COVID-19 Detection Mechanism in Vehicles Using a Deep Extreme Machine Learning Approach

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Epidemiology

Background:

• The COVID-19 pandemic necessitates rapid and accurate detection methods to curb viral spread and reduce mortality.
• Current RT-PCR testing faces challenges including long turnaround times and potential false negatives.
• Automated systems utilizing medical imaging and machine learning are emerging as alternatives for early disease identification.

Purpose of the Study:

• To propose a Vehicle-based COVID-19 Detection System for early symptom identification in individuals within vehicles.
• To leverage deep extreme machine learning and fuzzy modeling for accurate COVID-19 detection.
• To facilitate timely COVID-19 testing and intervention by enabling mobile screening.

Main Methods:

• Development of a COVID-19 detection system integrated into vehicles.
• Application of deep extreme machine learning algorithms for symptom analysis.
• Utilization of fuzzy modeling to account for the ambiguity of human symptoms.
• Inclusion of key symptoms such as fever, cough, shortness of breath, and pneumonia as detection parameters.

Main Results:

• The proposed system demonstrated high accuracy in detecting COVID-19 related symptoms.
• Achieved an accuracy exceeding 90% in the COVID-19 detection model.
• The vehicle-based approach offers a practical solution for widespread, timely screening.

Conclusions:

• The Vehicle-based COVID-19 Detection System provides an effective and automated method for early disease detection.
• This system can significantly assist governments in managing the pandemic through efficient and timely testing.
• The integration of deep learning and fuzzy logic enhances the reliability of COVID-19 symptom identification.