A novel hybrid Extreme Learning Machine and Teaching–Learning-Based​ Optimization algorithm for skin cancer detection

Abstract

Skin cancers, such as melanoma, can be difficult to spot in their early stages because they often resemble benign moles. Early detection of melanoma is crucial as it increases the chances of successful treatment and prevents cancer from spreading to other areas of the body. Machine learning algorithms and computer vision techniques are versatile techniques for detecting melanoma. However, current research has limitations, such as inaccurate detection and longer computation times. This paper proposes a novel hybrid Extreme Learning Machine (ELM) and Teaching–Learning-Based Optimization (TLBO) algorithm as a versatile technique for detecting melanoma. ELM is a single-hidden layer feed-forward neural network that can be trained quickly and accurately, while TLBO is an optimization algorithm used to fine-tune the network’s parameters for improved performance. Together, these techniques can classify skin lesions as benign or malignant images, potentially improving melanoma detection accuracy.

Keywords

• Extreme learning classifier
• Teaching learning based optimization
• Improved weighted fuzzy C-Means algorithm
• Segmentation
• Skin cancer
• Neural networks