Machine learning-based performance comparison of breast cancer detection using support vector machine

Abstract

The most common disease is breast cancer among all women in the world. The death rate of breast cancer is higher due to unawareness of cancer's initial symptoms. There are methods already existed to classify the disease using various real-time tools and algorithms. Machine learning has emerged as a fast boom in all fields of training and classification. The traditional computer programming techniques for the classification of breast cancer disease utilize the Deep Learning (DL) technique for training the model using Convolutional Neural Network (CNN) for dominant feature extraction to identify the given breast cancer test image samples. The datasets of the test samples are fed to the automated detection model for classifying the mammography images into 'Malignant' and 'Benign' breast tumors using Kernel SVM classification. In this paper, the breast cancer recognition accuracy results are compared for different kernels like linear, poly, Radial Basis Function, and sigmoid function. The linear Kernel gives better accuracy of "95.78%". The training set is varied, and their recognition performance is observed until the recognition accuracy is better.