Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets

doi:10.1016/j.neucom.2014.05.096

	Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets
	Bao, Lei 1,2; Juan, Cao 1; Li, Jintao 1; Zhang, Yongdong 1
	2016-01-08
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	172 页码:198-206
摘要	Considering the challenges of using SVM to learn concepts from large-scale imbalanced datasets, we proposed a new method: Boosted Near-miss Under-sampling on SVM ensembles (BNU-SVMs). The BNU-SVMs is under the framework of under-sampling ensemble method, where a sequence of SVMs is trained and the training dataset for each base SVM is selected by a Boosted Near-miss Under-sampling technique. More specifically, by adaptively updating weights over negative examples, the most near-miss negative examples in output space are selected in each iteration. Since the training dataset is balanced and reduced by under-sampling and the performance of classifier is improved by ensembles, the BNU-SVMs is a promising solution for large-scale and imbalance problem. Moreover, the negative examples selected by BNU-SVMs not only contain the most representative ones from data distribution perspective, but also cover the easily misclassified ones from data accuracy perspective. Therefore, the outperformance of the BNU-SVMs is expected. In addition, considering the computation cost caused by high-dimensional visual features, we proposed a kernel-distance pre-computation technique to further improve the efficiency of the BNU-SVMs. Experiments on TRECVID benchmark datasets show that the BNU-SVMs outperforms the previous methods significantly, which demonstrates that the BNU-SVMs is a both effective and efficient solution to concept detection in large-scale imbalanced datasets. (C) 2015 Published by Elsevier B.V.
关键词	Concept learning Large-scale Imbalance Ensmeble learnning Support Vector Machine Boosted Near-miss Under-sampling
DOI	10.1016/j.neucom.2014.05.096
收录类别	SCI
语种	英语
资助项目	National High Technology Research and Development Program of China[2014AA015202] ; National Natural Science Foundation of China[61172153] ; National Natural Science Foundation of China[61100087] ; National Key Technology Research and Development Program of China[2012BAH39B02]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000364884700020
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：43[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/9140
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Yongdong
作者单位	1.Chinese Acad Sci, ICT, Lab Adv Comp Technol Res, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Grad Univ, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Bao, Lei,Juan, Cao,Li, Jintao,et al. Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets[J]. NEUROCOMPUTING,2016,172:198-206.
APA	Bao, Lei,Juan, Cao,Li, Jintao,&Zhang, Yongdong.(2016).Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets.NEUROCOMPUTING,172,198-206.
MLA	Bao, Lei,et al."Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets".NEUROCOMPUTING 172(2016):198-206.