Benchmark for filter methods for feature selection in high-dimensional classification data.
Andrea BommertXudong SunBernd BischlJörg RahnenführerMichel LangPublished in: Comput. Stat. Data Anal. (2020)
Keyphrases
- feature selection
- high dimensional data
- high dimensional
- small samples
- data sets
- data points
- classification method
- text classification
- machine learning methods
- classification performances
- feature subset
- data sources
- noisy data
- high dimensionality
- feature space
- statistical methods
- data mining techniques
- data analysis
- dimension reduction
- irrelevant features
- selecting relevant features
- dimensionality reduction
- classification accuracy
- missing values
- nearest neighbor
- support vector machine
- support vector
- variable selection
- informative features
- sparse data
- preprocessing
- feature extraction
- benchmark datasets
- irrelevant attributes
- training data
- high dimensional spaces
- discriminative features
- feature selection algorithms
- classification models
- training set
- supervised learning
- similarity search