A Comparative Study of Different Classifiers to Propose a GONN for Breast Cancer Detection
Ankita Tiwari, Bhawana Sahu, Jagalingam Pushparaj, Muthukumaran Malarvel · 2021
The most occurring cancer among Indian females is breast cancer, which was found as 25.8 per 100,000 women and mortality of 12.7 per 100,000 women as per the government of India survey from 2010 to 2014. The survey revealed that only 66.1% of women were diagnosed for cancer and survived. The detection of early cancer symptoms is important for diagnosing the ailment. To identify the tumor for breast cancer various machine learning algorithms were adopted in the literature. In this paper, a comparative study of existing classifiers like support vector clustering (SVC), decision tree classification algorithm (DTC), K-nearest neighbours (KNN), random forest (RF), and multilayer perceptron (MLP) are demonstrated on Wisconsin-breast-cancer-dataset (WBCD) of UCI Machine learning repository. The results indicate that the MLP outperformed the other classifier algorithms. Further, the linear regression approach is adopted to optimize the feature selection for giving an input to the genetic algorithm.