A Reliable and Efficient Tracking System Based on Deep Learning for Monitoring the Spread of COVID-19 in Closed Areas

Since 2020, the world is still facing a global economic and health crisis due to the COVID-19 pandemic. One approach to fighting this global crisis is to track COVID-19 cases by wireless technologies, which requires receiving reliable, efficient, and accurate data. Consequently, this article propose...

Full description

Saved in:
Bibliographic Details
Published in:International journal of environmental research and public health 2021-12, Vol.18 (24), p.12941
Main Authors: Osman, Radwa Ahmed, Saleh, Sherine Nagy, Saleh, Yasmine N M, Elagamy, Mazen Nabil
Format: Article
Language:English
Subjects:
Artificial intelligence
Benchmarks
Coronaviruses
COVID-19
Deep Learning
Disease transmission
Epidemics
Humans
Infections
Internet of Things
Learning algorithms
Masks
Medical equipment
Medical supplies
Neural networks
Neural Networks, Computer
Optimization
Pandemics
Privacy
Radio equipment
Radio frequency identification
Radio-tagging
SARS-CoV-2
Sensors
Severe acute respiratory syndrome coronavirus 2
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Since 2020, the world is still facing a global economic and health crisis due to the COVID-19 pandemic. One approach to fighting this global crisis is to track COVID-19 cases by wireless technologies, which requires receiving reliable, efficient, and accurate data. Consequently, this article proposes a model based on Lagrange optimization and a distributed deep learning model to assure that all required data for tracking any suspected COVID-19 patient is received efficiently and reliably. Finding the optimum location of the Radio Frequency Identifier (RFID) reader relevant to the base station results in the reliable transmission of data. The proposed deep learning model, developed using the one-dimensional convolutional neural network and a fully connected network, resulted in lower mean absolute squared errors when compared to state-of-the-art regression benchmarks. The proposed model based on Lagrange optimization and deep learning algorithms is evaluated when changing different network parameters, such as requiring signal-to-interference-plus-noise-ratio, reader transmission power, and the required system quality-of-service. The analysis of the obtained results, which indicates the appropriate transmission distance between an RFID reader and a base station, shows the effectiveness and the accuracy of the proposed approach, which leads to an easy and efficient tracking system.
ISSN:1660-4601
1661-7827
1660-4601
DOI:10.3390/ijerph182412941