Abstract—Feature selection is an important issue in classification of cancer diagnosis. In this paper, a new feature selection method, named improved F-Score is applied for breast cancer diagnosis. First, the improved F-Score values of all the features are calculated using improved F-Score formula. Then the mean value is computed for the calculated improved F-Score values. The improved F-Score values which are greater than the mean improved F-Score are selected. Wisconsin breast cancer dataset (WBCD) is used in this study. As classification algorithms, Support Vector Machine and RBF Network are sued. The results obtained from improved F-Score with Support Vector Machines have produced efficient results compared to improved F-Score with RBF Network. Therefore we show that improved F-Score combined with promising than improved F-Score with RBF Network.
Index Terms—Breast cancer, feature selection, improved F-Score, RBF network, SVM.
The authors are with Department of Computer Applications, PSNA College of Engineering & Technology, Dindigul, Tamilnadu, India ( email:firstname.lastname@example.org)
Cite:P. Jaganathan, N. Rajkumar, and R. Kuppuchamy, "A Comparative Study of Improved F-Score with Support Vector Machine and RBF Network for Breast Cancer Classification," International Journal of Machine Learning and Computing vol.2, no. 6, pp. 741-745, 2012.