Classification of Viral Pneumonia Disease: Dataset of the Normal Class

Pneumonia is regarded as a dangerous and harmful disease worldwide. Indeed, pneumonia can be fatal if not treated swiftly with medications. As a result, early identification of pneumonia improves the chances of recovery and reduces mortality. X-rays are one of the most significant diagnostic techniques for pneumonia. Because of its cheaper diagnostic expenses, the chest X-ray is commonly employed in the diagnosis of numerous lung disorders (such as breast cancer, pneumonia, tuberculosis, and so on). Indeed, diagnosis can be subjective for a variety of reasons, including the presentation of disease, which may be ambiguous in chest X-ray pictures or mistaken with other conditions. Therefore, the research aims to build five Machine Learning Models and five Deep learning applying transfer learning approaches to classify pneumonia disease. The methodology entails SVM, DT, LR, KNN, and RF classifiers together with GoogleNet, DenseNet-121, VGG-19, MobileNet-V2, and AlexNet. This would help in early diagnosis, and disease progression awareness, ease the diagnosis process to a great extent and fast-track the entire process of radiological imaging results.