SVM-ANN Optimized Algorithm for the Classification of Breast Cancer Data as Benign and Malignant

Abstract

The second most widespread cancer in women, breast cancer, is the most lethal and is responsible for an increasing number of daily deaths in females. Breast cancer patients who receive an advanced diagnosis have a higher probability of dying and reduces the probability of surviving. Numerous research projects are being implemented in order to improve breast cancer rapid identification. Despite the existence of numerous medical diagnostic techniques for predicting breast cancer, it remains difficult to anticipate breast cancer at its earliest stages. The major objective of this research is to establish a predictive model that could really identify breast cancer earlier on and increase survival rates. The Wisconsin Breast Cancer (Original) Dataset is utilized in this research to forecast breast cancer utilizing techniques from data mining like K-Nearest Neighbor Algorithm(KNN), Support Vector Machine Algorithm(SVM), and Artificial Neural Network Algorithm(ANN), a new model SVM-ANN optimized algorithm is also proposed. A variety of parameters which including Accuracy, Precision, and Recall, have been employed to compare the results of these algorithms in order to fully evaluate their effectiveness. Finally, with a 97 percent accuracy rate, the proposed algorithm SVM-ANN optimized algorithm significantly outperformed other current algorithms.