Machine learning algorithms for real time arrhythmias detection in portable cardiac devices: Microcontroller implementation and comparative analysis

Santiago Rua, Santiago A. Zuluaga, Alfredo Redondo, Andres Orozco-Duque, Jose V. Restrepo, John Bustamante

Producción científica: Capítulo del libro/informe/acta de congresoPonencia publicada en las memorias del evento con ISBNrevisión exhaustiva

3 Citas (Scopus)

Resumen

This paper presents the development of two machine learning algorithms on a 32-bit ARM® Cortex® M4 microcontroller core from Freescale Semiconductors. A neural network (ANN) and a support vector machine (SVM) were implemented for real time detection of ventricular tachycardia (VT) and ventricular fibrillation (VF), and they were compared in terms of accuracy. In the feature extraction step a Fast Wavelet Transform (FWT) was used; which was analyzed using the time-frequency characteristics of energy in each sub-band frequency. For the training and validation algorithms, signals from MIT-BIH database with normal sinus rhythm, VF and VT in a time window of 2 seconds were used. Validation results achieve test accuracy of 99.46% by ANN and SVM in VT/VF detection.

Idioma originalInglés
Título de la publicación alojadaSTSIVA 2012 - 17th Symposium of Image, Signal Processing, and Artificial Vision
Páginas50-55
Número de páginas6
DOI
EstadoPublicada - 2012
Evento17th Symposium of Image, Signal Processing, and Artificial Vision, STSIVA 2012 - Medellin, Colombia
Duración: 12 sep. 201214 sep. 2012

Serie de la publicación

NombreSTSIVA 2012 - 17th Symposium of Image, Signal Processing, and Artificial Vision

Conferencia

Conferencia17th Symposium of Image, Signal Processing, and Artificial Vision, STSIVA 2012
País/TerritorioColombia
CiudadMedellin
Período12/09/1214/09/12

Huella

Profundice en los temas de investigación de 'Machine learning algorithms for real time arrhythmias detection in portable cardiac devices: Microcontroller implementation and comparative analysis'. En conjunto forman una huella única.

Citar esto