Skin Cancer And Covid19 Classification Using Machine And Deep Learning

Résumé: On one hand, skin cancer is one of the most known cancer in the world, the early detection plays a major role in the ability to remove this kind of tumors. On another hand, Covid-19 is the most dangerous corona virus that has spread around the world in 2020. One of the fastest and most useful ways to achieve early detection is to use machine learning and deep learning classifiers. To get a good performance, the accuracy of the classifier should be high so the patients may have a clear idea about their state. For this purpose, there are many hyper parameters that can be changed in order to improve the performance of the artificial models that are used for the identification of such illnesses.In this project we have applied some classification algorithms on two applications which are Covid-19 identification and multiclass skin cancer classification. In the first application, we have applied the classification algorithms on the Covid-19 data set and we have got good performance concerning the random Forest and SVM classifiers and acceptable accuracy by the CNN models due to the lack of data samples. In the second application, we have adapted the same models to be applied on the skin cancer dataset. In this part, CNN models have overpassed the other algorithms in the performance.After that we have compared the results of the two applications and we have suggested some methods in order to improve the performance of these classification algorithms.

Publié dans la revue: