Probabilistic Neural Network Approach for Classifying Ventricular Tachyarrhythmias

Accurate observation of cardiac dysrhythmias are extremely important for clinical applications. Arrhythmias are one of the leading causes of cardiovascular mortality, direct evidences of clinical records has been lacking. Authors of this paper presents a unified approach for classifying ventricular tachyarrhythmias. The methodology adopted by the authors of this work are discrete wavelet transform (DWT) for extracting the features from ECG signals, cross recurrence quantification analysis (CRQA) for calculating the recurrent rate values using the cross recurrence plot (CRP) toolbox of Matlab and probabilistic neural network (PNN) concept for classification of ECG signals.