ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

The modelling and simulation of IoT system in healthcare applications

Journal: International Journal of Advanced Technology and Engineering Exploration (IJATEE) (Vol.8, No. 74)

Publication Date:

Authors : ; ;

Page : 167-177

Keywords : Internet of things; Healthcare application; Modelling and simulation.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

This paper presents a review on modelling and simulation of Internet of things (IoT) in healthcare application. IoT is a large-scale ecosystem of socio-technical application. The emerging technology of IoT has gained enormous attention in a wide range of industries and used in various kind of environments. Healthcare application is one of the vital IoT applications for smart cities. Medical devices and applications of IoT healthcare are emerging rapidly in the global market. Various IoT-based health applications have been proposed to help patients monitor the disease and track the health information without visiting the hospital, clinic, or any medical centre. This paper has briefly described the methods and devices used in IoT-based healthcare application, namely blood pressure monitoring, glucose and cholesterol monitoring, asthma monitoring, and stroke rehabilitation system. The modelling and simulation process of IoT-based healthcare applications are discussed on blood pressure and stroke rehabilitation system only. The development of electrocardiogram (ECG) and Photoplethysmogram (PPG) in blood pressure measurement integration with a smartphone has created simplicity and usability of the device. Nevertheless, further investigation is required to improve the accuracy in collecting the patient's health information. For hand rehabilitation training purposes, an IoT-enabled stroke rehabilitation device depends on machine learning, smart wearable armband and a 3D printed robot hand were developed to imitate the movements of the patient in a real-time mode. The feature selection used in the development of the device using machine learning has produced a high classification accuracy which helps stroke patients to strengthen the muscles with their motion patterns after stroke.

Last modified: 2021-02-09 19:52:12