Wavelet Transformation, Artificial Neural Network and Neuro-Fuzzy Approach for CVD Detection and Classification An Overview

Abstract

Automatic electrocardiogram (ECG) beat classification is essential for timely diagnosis of dangerous heart conditions. So AI based arrhythmia recognition is effective for the management of cardiac disorders. Various techniques have been studied to classify arrhythmias. A simple wavelet transform based technique is proposed to classify normal sinus rhythm (NSR) and various cardiac arrhythmias including atrial premature contraction (APC), premature ventricular contraction (PVC), super ventricular tachycardia (SVT), ventricular tachycardia (VT) and ventricular fibrillation (VF). Wavelet transform may be performed on ECG data with normal sinus rhythm as well as various arrhythmias. Accuracy of most of existing methods for detecting NSR, APC, PVC, SVT, VT and VF is between 90% to 98%. Expanding the overall data set greatly reduces overall accuracy due to significant variation in ECG morphology among different patients. As a result, morphological information must be coupled with timing information, which is more constant among patients, in order to achieve high classification accuracy for larger data sets. An AI based detection and classification techniques coupled with wavelet based processing is suggested which will extend accuracy even to large data sets.