Electrocardiogram signal processing and analysis in real time

• Grant number: 12/07071-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2012
• End date: April 30, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Regina Célia Coelho
• Grantee: Fernanda Lembo Vedovello
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Federal de São Paulo (UNIFESP). Campus São José dos Campos. São José dos Campos , SP, Brazil

Abstract

The electrocardiographic allows the analysis of heart beating noninvasively, and can diagnose heart disease, including arrhythmias. The graphic record of the electrocardiographic signal, also known as electrocardiogram (ECG), shows characteristic waves designated by the letters P, Q, R, S and T, among others. The R wave is characterized by being a sharp peak in the signal, and it is related to a ventricular contraction that promotes the circulation of blood throughout the body. Based on the detection of R wave peak of ECG, in this project it is proposed the classification of heart beating into normal beat, bradycardia and tachycardia. We are using the artificial neural network called MLP (Multi-Layer Perceptron) with the Backpropagation algorithm. This artificial neural network will be trained and tested with ECG signals from database of MIT-BIH. The main distinguishing feature of this project is the implementation of artificial neural network could, in real time, detect R wave peaks and classify the heart beats. (AU)