Fast feature selection aimed at high-dimensional data via hybrid-sequential-ranked searches.
Roberto RuizJosé C. RiquelmeJesús S. Aguilar-RuizMiguel García-TorresPublished in: Expert Syst. Appl. (2012)
Keyphrases
- high dimensional data
- high dimensionality
- feature selection
- dimensionality reduction
- low dimensional
- high dimensional
- dimension reduction
- nearest neighbor
- gene expression data
- high dimensions
- data analysis
- data points
- subspace clustering
- missing values
- data sets
- original data
- nonlinear dimensionality reduction
- data distribution
- input space
- manifold learning
- clustering high dimensional data
- text categorization
- similarity search
- linear discriminant analysis
- high dimensional spaces
- pattern recognition
- variable selection
- lower dimensional
- machine learning
- principal component analysis
- feature space
- dimensional data
- text data
- subspace learning
- real world
- high dimensional data sets
- high dimensional datasets
- feature selection algorithms
- knn
- feature set
- text classification
- sparse representation
- decision trees
- feature extraction
- microarray data
- image processing
- small sample size