An Intelligent and Energy-Efficient Wireless Body Area Network to Control Coronavirus Outbreak.

Area of Science:

• Biomedical Engineering
• Health Informatics
• Epidemiology

Background:

• Coronaviruses are highly contagious epidemic viruses necessitating rapid diagnosis to reduce mortality.
• Early identification and monitoring of infected individuals are crucial for controlling the spread of diseases like COVID-19.
• Wireless Body Area Networks (WBANs), Machine Learning (ML), and the Internet of Things (IoT) offer potential for real-time health monitoring and disease detection.

Purpose of the Study:

• To propose a novel coronavirus-body area network (CoV-BAN) model utilizing IoT technology for real-time health monitoring.
• To detect early stages of coronavirus infection through wearable biosensors and ML-based classification.
• To optimize COVID-19 diagnosis accuracy and ensure energy efficiency for sustainable sensor device operation.

Main Methods:

• Development of a CoV-BAN model integrating wearable biosensors, IoT, and ML for real-time patient health monitoring.
• Evaluation of five ML classifiers (random forest, logistic regression, Naive Bayes, SVM, MLP) for COVID-19 diagnosis accuracy.
• Implementation of a long-range (LoRa)-based IoT program for energy-efficient signal transmission from biosensors to the cloud.

Main Results:

• The CoV-BAN model with the random forest classifier achieved the highest average accuracy of 88.6% in diagnosing COVID-19.
• The proposed model effectively monitors patient health status using wearable biosensors for early infection detection.
• Utilizing LoRa technology as a relay node significantly reduced power consumption, enhancing the long-term sustainability of sensor devices.

Conclusions:

• The proposed CoV-BAN model demonstrates a promising approach for the early detection and monitoring of coronavirus infections.
• The integration of IoT, WBANs, and ML, particularly the random forest classifier, enhances diagnostic accuracy.
• Energy-efficient LoRa technology is vital for the sustainable deployment of wearable biosensor networks in healthcare applications.