Heartbeat Classification Using MLP and Random Forest Techniques

This work aims at presenting a method for heartbeat classification based on multi-layer perceptron (MLP) and random forest (RF) techniques applied to the first difference of ECG signals. From the MIT-BIH Arrhythmia Database, each annotated P-QRS segment was extracted, low-pass filtered, and the first-order difference was used as input for the neural networks. The MLP and Random Forest were used to obtain a model for classifying the heartbeats. The results were compared with other algorithms existing in the literature, and the model developed produced good results and noticed improvements when using the first difference.