Multithreaded and Spark parallelization of feature selection filters.
Carlos Eiras-FrancoVerónica Bolón-CanedoSabela RamosJorge González-DomínguezAmparo Alonso-BetanzosJuan TouriñoPublished in: J. Comput. Sci. (2016)
Keyphrases
- feature selection
- shared memory
- text categorization
- distributed memory
- mutual information
- parallel processing
- text classification
- information gain
- support vector
- feature selection algorithms
- multi class
- feature set
- irrelevant features
- edge enhancement
- mutual exclusion
- parallel execution
- feature subset
- feature space
- machine learning
- adaptive filtering
- bandpass
- low pass filter
- selected features
- gabor filters
- multi task
- neural network
- classification accuracy
- knn
- support vector machine
- selecting relevant features
- edge detection
- dimensionality reduction
- model selection
- small sample
- unsupervised learning
- order statistics
- discriminative features
- high dimensionality
- gene expression data
- multi user