A Multi-Classifier Method based Deep Learning Approach for Breast Cancer
Mokhairi Makhtar, Rosaida Rosly, Mohd Khalid Awang, Mumtazimah Mohamad, Aznida Hayati Zakaria · International Journal of Engineering Trends and Technology · 2020
Breast cancer is one of the diseases that haunt every woman around the world.It is one of the main killers of women not only in Malaysia, even around the world.Medical diagnosis such as breast cancer is considered a significant but complicated task that needs to be carried out correctly and effectively.In improving the prediction accuracy of breast cancer dataset, this study evaluates the performance of multi-classifier based deep learning approach on datasets.There are five classifiers that are involved like Sequential Minimal Optimization (SMO) , decision tree (J48) , random forests (RFs), Naïve Bayes (NB) and Instance Based for K-Nearest neighbor (IBk).These classifiers will be combined and analyzed using deep learning approach.This strategy utilizes models of deep neural network that is a variant of Neural Network but with big approximation to human brain using an advance system compared to a straightforward neural network.The results of combination different classifiers using deep learning approach indicate the highest accuracy than single classification with 96.63% as a combination SMO+RF+IBK+NB.