COVID-19 pandemic deep learning implementations of prediction of disease with data analysis and real-time face-mask detection with camera

Abstract

In biomedical sciences, data mining skills are used to research and provide predictions to aid in the identification and classification of diseases. Controlling the spread of Corona Virus Disease requires screening a high number of reported cases for effective isolation and treatment (COVID-19). Infective laboratory testing (Pathogenic) is the benchmark in science, but it is time-consuming because of the high rate of false-negative? findings. To treat the illness, there is an urgent need for rapid and dependable diagnosis techniques.We wanted to create a deep learning system that could retrieve COVID-19 pictorial features from Computed tomography applying COVID-19 radiographic enhancements. In earlier study investigations, machine learning methods were employed in the prediction and categorization of COVID-19. This research, on the other hand, concentrates on the different effects of certain image processing techniques rather than on optimising these processes through the use of improved approaches. The CT image dataset benefits from the extraction of classified correctness. The DeTraC model, a previously published convolutional neural network architecture based on class decomposition, is used in this study to increase the performance of pre-trained models in detecting COVID-19 instances from chest X-ray pictures. This may be accomplished by including a class breakdown layer into the pre-trained models.