Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data

doi:10.1109/JSTARS.2019.2922297

CORC > 理论物理研究所 > 中国科学院理论物理研究所 > 理论物理所科研产出 > 理论物理所1978-2010年知识产出

	Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data
	Feng, Wei 5; Dauphin, Gabriel 4; Huang, Wenjiang ; Quan, Yinghui 3; Bao, Wenxing 2; Wu, Mingquan 7; Li, Qiang 6
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2019
卷号	12 期号:7 页码:2159-2169
关键词	ENSEMBLES SELECTION SMOTE
ISSN号	1939-1404
DOI	10.1109/JSTARS.2019.2922297
英文摘要	Rotation forest (RoF) is a powerful ensemble classifier and has attracted substantial attention due to its performance in hyperspectral data classification. Multi-class imbalance learning is one of the biggest challenges in machine learning and remote sensing. The standard technique for constructing RoF ensemble tends to increase the overall accuracy; RoF has difficulty to sufficiently recognize the minority class. This paper proposes a novel dynamic SMOTE (synthetic minority oversampling technique)-based RoF algorithm for the multi-class imbalance problem. The main idea of the proposed method is to dynamically balance the class distribution before building each rotation decision tree. A resampling rate is set in each iteration (ranging from 10% in the first iteration to 100% in the last) and this ratio defines the number of minority class instances randomly resampled (with replacement) from the original dataset in each iteration. The rest of the minority class instances are generated by the SMOTE method. The reported results on three real hyperspectral datasets show that the proposed method can get better performance than random forest, RoF, and some popular data sampling methods.
学科主题	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
内容类型	期刊论文
源URL	[http://ir.itp.ac.cn/handle/311006/27215]
专题	理论物理研究所_理论物理所1978-2010年知识产出
作者单位	1.Chinese Acad Sci, Inst Theoret Phys, Beijing 100190, Peoples R China 2.Xidian Univ, Key Lab Radar Signal Proc, Xian 710071, Shaanxi, Peoples R China 3.Univ Paris 13, Inst Galilee, L2TI, Lab Informat Proc & Transmiss, F-93430 Villetaneuse, France 4.Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China 5.Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China 6.Chinese Acad Sci, Aerosp Informat Res Inst, State Key Lab Remote Sensing Sci, Beijing 100101, Peoples R China 7.Beifang Univ Nationalities, Sch Comp Sci & Engn, Yinchuan 750021, Ningxia, Peoples R China
推荐引用方式 GB/T 7714	Feng, Wei,Dauphin, Gabriel,Huang, Wenjiang,et al. Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2019,12(7):2159-2169.
APA	Feng, Wei.,Dauphin, Gabriel.,Huang, Wenjiang.,Quan, Yinghui.,Bao, Wenxing.,...&Li, Qiang.(2019).Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,12(7),2159-2169.
MLA	Feng, Wei,et al."Dynamic Synthetic Minority Over-Sampling Technique-Based Rotation Forest for the Classification of Imbalanced Hyperspectral Data".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 12.7(2019):2159-2169.