COVID-19 prediction using Caviar Squirrel Jellyfish Search Optimization technique in fog-cloud based architecture

Area of Science:

• Healthcare Informatics
• Artificial Intelligence
• Optimization Algorithms

Background:

• COVID-19 patients face long hospital wait times due to data management challenges.
• Wearable devices generate preliminary patient data, requiring robust storage and processing.
• Existing healthcare systems struggle with the complexity of handling large volumes of patient data.

Purpose of the Study:

• To propose a novel fog-cloud based scheme, Caviar Squirrel Jellyfish Search Optimization (CSJSO), for efficient COVID-19 prediction.
• To integrate healthcare IoT sensors, fog computing, and cloud computing for improved patient data analysis.
• To enhance the accuracy and speed of COVID-19 detection and management.

Main Methods:

• Developed CSJSO, combining CAViar Squirrel Search Algorithm (CSSA) and Jellyfish Search Optimization (JSO).
• Implemented a Deep Neuro Fuzzy Network (DNFN) in the fog layer trained by Remora Namib Beetle JSO (RNBJSO).
• Utilized Deep Long Short Term Memory (Deep LSTM) in the cloud layer trained with CSJSO for COVID-19 detection.

Main Results:

• CSJSO achieved Mean Squared Error (MSE) of 0.062 and Root Mean Squared Error (RMSE) of 0.252 in confirmed cases (database-1).
• CSJSO demonstrated high performance in database-2 with accuracy (0.925), sensitivity (0.928), and specificity (0.925).
• The proposed architecture effectively manages patient data and improves COVID-19 diagnostic capabilities.

Conclusions:

• The CSJSO scheme offers a potent solution for COVID-19 prediction in a fog-cloud environment.
• This approach addresses data complexity and enhances diagnostic efficiency in healthcare.
• The integration of advanced optimization algorithms and deep learning models shows significant promise for pandemic response.