Ventricular Arrhythmia Detection Techniques for ECG Signal: A Survey Approach

Abstract

Electrocardiogram (ECG) represents the electrical activity of the heart and is used to measure the rate and regularity of heartbeats. In this paper we propose a method for an Independent Component Analysis (ICA) based detection and classification of the ventricular arrhythmia. The malignant ventricular arrhythmia database from www.physionet.org/physiobank/database/vfdb has been utilized for evaluating the algorithm over MATLAB interface. This scheme assimilates ICA and probabilistic neural network for classifying critical arrhythmia like Ventricular Fibrillation, Ventricular Flutter and V-Tachycardia into VF rhythms and decomposes ECG signals that are statistically mutual independent into basis vectors that serve as ICA components and when projected with RR interval constitutes the feature vector. The independent components (ICs) are arranged strategically for their selection. Probabilistic neural network will be used as a classifier to evaluate the proposed method. The selected features are used to train the classifier to recognize different ventricular arrhythmias.

Keywords: Arrhythmia, electro cardio graph (ECG), fibrillation, ventricular tachycardia (VT), ventricular flutter (VF)

Cite this Article

Taru Aggarwal, Sharda Vashisth. Ventricular Arrhythmia Detection Techniques for ECG Signal: A Survey Approach. Research and Reviews: Journal of Neuroscience (RRJoNS). 2015; 5(1): 25–30p.