Classification and feature gene selection using the normalized maximum likelihood model for discrete regression.
Ioan TabusJorma RissanenJaakko AstolaPublished in: Signal Process. (2003)
Keyphrases
- gene selection
- cancer classification
- likelihood model
- feature vectors
- microarray
- dna microarray data
- gene expression profiles
- microarray data
- ovarian cancer
- feature ranking
- dna microarray
- support vector machine svm
- cancer diagnosis
- support vector
- feature selection
- feature set
- gene expression
- tumor classification
- colon cancer
- microarray datasets
- gene expression data
- microarray data analysis
- survival prediction
- pattern recognition
- microarray classification
- decision trees
- classification accuracy
- microarray analysis
- relevant genes
- machine learning methods
- model selection
- small number of samples
- feature subset
- feature extraction
- feature space
- training set
- class labels
- informative genes
- probabilistic model
- knn
- bayesian networks
- support vector machine
- svm classification
- data sets
- machine learning