There are no reviews yet. Be the first to send feedback to the community and the maintainers!
product
Back-end of a e-commerce site developed by node.js, MySQL and Sequelize ORM. Incorporated JOI framework for validation and Promise for asynchronous operations.scdusingka
Skin cancer is one of the most common types of human malignancy in medical sec-tor. Normally, it is being diagnosed visually starting with an initial clinical screeningand then possibly followed by dermoscopic analysis, a biopsy and histopathologicalexamination. Application of machine learning is continuously being used to deter-mine the accuracy of detecting different medical problems more effectively. A lotof new techniques have been discovered to fast forward the procedure with havinghighest percentage of accuracy. In this thesis work, we have proposed a model todetect skin cancer more effectively using image processing with convolutional neu-ral network, a part of deep learning concept under machine learning. The datasetcontains almost 3000+ images of the patients having skin diseases classified intotwo classes, malignant and benign. We have introduced CNN along with its sevendifferent architectures to find the accuracy of the images of skin cancer and per-formed a comparative analysis to find out the best architecture that suits this typeof problem. Among all the architectures Xception performed the best results withhaving almost 85.303% accuracy to determine skin cancer. Furthermore a new model was introduced which suppress the accuracy of predefined models.Love Open Source and this site? Check out how you can help us