BREAST CANCER DETECTION USING AB-GWO

Breast cancers are among the top two causes for deaths relating to cancers among women. Mammography's are effective tools for detecting breast cancers in early stages. Mammography's involve the production of scans of breast regions by using Xrays, and ensuring that visualizations of internal breast structures for analyses are clear for detection for anomalies, in the event that they occur. Extracting features refers to the simplification of the quantity of vectors that are needed for describing big data sets in an accurate manner. Selecting features is also significant in detecting breast cancers and subsequently classifying them. AdaBoost is the most commonly known boosting process which has obtained significant interest from the machinelearning research domain. Grey wolf optimization (GWO) is the most recent technique, inspired by nature, which mimics the hunting procedure of grey wolves. In the current work, Genetic Algorithm (GA)as well as GWO optimization is incorporated with AdaBoostto improve the detection of cancer in mammograms. Results show that the classification accuracies of optimization with Grey wolf performs better by 6.65% than Adaboost and by 3.28% than optimization with GA.