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

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.