Breast Cancer Intelligent Diagnosis Based on Subtractive Clustering Adaptive Neural Fuzzy Inference System and Information Gain

This paper uses a new intelligent method for the diagnosis of fatal breast cancer. The method combines the information gain method and the subtractive clustering adaptive neural fuzzy inference system (IG-SCANFIS). Information Gain method was applied to reduce the attributes dimension and then applies the selected attributes as input to SCANFIS. The SCANFIS model uses the subtractive clustering algorithm to cluster the input data to obtain the fuzzy rules and establish the neural fuzzy reasoning system. The system is used to diagnosis the breast cancer. The data sets used for training and testing were obtained from the University of California, Irvine (UCI) machine learning library. The simulation result shows that the proposed method has high prediction accuracy and the accuracy rate is as high as 99.44%.