A CNN-based scheme for COVID-19 detection with emergency services provisions using an optimal path planning

Area of Science:

• Medical Imaging Analysis
• Artificial Intelligence in Healthcare
• Logistics and Supply Chain Management

Background:

• The COVID-19 pandemic highlighted challenges in rapid diagnostics and medical supply delivery.
• Unmanned Air Vehicles (UAVs) offer potential solutions for healthcare logistics.
• Accurate and timely detection of COVID-19 cases is crucial for patient management.

Purpose of the Study:

• To develop a deep learning model for classifying COVID-19, pneumonia, and normal cases from X-ray images.
• To propose an optimal path planning scheme for UAVs to deliver emergency medical supplies.
• To enhance healthcare response during the COVID-19 pandemic.

Main Methods:

• A deep convolution neural architecture utilizing transfer learning was developed for X-ray image classification.
• The proposed model was compared against state-of-the-art deep learning models.
• An optimal path planning approach was designed for UAV-based medical kit delivery.

Main Results:

• The proposed deep learning model achieved an accuracy of 94.92% in classifying COVID-19, pneumonia, and normal X-ray images.
• The study demonstrated the feasibility of using UAVs for time-bounded delivery of medical supplies.
• The research provides a dual approach to address diagnostic and logistical challenges posed by COVID-19.

Conclusions:

• The developed deep learning model shows high efficacy in COVID-19 detection from X-rays.
• UAVs can significantly improve the efficiency of medical supply chains, especially during health crises.
• Integrating AI-driven diagnostics and UAV logistics can enhance pandemic preparedness and response.