Human activity recognition using electrocardiogram data by deep neural networks methods and mobile health

Today, heart disease is one of the most common causes of death in the world. For this reason,accurate and timely diagnosis of patients’ conditions is essential. Because traditional diagnosticmethods for these kinds of diseases have many costly side effects, researchers are always lookingfor cheaper and more accurate ways to diagnose. One effective strategy is using mobile health de-vices to monitor the person’s health status through the signals received by an electrocardiogram.Early diagnosis enables more effective treatment and prevention of chronic diseases. Measuringand recording electrocardiogram signals by mobile services is a valuable solution in the field ofhealth care, such as processes for classifying and diagnosing the activity or condition of patients.This study aimed to find a model with a precise function for classifying and recognizing humanactivities using cardiac data taken from wearable sensor signals from two electrocardiographysensor. This classification model of human activity is based on the electrocardiogram data of them -health data set and obtained using four deep learning models. These models include recur-rent neural networks like (LSTM), Convolutional Neural Network (CNN), and attention-basedhybrid neural networks.This research has taken a step in classifying different types of human activities only throughelectrocardiogram signals. By examining other hyper parameters and selecting the best ones,our proposed network has achieved slightly higher accuracy than previous research. The pro-posed CNN-LSTM combination-based learning model obtained approximately values of 99.9%accuracy, 100% precision, 100% recall, 100% F1 score, and 100% for the ROC AUC scale, re-spectively, in terms of validation results. The results show that our designed network performsbetter than the advanced models of previous research.