Sharif Digital Repository

A hybrid algorithm of a particle swarm optimization and a fuzzy rule-based classification system is proposed in this study to diagnose breast cancer. Two orthogonal and triangular types of fuzzy sets are applied to represent the input variables. In additional, different input membership functions are considered to increase the classification accuracy. The performance of the proposed hybrid algorithm is studied using a classification accuracy measure on the Wisconsin breast cancer dataset. The results of the comparison using different training data sets show the higher performance of the proposed methodology  

in this paper we present an integrated classifier that is used in mammogram MR-image for classification of breast cancers and abnormalities using a Multi-stage classifier, the method developed here first classifies mammograms into normal and abnormal and then for abnormal cases determines that if the case cancer is benign or malignant and also determine the type of breast cancer. In this paper there are two main topics that must be considered. First one is selection of good features and second is designing a good structure for classifier. In this study, the features are a combination of some features that are extracted from Spatial Grey Level Dependency matrix and some statistical descriptor...