Breast cancer (BC) is a standout disease of the most well-known cancers among women around the world. The analysis and prediction of BC leads to early manage the disease and protect the patients from further medical complications. In the light of its noticeable focal points in basic highlights identification from complex BC datasets, Machine Learning (ML) is generally perceived as the technique of decision in BC design order and gauge displaying. Because of the high performance of the Multi-layer Perceptron (MLP) algorithm as one of the ML techniques, we conducted experiments in order to enhance the accuracy rate of MLP by tuning its hyper-parameters along with studying the effect of feature selection methods and feature reduction of MLP. As feature selection results indicated that an increase in the number of input parameters tends to reduce the error associated with the estimator model. The tuned MLP proposed in this paper, based MLP best fit hyper-parameters along with feature selection is applied for breast cancer classification using Wisconsin Diagnostic Breast Cancer (WDBC) dataset. As the tuned MLP experimental result shows an accuracy reached 97.70% as it outperforms the basic MLP.

No abstract