Multi-labeler Classification Using Kernel Representations and Mixture of Classifiers.
David Esteban Imbajoa-RuizI. D. GustinM. Bolaños-LedezmaAndrés F. Arciniegas-MejíaF. A. Guasmayan-GuasmayanM. J. Bravo-MontenegroAndrés Eduardo Castro-OspinaDiego Hernán Peluffo-OrdóñezPublished in: CIARP (2016)
Keyphrases
- support vector
- decision trees
- classification systems
- classification models
- svm classifier
- classification method
- classification algorithm
- classification accuracy
- improves the classification accuracy
- classification process
- supervised classification
- kernel classifiers
- training samples
- machine learning algorithms
- feature set
- kernel function
- accurate classification
- class labels
- multiple kernel learning
- classification procedure
- feature space
- feature selection
- higher classification accuracy
- multiclass classification
- support vector machine
- training set
- svm classification
- kernel machines
- k nearest neighbour
- classification rate
- kernel density estimators
- classifier combination
- multiple classifiers
- binary classifiers
- classification decisions
- image classification
- naive bayes
- probabilistic classifiers
- text classification
- nearest neighbor classifier
- machine learning methods
- supervised learning
- kernel methods
- feature subset
- reproducing kernel hilbert space
- support vector machine svm
- mixture model
- discriminant functions
- decision boundary
- linear classifiers
- training data
- feature vectors
- tree kernels
- feature extraction
- rule based classifier
- machine learning
- multi category
- optimum path forest
- accurate classifiers
- multiple classifier systems
- discriminative learning
- bayesian classifier
- nearest neighbour