Chakrabarty, AmitabhaUtsab, Arnab Mitra2025-06-252025-06-2520252025-02ID 19101030http://hdl.handle.net/10361/26298Cataloged from PDF version of thesis.Includes bibliographical references (pages 50-53).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2025.To stop the spread of monkeypox, a viral skin disease and other skin diseases, early detection and precise classification are essential. Using VGG16, ResNet50, CNN, and AlexNet, this work investigates a Machine Learning (ML)-based system for categorizing monkeypox and other skin conditions. We trained many deep learning models, did data augmentation, and downloaded lesion images from Kaggle. custom CNN (94.66%) and VGG16 (80.26%) attained the best accuracy , whereas ResNet50 (55.33%) and AlexNet (37.35%) had poorer stability. We created a React JS web application that allows users to contribute photographs for analysis in real-time classification. In order to increase model performance and interpretability, future developments will incorporate Explainable AI (XAI), GPU acceleration, and dataset expansion. Our study shows how ML-driven skin disease identification can be used for early diagnosis and public health monitoring.53 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Machine learningMonkeyPoxSkin diseaseHealthcareChickenPoxArtificial intelligenceArtificial intelligence.Machine learning.Monkeypox virus.Medical care.Skin--Diseases--Diagnosis.Thesis