An effective feature selection method based on pair-wise feature proximity for high dimensional low sample size data.
S. L. HappyRamanarayan MohantyAurobinda RoutrayPublished in: EUSIPCO (2017)
Keyphrases
- sample size
- pairwise
- statistical power
- random samples
- noisy data
- data points
- hypothesis tests
- training data
- high dimensional
- statistical methods
- input data
- similarity matrix
- covariance matrix
- training samples
- high dimensional data
- nearest neighbor
- objective function
- data structure
- data analysis
- data sets
- feature set
- worst case
- upper bound
- support vector machine svm
- support vector machine
- model selection
- training set
- sampling algorithm
- information criterion
- small samples
- similarity measure