Analyse du signal ECG par réseau adaptif d’ondelettes en vue de la reconnaissance de pathologies cardiaques

Abstract

The electrocardiogram (ECG) signal is widely employed as one of the most important tools in clinical practice in order to assess the cardiac status of patients. It represents the variations of the electrical activity of the heart as function of time. The classification of the ECG beats into different pathologic disease categories is a complex pattern recognition task. In this thesis, we propose a method for ECG heartbeat pattern recognition using wavelet neural network. An algorithm based on wavelet for QRS detection is first implemented, and then a wavelet neural network Classifier is developed. The experimental results obtained by testing the proposed approach on ECG data from the MIT-BIH arrhythmia database demonstrate the efficiency of such an approach when compared with other methods existing in the literature