Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyper-spectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning.
Quan, Y, Zhong, X, Wei, FENG, Chan, JC-W, Li, Q & Xing, M 2021, 'SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification', Remote Sensing, vol. 13, no. 3, 464. https://doi.org/10.3390/rs13030464
Quan, Y., Zhong, X., Wei, FENG., Chan, J. C.-W., Li, Q., & Xing, M. (2021). SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification. Remote Sensing, 13(3), Article 464. https://doi.org/10.3390/rs13030464
@article{9ba2ce3fa9ac466aa44dcfc918c2a42d,
title = "SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification",
abstract = "Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyper-spectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning.",
author = "Yinghui Quan and Xian Zhong and FENG Wei and Chan, {Jonathan Cheung-Wai} and Qiang Li and Mengdao Xing",
note = "Funding Information: Funding: This research was funded by the National Natural Science Foundation of China (61772397, 12005169), National Key R&D Program of China (2016YFE0200400), the Open Research Fund of Key Laboratory of Digital Earth Science (2019LDE005), science and technology innovation team of Shaanxi Province (2019TD-002), Fundamental Research Funds for the Central Universities (XJS200205), and the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University. Funding Information: Acknowledgments: This work is supported by the National Natural Science Foundation of China (61772397, 12005169), National Key R&D Program of China (2016YFE0200400), the Open Research Fund of Key Laboratory of Digital Earth Science (2019LDE005), science and technology innovation team of Shaanxi Province (2019TD-002), Fundamental Research Funds for the Central Universities (XJS200205), and the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University. Publisher Copyright: {\textcopyright} 2021 by the authors. Licensee MDPI, Basel, Switzerland.",
year = "2021",
month = jan,
doi = "10.3390/rs13030464",
language = "English",
volume = "13",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Torrent Valencia: Recent Advances, [2024]-",
number = "3",
}