Comparing the Performance of Classification Algorithms for Melanoma Skin Cancer

Computer vision plays a beautiful role in the early identification of Melanoma skin cancer. Images are used to classify malignant and benign phenotypes. Also, Dermatologists claim that Melanoma may be diagnosed and cured if it is identified in the early stage. However, selecting an appropriate classification algorithm is essential in early and accurate melanoma detection.Therefore, inspired and motivated by our previous study outcome, we know that early detection and prediction of melanoma skin cancer may be cured (malignant and benign images are classified using CNN, RNN, and XG-Boost methods) [10, 11, 22, 23, 24, 25]. In this experiment, we compared the performance of supervised learning methods like Linear Regression, Light Gradient Boosting Regression, Random Forest Regression, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) Classifier, Decision Tree, Passive Aggressive, Multinomial Naïve Bayes, and Bernoulli Naïve Bayes. Moreover, a better and more accurate performing algorithm is used in early melanoma skin cancer detection.