Comparison of shallow and deep learning methods of ECG signals clas-sification for arrhythmia detection

The research aimed to compare the classification performance of arrhythmia from ECG signal dataset Massachusetts Institute Technology–Beth Israel Hospital (MIT-BIH) database. Shallow learning methods that were used in this study are Support Vector Machine, Naïve Bayes, and Random Forest. 1D Convolutional Neural Network (1D CNN), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU) deep for study. models tested on a with 140 samples grouped into four class labels, each sample has 2160 features. Those performance. This shows Forest CNN have best