocardiographic (ECG) signals: (i) the Normalized LMS (NLMS), and (ii) Sign based LMS (S-LMS) algorithms. The algorithms are suitable for implementation on Digital Signal Processors (DSPs) or on Field Programmable Gates Arrays (FPGAs), and the practical implementations of their equations are presented. The implementation of the iterative steps can be done in an easy manner with low computational complexity with good effect on the filtering process, for both types of perturbations, electronic noises and power line interference signals, which can occur on ECG signals.