AI Powered COVID-19 Detection System using Non-Contact Sensing Technology and Deep Learning Techniques

The SARS-CoV-2 virus causes coronary artery disease (COVID-19). The majority of persons who are infected with the virus will have mild to severe respiratory illness and recover without the need for therapy. Some, on the other hand, will become critically unwell and require medical assistance. People over the age of 65, as well as those with underlying medical diseases such as cardiovascular disease, diabetes, chronic respiratory disease, or cancer, are at a higher risk of developing serious illness. Being thoroughly informed on the disease and how it spreads is the best strategy to avoid and slow down transmission. Stay at least 1 metre apart from other people to avoid infection. In this research work, we focus on how non-contact sensing technology and deep learning technique are being used to detect COVID-19 and assist healthcare workers in caring for COVID-19 patients. The proposed system captures images from the patient using non-contact sensing technologies and feeds the data into deep learning convolutional neural network architectures such as VGG16, VGG19, ResNet101, NASNet, DenseNet121, MobileNet, Xception, EfficientNet, and InceptionV3. In comparison to other architectures, the VGG16 architecture delivers superior accuracy.