Soft Computing Algorithms and Their Application on Breast Cancer Data Classification: An Experimental Analysis
Juned A. Siddiqui, Sakshee Vaidya · Apple Academic Press eBooks · 2025
Breast cancer is a disease which has high morbidity and mortality. Breast cells are the starting point for the development of breast cancer. Cancer starts when old, damaged cells start to multiply uncontrollably. Breast cancer has the highest incidence rate of any cancer in women and the second highest incidence rate of any cancer in the world. Analysis of the dataset of cancer patients can give us a more personalized and early approach to the treatment. Data mining techniques using Machine learning and artificial intelligence algorithms help us to classify, analyze, and also visualize this kind of data. This research is done to predict if it is possible to employ data mining methods for the classification and analysis of dataset for categories such as breast cancer cell data. The accuracy and the error of the applied algorithms, that is, artificial neural network (ANN) and k-nearest-neighbor algorithm (KNN) are also found. RStudio is the environment on which these algorithms are run using the R programing language. Two algorithms ANN and the KNN are applied giving an accuracy of 94.59%, an error of 6.4%, and 52% for KNN.