Detection and classification of cardiac arrhythmias using machine learning techniques

• Grant number: 19/26911-6
• Support type: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): May 01, 2020
• Effective date (End): April 30, 2021
• Field of knowledge: Engineering - Electrical Engineering
• Principal researcher: Magno Teófilo Madeira da Silva
• Grantee: Natália Nagata
• Home Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

In the literature, many computational methods for automatic detection of cardiac arrhythmias from ECG signals have been proposed. The diagnosis of these diseases by the cardiologist usually takes a long time since it is a complex task due to the variable morphological characteristics of the ECG signal. However, due to the high error rates of computational techniques and the growth of machine learning area, research in automatic diagnostic has attracted attention. In this work, we propose the use of neural networks for the identification and classification of cardiac arrhythmias. In particular, three types of networks will be considered: (I) multilayer perceptron (MLP), (II) convolutional neural network (CNN) and (III) recurrent neural network (RNN).