Using an Adaptive Neuro-fuzzy Inference System (anfis) Algorithm for Automatic Diagnosis of Skin Cancer

This paper presents a diagnosis system, based on an adaptive neuro-fuzzy inference system (ANFIS) algorithm, for applications in biomedical fields. This paper deals specifically with skin cancer diagnosis. Our system can be divided into two main parts: feature selection, using the Greedy feature flip algorithm (G-flip), and Classification method using ANFIS algorithm. The ANFIS algorithm could be trained with the back propagation gradient descent method in combination with the least squares method. Three different types of skin lesions were introduced to this diagnosis system and the performance of the ANFIS model was evaluated in terms of training performance and classification accuracies. The results confirmed that the proposed ANFIS model has potential in classifying the skin cancer diagnosis.