A Supervised Filter Feature Selection method for mixed data based on Spectral Feature Selection and Information-theory redundancy analysis.
Saúl Solorio-FernándezJosé Fco. Martínez-TrinidadJesús Ariel Carrasco-OchoaPublished in: Pattern Recognit. Lett. (2020)
Keyphrases
- feature selection
- information theory
- mutual information
- feature set
- information theoretic
- feature extraction
- conditional entropy
- spectral analysis
- support vector
- classification accuracy
- similarity measure
- pairwise
- support vector machine
- semi supervised
- knn
- feature selection algorithms
- wavelet transform
- data sets
- video sequences
- learning algorithm
- machine learning