Automatic classification of arrhythmic beats using Gaussian Processes

We propose a novel approach to the automated discrimination of normal and ventricular arrhythmic beats. The method employs Gaussian Processes, a non-parametric Bayesian technique which is equivalent to a neural network with infinite hidden nodes. The method is shown to perform competitively with other approaches on the MIT-BIH Arrhythmia Database. Furthermore, its probabilistic nature allows to obtain confidence levels on the predictions, which can be very useful to practitioners.