Adaptive Signal Enhancement in clinical cardiac care Systems Using Normalized Median LMS Variants Sulthana Asiya1,*, Md. Rahman Zia-Ur2 1Research Scholar, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Greend Fileds, Vaddeswaram, Guntur, Andhra Pradesh, India 2Professor, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Greend Fileds, Vaddeswaram, Guntur, Andhra Pradesh, India *Corresponding Author: Asiya Sulthana, Research Scholar, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Greend Fileds, Vaddeswaram, Guntur-522502, A.P., India, Email: asiyasulthana1984@gmail.com
Online published on 13 November, 2019. Abstract In this paper, a new variant of elimination of adaptive artifact from Electrocardiography (ECG) signals is presented. ECG is a noninvasive method for indirect assessment of monitoring the stroke volume, cardiac output and other hemodynamic parameters. But this method is affected by various non-stationary artifacts such as sinusoidal artifacts (SA), respiration artifacts (RA), muscle artifacts (MA) and electrode artifacts (EA) while acquiring the ECG signal which leads to ambiguity in diagnosis. Hence these artifacts should be eliminated for accurate diagnosis. For filtering these artifacts, we proposed several hybride adaptive filtering techniques based on conventional Least Mean Square (LMS) algorithm. These are Normalized Median LMS (NMLMS), Sign Regressor NMLMS(SRNMLMS), Sign NMLMS (SNMLMS), Sign Sign NMLMS (SSNMLMS) are the hybride variants of LMS algorithm. Based on these adaptive algorithms, we developed several adaptive signal enhancement units (ASEUs) and performance is evaluated on the real ECG signal components obtained from MIT-BIT database. Among these techniques, SRNMLMS based ASEU performs better in the filtering process. The signal to noise ratio improvement (SNRI) for this algorithm is calculated as 21.6985 dBs, 7.9864 dBs, 7.8346 dBs and 10.6857 dBs respectively for SA, RA, MA and EA. Hence, the SRMLMS based ASEUs are more suitable in ECG signal filtering in real time health care sensing systems. Top Keywords Adaptive Filter, Hemodynamic parameters, Electrocardiography, signal enhancement, stroke volume. Top |