A Hybrid Grey Wolf-Whale Optimization Algorithm for Optimizing SVM in Breast Cancer Diagnosis

Abstract

Breast cancer is one of the major causes of death among women in many parts of the world but, it is confirmed that early detection and accurate diagnosis of this disease ensures the long survival of the patient. In our research, a hybrid meta-heuristic swarm intelligence based Support Vector Machine Classifier called Grey Wolf-Whale Optimization Algorithm with Support Vector Machine (GWWOA-SVM) is proposed for early-stage detection of the disease. Anamalgamation of Whale Optimization Algorithm (WOA) and Grey Wolf Optimization (GWO) is used for tuning the hyper-parameters of SVM. The effectiveness of GWWOA-SVM is evaluated against the Wisconsin Breast Cancer Dataset (WDBC). The performance of the proposed model is evaluated on various metrics such as accuracy, precision, recall, specificity, and F1 Score. Our model achieves a classification accuracy of 97.721 % for WDBC dataset. The GWWOA algorithm is compared with GWO and WOA based on their extent of optimization of the fitness function. The comparison of breast cancer diagnosis corroborates that our model evaluates more nuanced performance metrics.