Open AccessIot Based Health Care System for Predicting Cardiac Issues
Author(s) -
A. Rama Narsimha Reddy,
G. P. Reddy,
A V R M Koushik,
K V Siddeshwar
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.d7233.049420
Subject(s) - computer science , stage (stratigraphy) , disease , feature (linguistics) , process (computing) , microcontroller , stroke (engine) , artificial intelligence , transfer (computing) , health care , medical emergency , medicine , machine learning , engineering , embedded system , mechanical engineering , paleontology , linguistics , philosophy , economics , biology , economic growth , operating system , parallel computing
According to the survey conducted by the WHO (World Health Organization), out of 56.9 million deaths, Ischemic heart disease and Heart stroke account for 15.2 million deaths of the total deaths in 2016. These are regarded, as the Non-Communicable Diseases (NCD) also known as chronic diseases, tend to affect a person for a long duration. Along with in most of the cases, it is hard to find the disease existence in its primary stage; we can find it only with the symptoms like stroke or heart attack. Due to the lack of these symptoms, healthcare awareness and the financial needs many people are losing their lives. It is a very long process and cost effective. Hence, we are proposing a model, which predicts these symptoms with the implementation of latest technological advances like IoT, machine learning and deep learning algorithms. The proposed methodology takes place in three stages. Primary stage consists of collecting the data through sensors attached to the patient. Secondary stage involves the transfer of data from the microcontroller to the application and converting the data to suitable form. Tertiary stage involves feature extraction of the data and classification of the data using the CNN algorithm. All the stages run dynamically and generate the results based on the data collected. These results are then analyzed to check if the patient has arrhythmias or normal.