An incremental dimensionality reduction method on discriminant information for pattern classification

doi:10.1016/j.patrec.2009.06.013

CSpace

	An incremental dimensionality reduction method on discriminant information for pattern classification
	Hu, Xiaoqin 1; Yang, Zhixia 2,3; Jing, Ling 1
	2009-11-01
发表期刊	PATTERN RECOGNITION LETTERS
ISSN	0167-8655
卷号	30 期号:15 页码:1416-1423
摘要	From the view of classification, linear discriminant analysis (LDA) is a proper dimensionality reduction method which finds an optimal linear transformation that maximizes the class separability. However it is difficult to apply LDA in under sampled problems where the number of data samples is smaller than the dimensionality of data space, due to the singularity of scatter matrices caused by high-dimensionality. In order to make LDA applicable, we propose a new dimensionality reduction algorithm called discriminant multidimensional mapping (DMM), which combines the advantages of multidimensional scaling (MDS) and LDA. DMM is effective for small sample datasets with high-dimensionality. Its superiority is given from theoretical point of view. Then we extend DMM for large datasets and datasets with non-linear manifold respectively, and get two algorithms: landmark DMM (LDMM) and geodesic-metric discriminant mapping (GDM). The performances of these algorithms are also shown by preliminary numerical experiments. (C) 2009 Elsevier B.V. All rights reserved.
关键词	Dimensionality reduction Pattern classification Discriminant mapping
DOI	10.1016/j.patrec.2009.06.013
语种	英语
资助项目	National Natural Science Foundation of China[10631070] ; National Natural Science Foundation of China[10801112] ; China Postdoctoral Science Foundation[20080432573] ; Ph.D Graduate Start Research Foundation of Xinjiang University[BS080101]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000271363500009
出版者	ELSEVIER SCIENCE BV
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/8777
专题	中国科学院数学与系统科学研究院
通讯作者	Jing, Ling
作者单位	1.China Agr Univ, Coll Sci, Beijing 100083, Peoples R China 2.Xinjiang Univ, Coll Math & Syst Sci, Urumqi 830046, Peoples R China 3.CAS, Acad Math & Syst Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Hu, Xiaoqin,Yang, Zhixia,Jing, Ling. An incremental dimensionality reduction method on discriminant information for pattern classification[J]. PATTERN RECOGNITION LETTERS,2009,30(15):1416-1423.
APA	Hu, Xiaoqin,Yang, Zhixia,&Jing, Ling.(2009).An incremental dimensionality reduction method on discriminant information for pattern classification.PATTERN RECOGNITION LETTERS,30(15),1416-1423.
MLA	Hu, Xiaoqin,et al."An incremental dimensionality reduction method on discriminant information for pattern classification".PATTERN RECOGNITION LETTERS 30.15(2009):1416-1423.