Performance Analysis of Machine Learning Algorithms for COVID-19 Detection

The Novel Coronavirus Illness 2019 (COVID-19) was found in Wuhan, Hubei, China, in December 2019 and has since spread globally. When the patient's corona sickness worsened, his life was in danger. Coronavirus assaults the lungs. Diagnostic kits today only search for viral illnesses, which deceives doctors. All patients receiving the same treatment harm patients with less infection. This publication describes non-invasive treatment for infected people. Dissecting chest X-ray pictures to examine the coronavirus helps investigate and predict COVID-19 patients. We offer a hybrid method for detecting Covid. CNN and SVM identify Covid. Because X-ray pictures are inconsistent, CNN is used for feature extraction. To construct a training dataset before CNN, we used data augmentation. Data augmentation increases the training dataset's amount and quality. SVM is used for classification since it tolerates feature differences. The main goal is to help clinical doctors determine the severity of a chest infection so they can administer life-saving treatment. Deep learning and machine learning-based techniques will determine the degree of chest infection and lead to optimal medication, avoiding expensive treatment for all patients.