Feature selection for pattern classification with Gaussian mixture models: A new objective criterion.
S. KrishnanK. SamudravijayaP. V. S. RaoPublished in: Pattern Recognit. Lett. (1996)
Keyphrases
- pattern classification
- gaussian mixture model
- feature selection
- feature extraction
- feature space
- speaker recognition
- feature vectors
- mixture model
- probabilistic neural network
- pattern recognition
- pattern classification problems
- maximum likelihood
- expectation maximization
- em algorithm
- mutual information
- nearest neighbor rule
- gaussian mixture
- density estimation
- probability density
- feature subset selection
- maximum likelihood criterion
- support vector
- dimensionality reduction
- classification accuracy
- probability density function
- support vector machine
- gaussian distribution
- neural network
- speaker identification
- model selection
- minimum message length
- learning algorithm
- supervised learning
- feature set
- knn
- linear discriminant analysis
- text classification
- multiscale
- unsupervised learning