Breast cancer diagnosis using feature selection techniques
Authors:
- 3 March 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
This study focuses on feature selection for breast cancer diagnosis. Since the feature selection became a crucial task in machine learning, we will experiment some filter, wrapper approach and embedded approach on Wisconsin breast cancer dataset, which is commonly used by researchers who use machine-learning methods for breast cancer diagnosis. The performance of the feature selection method is evaluated by classification accuracy using two kinds of classifiers SVM and KNN.Keywords
This publication has 14 references indexed in Scilit:
- Unsupervised feature selection with ordinal locality2017
- A hybrid feature selection approach based on ensemble method for high-dimensional data2017
- LASSO: A feature selection technique in predictive modeling for machine learning2016
- Breast cancer diagnosis using GA feature selection and Rotation ForestNeural Computing and Applications, 2015
- The mRMR variable selection method: a comparative study for functional dataJournal of Statistical Computation and Simulation, 2015
- Neural Network Classifier with Entropy Based Feature Selection on Breast Cancer DiagnosisJournal of Medical Systems, 2009
- Support vector machines combined with feature selection for breast cancer diagnosisExpert Systems with Applications, 2009
- An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition systemApplied Mathematics and Computation, 2008
- Improved binary PSO for feature selection using gene expression dataComputational Biology and Chemistry, 2008
- A GA-based feature selection and parameters optimizationfor support vector machinesExpert Systems with Applications, 2006