Preserving empirical data utility in k-anonymous microaggregation via linear discriminant analysis.
Ana Rodríguez-HoyosDavid Rebollo-MonederoJosé Estrada-JiménezJordi FornéLuis Urquiza-AguiarPublished in: Eng. Appl. Artif. Intell. (2020)
Keyphrases
- empirical data
- linear discriminant analysis
- discriminant analysis
- face recognition
- dimensionality reduction
- principal component analysis
- dimension reduction
- small sample size
- discriminant features
- feature extraction
- support vector machine svm
- null space
- support vector
- high dimensional data
- fisher criterion
- utility function
- principal components analysis
- feature space
- class separability
- scatter matrices
- linear discriminant
- discriminative information
- subspace methods
- multivariate statistical
- original data
- scatter matrix
- dealing with high dimensional data
- subspace analysis
- information loss
- data sets
- machine learning
- locality preserving projections
- discriminant information
- k nearest neighbor
- image processing