ECG-Based Heart Arrhythmia Diagnosis Through Attentional Convolutional Neural Networks

Authors: Ziyu Liu, Xiang Zhang

Overview

In this repository, we provide the code for paper: ECG-Based Heart Arrhythmia Diagnosis Through Attentional Convolutional Neural Networks. The proposed deep learning model: Attention-Based Convolutional Neural Networks (ABCNN) take advantage of CNN and multi-head attention, to work straight on raw ECG data and extract the informative dependencies automatically for accurate arrhythmia detection.

Code

ABCNN_ECG.py: the implementation of the proposed ABCNN model.

Dataset

Please find the dataset in MIT-BIH Arrhythmia Database Directory.