Detection of pathological and normal heartbeat using wavelet packet, support vector machines and multilayer perceptron

  • Alejandro J. Orozco-Naranjo Universidad del Quindío, Armenia
  • Pablo A. Muñoz-Gutiérrez Universidad del Quindío, Armenia
Keywords: Classification, features extraction, heartbeats, supervised learning machines, Wavelet packets.

Abstract

This paper presents the results obtained by developing a methodology to detect 5 types of heartbeats (Normal (N), Right bundle branch block (RBBB), Left bundle branch block (LBBB), Premature atrial contraction (APC) and Premature ventricular contraction (PVC)), using Wavelet transform packets with non-adaptative mode applied on features extraction from heartbeats. It was used the Shannon function to calculate the entropy and It was added an identification nodes stage per every type of cardiac signal in the Wavelet tree. The using of Wavelet packets transform allows the access to information which results of decomposition of low and high frecuency, giving providing a more integral analysis than achieved by the discrete Wavelet transform. Three families of mother Wavelet were evaluated on transformation: Daubechies, Symlet and Reverse Biorthogonal, which were results from a previous research in that were identified the mother Wavelet that had higher entropy with the cardiac signals. With non-adaptive mode, the computational cost is reduced when Wavelet packets are used; this cost represents the most marked disadvantage from the transform. To classify the heartbeats were used Support Vector Machines and Multilayer Perceptron. The best classification error was achieved employing Support Vector Machine and a radial basis function; it was 2.57 %. 

Author Biographies

Alejandro J. Orozco-Naranjo, Universidad del Quindío, Armenia
Ingeniero Electrónico, Grupo de Automatización y Máquinas de Aprendizaje, Facultad de Ingeniería
Universidad del Quindío, Armenia
Pablo A. Muñoz-Gutiérrez, Universidad del Quindío, Armenia
Magister en Ingeniería Eléctrica, Grupo de Automatización y Máquinas de Aprendizaje, Facultad de Ingeniería
Universidad del Quindío, Armenia
How to Cite
Orozco-Naranjo, A. J., & Muñoz-Gutiérrez, P. A. (2011). Detection of pathological and normal heartbeat using wavelet packet, support vector machines and multilayer perceptron. TecnoLógicas, (31), 73-91. https://doi.org/10.22430/22565337.102

Downloads

Download data is not yet available.
Published
2011-11-30
Section
Research Papers