Heart Rate Variability Investigation of ECG Signal By Means of Windows and Wavelet Transform

Abstract

An electrocardiogram (ECG) is the gold standard for diagnosing heart conditions because it is painless and takes no physical contact with the patient. The electrophysiology of cardiac disorders and ischemia alterations can be better understood using data from a cleaned ECG signal. There is a wealth of useful data pertaining to the circulatory system and heart function that can be gleaned from this study. This study's goal is to develop a method for the automatic diagnosis of cardiac arrhythmias from an electrocardiogram (ECG) signal. This thesis employs Windows and wavelets processing techniques to identify heart arrhythmias. In the framework of preliminary experiments in two prospective application domains smokers and non-smokers. This publication explores the creation of suitable HRV signal processing algorithms. Automatic detection of cardiac arrhythmias in an ECG signal begins with RR interval detection. The electrocardiogram is recorded using a laboratory view. Using a windows and wavelet based approach; the RR interval is detected from the continuous ECG data. The results show clear differences between non-smokers and smokers, with an 80% accuracy rate in classifying the two groups.