Published Paper Details:

The correct diagnosis of patient's conditions and diseases is one of the most significant challenges that healthcare professionals face. A problem for both the patient and the doctor is being unable to correctly diagnose a condition. It can be very helpful, especially to increase a patient's chance of survival, to predict respiratory conditions earlier. One of the most dangerous diseases that kill a lot of people is pneumonia. The primary reason for this is that, for a variety of reasons, many people are unaware of it in its early stages, and by the time they do, it is too late. However, the likelihood of curing these conditions rises if they are discovered early on. However, because extensive screening with CT, MRI, or X-rays is not practical in many parts of the world, midsection radiology continues to be the most fundamental system. When working with medical imagery, there are frequently issues with reliability and interpretability that this model could help alleviate. For this classification task, it is difficult to obtain a large dataset of pneumonia, in contrast to other deep learning classification tasks with sufficient image repositories; As a result, we used a number of data augmentation algorithms to boost the CNN model's classification and validation accuracy, and we were able to achieve remarkable validation accuracy. For the classification of the images and the early diagnosis of pneumonia, our classification technique makes use of convolutional neural networks.