Classificação automática de cardiopatias baseada em eletrocardiograma

• Ano de defesa: 2006
• Autor(a) principal: Bueno, Nina Maria
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; BR; Programa de Pós-graduação em Engenharia Elétrica; Engenharias; UFU
• Palavras-chave em Português: ECG - Eletrocardiograma, exame não invasivo dos sinais elétricos cardíacos; Cardiopatia - Doença que acomete o coração; RNA - Rede neural artificial; Modelo AR - Modelo matemático auto-regressivo; Eletrocardiografia; Coração - Doenças - Diagnóstico; ECG - electrocardiograph, no invasive examination of the cardiac electric signals; Cardiopathy - Heart disease; RNA - Artifitial neural network; AR model - Auto-regressive model; CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://repositorio.ufu.br/handle/123456789/14594

This work is dedicated to study of the recognition and classification of cardiac disease, diagnosised through the electrocardiogram ECG. This examination is normally used in heart medical center, emergency, intensive therapy, and with complement diagnosis in heart disease as: acute myocardium infarction, bundle block branches, hypertrophy and others. The software was developed for support to the model, with focus on extraction of ECG signal characteristics, and an artificial neural network for recognition of diseases. For extraction these characteristics, we have used a auto-regressive model, AR, with the algorithm least mean square LMS, to minimize the minimum error. The neural network, with architecture multilayer perceptron and back propagation algorithm of training, was chosen for the recognition of the standards. The method was showed efficient.