Processing of Wisconsin Breast Cancer Data using Ebola Optimization Algorithm with Mixture Kernel SVM

Being a deadly disease, breast cancer is becoming the more progressive one in providing higher mortality for females around the world. Thereby, the need for an appropriate strategy is always required for earlier breast cancer diagnosis. The physicians utilize the Computer-Aided Diagnosis (CAD) tool for effective and tireless detection of such cancers. In this regard, the work is intended to design a CAD system for breast cancer diagnosis in a timely manner. The implementation starts with the use of Wisconsin Breast Cancer dataset. After performing preprocessing and visual analysis of the input dataset, feature selection is performed to improve the efficiency of the CAD system. This can be done by using the recently evolved Ebola Optimization Algorithm (EOA). This algorithm is based on an effective approach used in the propagation of the Ebola virus among individuals. After feature selection, the dominant features are then classified with the aid of a mixture Kernel Support Vector Machine (mK-SVM) algorithm. Additionally, the work utilized the Linear SVM, and KNN algorithms for the experimental analysis and comparison. As a result, the mK-SVM together with EOA provides maximum accuracy of 97.19% in classifying the input as either benign severity or malignant case.