Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data.
Wei FengGabriel DauphinWenjiang HuangYinghui QuanWenxing BaoMingquan WuQiang LiPublished in: IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2019)
Keyphrases
- hyperspectral data
- hyperspectral images
- hyperspectral
- minority class
- class imbalance
- class distribution
- hyperspectral imagery
- imbalanced data
- random projections
- multispectral
- remote sensing
- classification accuracy
- training set
- pattern recognition
- infrared
- supervised learning
- decision trees
- cost sensitive
- feature selection
- classification algorithm
- class labels
- image classification
- support vector machine
- image data
- feature extraction
- svm classifier
- machine learning methods
- ensemble methods
- classification models
- random forest
- training samples
- feature vectors
- feature space
- support vector
- machine learning