Abstract
In this work, we propose the use of an electrically small dipole antenna arrays as a microwave sensor combined with a classification algorithm for near field microwave breast tumor detection. The proposed sensor has high sensitive to detect any changes or abnormality in the dielectric properties of the breast tissues. Detecting the existence of the breast tumors are expected by estimating the variations in the response of the reflection coefficient of the sensor. The Principle Component Analysis (PCA) feature extraction technique is applied to accentuate the variance in the sensor responses for both healthy and tumourous cases. We show that when a numerical realistic breast with and without tumor cells is placed in the near field of the sensor, the sensor is capable of detection tumorous with various sizes placed in single locations at two different stand off 5 mm and 10 mm respectively.