Computational Intelligence for Observation and Monitoring: A Case Study of Imbalanced Hyperspectral Image Data Classification

Abstract

Imbalance in hyperspectral images creates a crisis in its analysis and classification operation. Resampling techniques are utilized to minimize the data imbalance. Although only a limited number of resampling methods were explored in the previous research, a small quantity of work has been done. In this study, we propose a novel illustrative study of the performance of the existing resampling techniques, viz. oversampling, undersampling, and hybrid sampling, for removing the imbalance from the minor samples of the hyperspectral dataset. The balanced dataset is classified in the next step, using the tree-based ensemble classifiers by including the spectral and spatial features. Finally, the comparative study is performed based on the statistical analysis of the outcome obtained from those classifiers that are discussed in the results section. In addition, we applied a new ensemble hybrid classifier named random rotation forest to our dataset. Three benchmark hyperspectral datasets: Indian Pines, Salinas Valley, and Pavia University, are applied for performing the experiments. We have taken precision, recall, F score, Cohen kappa, and overall accuracy as assessment metrics to evaluate our model. The obtained result shows that SMOTE, Tomek Links, and their combinations stand out to be the more optimized resampling strategies. Moreover, the ensemble classifiers such as rotation forest and random rotation ensemble provide more accuracy than others of their kind.

Assessment of Soybean Lodging Using UAV Imagery and Machine Learning

“…Random forest classifier showed the training score and AUC ROC values of 99.40% and 0.72 (without sampling), 99.78% and 0.73 (undersampling), and 99.92% and 0.90 (SMOTE sampling), respectively. Hyperspectral imagery data available from the public domain with 16 classes were classified using tree-based ensembled classifiers by Datta [49], encompassing several data balancing methods, which resulted in SMOTE, Tomek-Links and their combinations of higher accuracy and best resampling strategy. This study followed the same data balancing method, SMOTE-ENN, where the number of NL datasets (Table 1) was reduced, and the number of ML, HL, and SL increased using the data balancing method.…”

Mixed Pixel Classification on Hyperspectral Image Using Imbalanced Learning and Hyperparameter Tuning Methods

“…The classifier combined with oversampling algorithms such as SMOTE and ADASYN can produce excellent classification results for balanced hyperspectral datasets. Also, the maximum total time consumed by ADASYN for all the classifiers [22].…”