Evaluating the Performance of Machine Learning Techniques in the Classification of Wisconsin Breast Cancer

Abstract

Breast cancer is a considerable problem among the women and causes death around the world. This disease can be detected by distinguishing malignant and benign tumors. Hence, doctors require trustworthy diagnosing process in order to differentiate between malignant and benign tumors. Therefore, the automation of this process is required to recognize tumors. Numerous research works have tried to apply the algorithms of machine learning for classifying breast cancer and it was proven by many researchers that machine learning algorithms act preferable in the diagnosing process. In this paper, three machine-learning algorithms (Support Vector Machine, K-nearest neighbors, and Decision tree) have been used and the performance of these classifiers has been compared in order to detect which classifier works better in the classification of breast cancer. Furthermore, the dataset of Wisconsin Breast Cancer (Diagnostic) has been used in this study. The main aim of this work is to make comparison among several classifiers and find the best classifier which gives better accuracy. The outcomes of this study have revealed that quadratic support vector machine grants the largest accuracy of (98.1%) with lowest false discovery rates. The experiments of this study have been carried out and managed in Matlab which has a special toolbox for machine learning algorithms.