Institute of Computing Technology, Chinese Academy IR
Boosted Near-miss Under-sampling on SVM ensembles for concept detection in large-scale imbalanced datasets | |
Bao, Lei1,2; Juan, Cao1; Li, Jintao1; Zhang, Yongdong1 | |
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 | |
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. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论