Classification of ECG patterns for diagnostic purposes by means of Neural Networks and Support Vector Machines

This paper presents an application of Neural Networks (NNs) and Support Vector Machines (SVMs) for the detection and classification of heartbeats in electrocardiogram (ECG) signals. The preprocessing algorithm for the beats detection is based on well-known Pan-Tompkins´ algorithm. The proposed approach is robust to different types of noise and shows good performances both in beat analysis and QRS morphology extraction. The proposed method in combination with radial basis function SVM and adaptive NNs, brought remarkable results on the classification of different kind of cardiac arrhythmia as shown by suitable numerical simulations presented at the end of the paper.