Artifact Cancellation from Cardiac Signals in Health Care Systems using a Zoned Adaptive Algorithm
Asiya Sulthana1, Zia Ur Rahman2

1Asiya Sulthana, Department of Electronics and Communication Engineering, K L University, Vaddeswaram, Guntur (Andhra Pradesh), India.
2Md. Zia Ur. Rahman, Department of Electronics and Communication Engineering, K L University, Vaddeswaram, Guntur (Andhra Pradesh), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 988-993 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7064068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Electrocardiogram (ECG) is a noninvasive technique for indirect evaluation of volume of stroke, output related to cardiac is monitoredalsoobservation ofaddedparameters that are hemodynamic thru changes related to blood volume is done within the body. Changes taking place in the blood volume inside a certain body segment due to several physiological processes are extracted in the form of the impedance variations of the body segment. The Analysis of ECG facilitates the heart stroke volume in sudden cardiac arrest. In the clinical environment ECG signals are affected by various physiological and non-physiological artifacts.As these artifacts are not stationary, we propose adaptive filtering techniques to improve ECG signals. In this paper we used normalized version of Dead Zone Least Mean Square (NDZLMS) adaptive techniques to remove artifacts in ECG signals. So as to minimize the computational complexity, this DZLMS is combined with sign algorithms and results Sign Regressor NDZLMS (SRNDZLMS), Sign NDZLMD (SNDZLMS), Sign Sign NDZLMS (SSNDZLMS) algorithms. Based on these algorithms, several adaptive signal enhancement units (ASEUs) are developed and validated on the real ECG signal components.To ensure the ability of these algorithms, four experiments were performed to eliminate the various artifacts such as sinusoidal artifacts (SA), respiration artifacts (RA), muscle artifacts (MA) and electrode artifacts (EA). Among these techniques, the ASEU based on SRNDZLMS performs better with respect to process of filtering. The signal to noise ratio improvement (SNRI) for this algorithm is calculated as 21.8684 dB, 8.4544 dB, 8.6966 dB and 8.7101 dB respectively for SA, RA, MA and EA. Hence, the SRNDZLMS based ASEUs are more suitable for filtering ECG signal in real health care monitoring systems.
Keywords: Adaptive Filter, Artifacts, Electrocardiogram, Signal Enhancement, Stroke Volume

Scope of the Article: Healthcare Informatics