Intelligent System for Identification and Classification of Pneumonia using Machine Learning

The current study introduces an advanced system that utilizes machine learning methodologies to accurately detect and categorize pneumonia cases from chest X-ray images. The utilized system employs the VGG16 model as the foundational architecture for the classifier. It also utilises transfer learning techniques to adjust the model to the merged dataset of chest X-ray images that have been labelled. The model has been enhanced with the utilisation of Grad-CAM, a methodology that offers interpretability for the model's predictions through visual explanations. The training methodology employed involves mini-batch stochastic gradient descent, with a batch size of 8, for a total of 200 epochs. The evaluation of the system's performance is conducted by means of the utilisation of the test dataset. The findings indicate that the system that was created has the ability to effectively and precisely detect and categorise pneumonia based on chest X-ray images. This suggests that the system has the potential to be a valuable tool in the medical field for prompt diagnosis and treatment.