A Hyper-tuned Metrics based Augmented CNN Model for Accurate Prediction of Monkeypox Risk

Monkeypox, a zoonotic viral infection, has emerged as a global health concern. Early and accurate diagnosis is crucial for effective containment. This research investigates the application of Convolutional Neural Networks (CNNs) for the classification of monkeypox skin lesions from other pox types and normal skin. Leveraging a comprehensive dataset of skin images, we explored various CNN architectures, including pre-trained models and custom designs. Data augmentation techniques were employed to enhance model robustness. The performance of the models was evaluated using metrics such as accuracy, precision, recall, and F1-score. Our findings demonstrate the potential of CNNs as a valuable tool for the rapid and accurate detection of monkeypox, aiding in public health efforts to control the spread of this disease.