Synthetic Minority Over-Sampling Technique Based Rotation Forest for the Classification of Unbalanced Hyperspectral Data
Wei Feng, Wenjiang Huang, Huichun Ye, Longlong Zhao · 2018
In this paper, we propose a novel Synthetic Minority Oversampling Technique based Rotation forest (SMOTERoF) algorithm for the classification of imbalanced hyperspectral image data. The main idea of the proposed method is to iteratively balance the class distribution of training set by SMOTE for each rotation decision tree. Experiment results on the hyperspectral image Indian Pines AVRIS with different imbalance ratio (IR) show that our algorithm obtains better classification performance compared with Rotation Forest (RoF), random undersampling, random oversampling, SMOTE, as well as Under sampling based RoF (UnderRoF) which is an extended version of UnderBagging.