Prediction Of Breast Cancer Using Support Vector Machine And K-Nearest Neighbors

Breast Cancer is one of the most exquisite and internecine disease among all of the diseases in medical science. It is one of the crucial reasons of death among the females all over the world. We present a novel modality for the prediction of breast cancer and introduces with the Support Vector Machine and K-Nearest Neighbors which are the supervised machine learning techniques for breast cancer detection by training its attributes. The proposed system uses 10-fold cross validation to get an accurate outcome. The breast cancer termed as Wisconsin breast cancer diagnosis data set is taken from UCI machine learning repository. The performance of the proposed system is appraised considering accuracy, sensitivity, specificity, false discovery rate, false omission rate and Matthews correlation coefficient. The approach provides better result both for training and testing. Furthermore, the techniques achieved the accuracy of 98.57% and 97.14% by Support Vector Machine and K-Nearest Neighbors individually along with the specificity of 95.65% and 92.31% in testing phase.