Skin Cancer Detection using ELM Classifier

This research focuses on the crucial task of identifying and categorizing skin cancer through a novel approach employing the Extreme Learning Machine (ELM). The ELM algorithm, known for its rapid and effective learning capabilities, has shown success across various domains. In this proposed method, ELM is utilized to extract salient features from skin cancer images, subsequently classifying them into benign or malignant cases. The study employs a diverse dataset comprising skin cancer images from multiple sources. Through the integration of the ELM algorithm, we introduce a model for the detection and classification of skin cancer. Evaluation of this model is conducted using publicly accessible skin cancer datasets, which encompass a range of dermatological images. The outcomes of this research highlight the model's substantial accuracy in both skin cancer detection and classification tasks. Performance assessment involves diverse metrics such as accuracy, sensitivity, specificity, and F1-score. Empirical findings underscore the efficacy of our proposed ELM-based methodology, surpassing existing state-of-the-art techniques in skin cancer detection and classification. This research accentuates the potential of the ELM-based approach as a robust tool for precise and efficient skin cancer diagnosis. The empirical validation of our model underscores its efficacy in detecting and categorizing skin cancer, indicating its potential to aid medical practitioners in early diagnosis and tailored intervention strategies for skin cancer patients.