Thesis (MSc) - Cyprus International University. Institute of Graduate Studies and Research Computer Engineering

Skin cancer is one of the most dangerous forms of cancer. Skin cancer is caused by unrepaired deoxyribonucleic acid (DNA) in skin cells, which generate genetic defects or mutations on the skin. Skin cancer is prone to spread over other parts of the body so it can be better treated in early stages and that's why you should detect it at an early stage. The increasing rate of skin cancer cases, high mortality rate, and expensive medical treatment require that its symptoms be diagnosed early. To take into account the seriousness of these matters, several early detection techniques for skin cancer have been identified by researchers. Parameters such as symmetry, color, size, and shape are used to identify skin cancer and differentiate benign skin cancer from melanoma. This master thesis researches the utilization of skin cancer identification through deep ensemble learning using given dataset images. The research evaluates how effectively the combination of a lot of deep learning models, such as convolutional neural networks (CNNs), through transfer learning and Ensemble learning. Machine learning is the main operation of the Convolutional Neural Network which is used as a deep neural networks model like ResNet152V2, MobileNetV2, VGG19, DenseNet201, and InceptionV3 for image classification and identification.