Optimizing Skin Cancer Detection in E-Health Systems with Mobilenet and Chaos PSO-Enhanced Random Forest

Early detection of skin cancer is critical for effective treatment, and recent advancements in e-health systems have enabled the integration of machine learning models for accurate diagnosis. In this context, this work provides an optimal method employing MobileNet for feature extraction and Random Forest for classification to identify skin cancer in e-health systems. Hyperparameter tuning of the Random Forest model using Chaos Particle Swarm Optimization (C-PSO) helped to improve model performance. Comprising 2,357 photos from ISIC, the collection comprises many skin disorders including melanoma, basal cell carcinoma, and squamous cell carcinoma. With an AUC of 0.88, the suggested model outperformed approaches like Extra Trees, K-Nearest Neighbors, and Naive Bayes. Comparative findings on accuracy, F1-score, precision, and recall show how well our method improves skin cancer diagnosis for e-health uses.