Portable ECG Device Based on Deep learning and Raspberry PI 4

Abstract

Positive characteristics physicians utilize electrocardiograms (ECGs) for the interpretation and diagnosis of cardiac conditions. Hence, it is imperative to automate the analyses of ECG heartbeats in order to diagnose cardiac diseases with optimal effectiveness. The rural in Iraq are deficient in essential equipment and require state-of-the- art medical technologies be low cost, easy to use and read, in addition to the students and researchers in the field of medicine and medical engineering who are interested to developing new technologies to monitor cardiac conditions. This research paper focuses on designing and implementing a technique for forecasting arrhythmia, while simultaneously monitoring the ECG signals, hence developing an arrhythmia predication model, based on Raspberry pi4, real-time ECG tracking system using the VVG-16 algorithm, NNC. The use of deep learning model and algorithms has an impressive overall accuracy of 97.1% in predicting arrhythmia and 98.4% in overall system accuracy. The machine is being developed using AD8232, Arduino UNO, Raspberry pi4, biomedical sensor pad and battery, this method can be viewed as a practical application of the Internet of Things (IOT) idea that describes the procedure for determining the number of heartbeats from the ECG signal and display the diseases type on the same screen from mobile application or computer.

Keywords

• Heart Disease, ECG, Deep Learning, VGG, Raspberry pi4