Cardiac Arrhythmia, CHF, and NSR Classification With NCA-Based Feature Fusion and SVM Classifier

An arrhythmia is an irregular heartbeat that causes abnormal heart rhythms. Manual analysis of electrocardiogram (ECG) signals not sufficient to quickly detect cardiac arrhythmias. This study proposes a deep learning approach based on convolutional neural network (CNN) architecture for the classification arrhythmias (ARR), congestive failure (CHF), and normal sinus rhythm (NSR). First, ECG signal converted into 2D image using time-frequency conversion. The scalogram constructed continuous wavelet transform extract dynamic features. With CNN, each broken down heartbeats, then grayscale heartbeat. Morphological feature extraction was performed by segmenting QRS complex detecting P T waves. A third dual-tree (DT-CWT). In addition, all extracted features are combined neighborhood component (NCA), selected classify support vector machine (SVM) classifier.