Published Paper Details:

COVID-19 is extremely infectious that spreads quickly from across the world, making early diagnosis critical. COVID-19 diagnosis is critical. Numerous investigations have been performed to ascertain if patients' chest X-rays, as well as computed tomography (CT), scans reveal COVID-19 infection. COVID-19 illness results on computed tomography (CT), as well as X-ray imaging, are like those of other lung infections, making it problematic for medical experts to differentiate COVID-19. The purpose of this research has been to determine the role of machine learning, deep learning, or pictures processing within fast or precise identification of COVID19 from two of the most frequently used medical imaging modalities, chest X-ray or CT pictures. We evaluated performance of ML and DL techniques on chest X-ray pictures as well as CT scans to COVID-19 diagnosis in this research. The proposed convolutional neural networks (CNNs) using the Alexnet Model for CAD of coronavirus from CT and X-ray pictures. The efficiency of this technique was checked on the data set obtained. We classified COVID-19 CT & X-ray scans as well as examined the evolution of the condition of the patients via CT scans. Accuracy of these techniques varied from 93.25 percent to more than 99.82 percent, suggesting that machines, as well as deep learning methods, apply to the clinical diagnosis of COVID-19. The trials carried out in this research have shown the efficacy of the pretrained COVID-19 alexnet model of CNN.