V Congreso Latinoamericano de Ingeniería Biomédica (CLAIB2011)

ECG Features Extraction Methods: Comparative Analise
Evangelista Neto João, Suárez León Alexander Alexeis, Vázquez Seisdedos Carlos Román, López Mora Nelson A, Cabral Leite Jandecy, Limao Oliveira Roberto Celio

##manager.scheduler.building##: Palacio de Convenciones de La Habana
##manager.scheduler.room##: Sala 12
Fecha: 2011-05-19 12:00  – 01:30
Última modificación: 2011-05-03 11:02


ECG Feature Extraction plays a significant role in diagnosing most of the cardiac diseases. In this paper, a comparison between three ECG feature extraction methods is presented. The methods are: Linear Principal Components Analysis (PCA), Discrete Cosine Transformation (DCT) and Kernel Principal Components Analysis (KPCA). A Multilayer Perceptron is used as classifier and beats for training and validation of the classifier are extracted from twelve            MIT – BIH Arrhythmia Database registers. The performance of the three classifiers is discussed and a simple execution time evaluation is performed.