A formulation and comparison of two linear feature selection techniques applicable to statistical classification
DOI10.1016/0031-3203(84)90083-9zbMath0557.62060OpenAlexW1983365877MaRDI QIDQ761746
Dean M. Young, Patrick L. Odell
Publication date: 1984
Published in: Pattern Recognition (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0031-3203(84)90083-9
decompositiondimension reductionprincipal componentssingular valuemisclassificationcomparison of linear feature selection techniquesprobability ofseparability measuressmallest Bayes- classification-region-preserving dimensionWilk's method
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Monte Carlo methods (65C05)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Distance preserving linear feature selection
- Feature selection for best mean square approximation of class densities
- Linear dimension reduction and Bayes classification
- Linear dimension reduction and Bayes classification with unknown population parameters
- On minimizing the probability of misclassification for linear feature selection
- Feature combinations and the divergence criterion
- Linear feature selection with applications
- A model for dimension reduction in pattern recognition using continuous data
- Statistical Properties of Error Estimators in Performance Assessment of Recognition Systems
- Feature combinations and the bhattacharyya criterion
This page was built for publication: A formulation and comparison of two linear feature selection techniques applicable to statistical classification
