Discrete Least Square Estimation of Polynomial Models for ECG Data

Abstract

The change of the electrical activity of the heart over time has been recorded by the Electrocardiogram which is called ECG. Electrocardiograms are used to diagnose the condition of patients’ hearts by measuring the heartbeat. However, an ECG generates a lot of information and requires a large amount of memory and storage to process and record this data. In this paper, a discrete least square estimation is used to estimate the coefficient of polynomial models for estimating the ECG signals. We propose the use of discrete least square estimation in order to fit all of the ECG data, in various orders, with polynomial models using separate parts of the ECG data. A simulation study has been conducted in order to compare the proposed polynomial models with a model restricted by using a Percentage Root mean square Difference (PRD). The results show that the proposed model gives low PRD.