Distinguishing and clustering breast cancer according to hierarchical structures based on chaotic multispecies particle swarm optimization

Breast Cancer Diagnosis and Prognosis are two medical applications pose a great challenge to the researchers. The use of machine learning and data mining techniques has revolutionized the whole process of breast cancer Diagnosis and Prognosis. Breast tumors are divided in to two types; malignant and benign. In this paper we propose how to distinguish the type of breast cancer by creating a Fuzzy system (FS). To detect the type of breast censer we use a chaotic hierarchical cluster-based multispecies particle swarm optimization (CHCMSPSO) to optimization a FS indeed. The objective of this paper is to learn Takagi-Sugeno-Kang (TSK) type fuzzy rules with high accuracy. In addition to this, we will introduce chaos into the HCMSPSO in order to further enhance its global search ability. In the paper, eleven chaotic maps are used in the intelligent diagnosis system. The accuracy rate of distinguishing between benign and malignant censer is above 90 percent. However, among the chaotic maps, the Sinusoidal chaotic map provides us with the accuracy rate 99 percent because it coordinates with the problems conditions. This simulation is performed on UCI-Breast Censer data-base.