Paper Title
Deep Learning: 1-D Convolution Neural Network for ECG Signal

Abstract
This article presents a deep learning approach for cardiac arrhythmia detection based on electrocardiography (ECG) signal analysis. Most of cardiac arrhythmia or diseases can be prevented, but death continues to rise due to improper treatment because of misdiagnose. One of cardiovascular diseases is Arrhythmia. The goal of our research was to design a method based on one Dimensional Convolution Neural Networks (1-D CNN) for the classification of ECG Signal which is able to accurately classify three different arrhythmias, like N-Non-ecotic beats or normal beat , V -Ventricular ectopic beats , Q -Unknown Beats. The present research is based on 60,000 ECG signals fragments from the PhysionNet’s MIT-BIH Arrhythmia database. The database is divided into two categories, that is train set and test set. The 1-D CNN is applied to the database and the obtained result gives the accuracy of 97.44% . Keywords - ECG Arrhythmia, Deep Learning, 1 D Convolution Neural Networks.