A Supervised Feature Selection Method For Mixed-Type Data using Density-based Feature Clustering.
Xuyang YanMrinmoy SarkarBiniam GebruShabnam NazmiAbdollah HomaifarPublished in: SMC (2021)
Keyphrases
- clustering method
- synthetic data
- input data
- data sets
- clustering algorithm
- k means
- data points
- supervised feature selection
- categorical data
- spectral clustering
- missing data
- high dimensional data
- unsupervised learning
- probabilistic model
- feature set
- support vector machine
- cluster analysis
- training data
- feature subset
- similarity measure
- classification accuracy
- pairwise
- original data
- learning algorithm