Breast Cancer Classification using SVM and KNN

Abstract

The leading cause of death for women is now breast cancer. Researchers are encouraged to use studies in extracting unidentified patterns from healthcare datasets by the accessibility of healthcare datasets and data analysis. The main intention for this study is to know the best classification technique among the both techniques Support Vector Machines and K-Nearest Neighbor. As well as comparing the SVM and KNN classifiers, we propose a system for classifying breast cancer in this research. After receiving the findings from the Breast Cancer dataset using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN), a performance evaluation and comparison between these classifiers is done. Following that, we train the SVM and KNN classifiers separately using the collected features. The major goal of this study is to identify the best effective machine-learning algorithms for predicting and diagnosing breast cancer in terms of accuracy, precision, recall, and f1-score. Conducting training is a prerequisite for this strategy. The evaluation and comparison of the SVM and KNN classification models included evaluation methods such as heat map and scatter-plot. The comparison results show that the KNN and SVM algorithms perform well for identifying breast cancer.