Detection of atrial fibrillation using continuous wavelet transform and wavelet coherence

摘要

Atrial fibrillation (AF) is a type of heart ailment that occurs when atria beats quicker than normal to move blood from atria to the ventricles. Our present study proposes a technique to detect AF ECG patterns with the use of continuous wavelet transform (CWT), wavelet coherence (WTC) is presented. The wavelet coherence function finds common frequencies between two signals and evaluates similarity of the two signals. The mother wavelet used is db4. The ECG variation of atrial fibrillation (AF) is observed in lead Ⅱ of ECG. For the detection of normal and AF beats, WTC output values are given as the input features for the Levenberg-Marquardt neural network (LMNN) classifier. The data was collected from MIT/BIH AF database.