Breast cancer detection using K-nearest neighbors data mining method obtained from the bow-tie antenna dataset

摘要

Breast cancer, has been a significant cancer type for women on the society. Earlyrndiagnosis and timely medical treatment are important key factors spreading to thernother tissues and permitting long-time survival of patients. Since the existing methodsrnhave several serious shortfalls, microwave imaging method for the diagnosis of earlyrnstage tumors has been interested by different scientific research groups in terms ofrnmoderating endogenous the electrical property difference between healthy tissue andrnmalignancies. In this article, both an ultra-wideband bow-tie antenna with enhancedrnbandwidth and a 3D breast model which has different electrical properties which arernpermittivity and conductivity is created in simulation tool to solve electromagneticrnfield values. Return loss, VSWR, and radiation pattern characteristics, which are significantrnantenna parameters, are simulated and obtained whether the antenna possessrnan efficient characteristic or not. Electric field values over the breast tissue in whichrnthere is a tumor or not tumor are evaluated. In this article, above-mentioned values ofrnfrequency bandwidth, dielectric constant of antenna’s substrate, electric field, andrntumor information were consisted in their dataset. This dataset obtained from thernBow-Tie Antenna was used to detect the breast cancer with one of the data miningrnmethod, which is K-Nearest Neighbor Algorithm.