Comparative Analysis of Skin Cancer Prediction using Neural Networks and Transfer Learning

Abstract

The skin is the body’s outermost layer, concealing/covering many physical organs, muscles, and other innumerable bodily parts. The research found that the body’s exposure to ultraviolet light is the main contributor to skin cancer (UV). There are many layers to the surface, but the top and dermis are where cancer first appears. Variations in you complexion or the appearance of a blemish in many locations on your body are the most common warning signs. The only way to prevent cancer is to stay as far away from Uvr as you can, that could stop their skin from coming into contact with the disease. According to statistics, cases of this cancer are not only increased but are increasing swiftly as a result of the ozone layer’s deterioration, which causes it to stop emitting dangerous energy and, as a result, come into contact with our skin. For the following problem, several different strategies including machine learning, deep learning, and data augmentation are being used. Bayes Classifier, linear regression, random woodland, retiree, artificial neural network, and dnn are just a few of the many techniques used. The research makes an effort to put both transfer learning and deep learning approaches to use in order to provide a result that shows which performed best for the next challenge.