Improving Classification by Removing or Relabeling Mislabeled Instances.
Stéphane LallichFabrice MuhlenbachDjamel A. ZighedPublished in: ISMIS (2002)
Keyphrases
- classification accuracy
- pattern recognition
- decision trees
- class labels
- land cover classification
- classification method
- image classification
- support vector machine
- feature selection
- machine learning
- classification systems
- randomly generated
- classification models
- feature vectors
- classification algorithm
- remote sensing
- data sets
- training samples
- feature extraction
- feature space
- cross validation
- benchmark datasets
- classification rules
- automatic classification
- classification scheme
- classification rate
- preprocessing
- single instance
- data stream classification