Real-time data of COVID-19 detection with IoT sensor tracking using artificial neural network

Area of Science:

• Medical Informatics
• Artificial Intelligence
• Public Health

Background:

• The COVID-19 pandemic presented significant global health challenges.
• Effective early detection systems are crucial for managing infectious disease outbreaks.
• International health systems faced immense pressure during the pandemic.

Purpose of the Study:

• To develop a real-time detection system for COVID-19 using an Internet of Things (IoT) framework.
• To enhance patient classification accuracy using artificial intelligence (AI) and deep learning algorithms.
• To address challenges posed by imbalanced datasets in clinical data analysis.

Main Methods:

• Implementation of an IoT framework for real-time data collection from users.
• Development of a deep learning optimization system incorporating a synthetic minority oversampling technique (SMOTE) for data balancing.
• Application of a recursive feature elimination algorithm for feature selection.
• Validation of models using training and testing data splits.

Main Results:

• The developed deep learning models demonstrated high stability and compatibility with the data.
• Achieved a maximum classification accuracy of 98% and a precision of 97% for COVID-19 patient identification.
• Successfully handled data bias, leading to improved classification outcomes.
• The system effectively analyzes treatment responses and clinical datasets.

Conclusions:

• The proposed real-time IoT-based system with AI significantly improves COVID-19 detection accuracy.
• The deep learning approach effectively manages imbalanced datasets, a common issue in clinical research.
• Findings can assist healthcare organizations in optimizing resource allocation and prioritizing patient care during pandemics.