Review of ECG arrhythmia classification using deep neural network

Abstract Recently, Deep Learning (DL) or Deep Neural Network has become a focus of research in diverse fields, including medical and healthcare, where early identification of electrocardiogram (ECG) disturbances is very helpful in healthcare management. This paper provides a thorough overview of the new DL approaches used for classification purposes to the ECG signal. This research explores different types of DL techniques, such as ResNet, InceptionV3, Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM). In many cases, CNN is mostly used as the appropriate technique for extraction of useful features.