On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping.
Koreen MillardMurray RichardsonPublished in: Remote. Sens. (2015)
Keyphrases
- random forest
- sample selection
- training data
- image classification
- decision trees
- multi label
- active learning
- random forests
- svm classification
- feature extraction
- classification accuracy
- feature set
- ensemble methods
- data sets
- support vector machine
- selection strategy
- training examples
- ensemble learning
- image features
- naive bayes
- training set
- training process
- learning algorithm
- class labels
- decision tree learning algorithms
- learning tasks
- test data
- svm classifier
- test set
- prediction accuracy
- machine learning algorithms
- unlabeled data
- machine learning
- training samples
- supervised learning