Multi-Class Pneumonia Detection Using Machine Learning and Deep Learning Approach

Pneumonia is a life-threatening respiratory infection that affects millions of people worldwide, requiring accurate and early diagnosis to reduce mortality rates. This paper presents a multi-class pneumonia detection system using Machine Learning (ML) and Deep Learning (DL) approaches to classify chest X-ray images into Normal, Bacterial Pneumonia, and Viral Pneumonia categories. The proposed framework integrates image preprocessing techniques such as resizing, normalization, and data augmentation to enhance model robustness. Traditional ML classifiers, including Support Vector Machine (SVM) and Random Forest, are compared with advanced Convolutional Neural Network (CNN) architectures for performance evaluation. Feature extraction is performed using both handcrafted features and deep feature representations. The system is trained and validated on publicly available medical imaging datasets, and evaluation metrics such as accuracy, precision, recall, and F1-score are used to assess performance. Experimental results demonstrate that deep learning models outperform conventional machine learning algorithms in multi-class classification tasks, providing higher diagnostic accuracy and reliability. The proposed approach can assist radiologists in early pneumonia detection and improve clinical decision-making.