Title: feature extraction using maximum variance sparse mapping
Author: Liu Jin
; Li Bo
; Zhang Wen-Sheng
Keyword: Feature extraction
; Optimization
Source: Neural Computing and Applications
Issued Date: 2012
Volume: 21, Issue: 8, Pages: 1827-1833 Indexed Type: EI
Department: (1) State Key Laboratory of Software Engineering Wuhan University 430072 Wuhan China; (2) College of Computer Science and Technology Wuhan University of Science and Technology 430081 Wuhan China; (3) Key Lab Complex System and Intelligence Science Institute of Automation Chinese Academy of Science 100190 Beijing China
Abstract: In this paper, a multiple sub-manifold learning method-oriented classification is presented via sparse representation, which is named maximum variance sparse mapping. Based on the assumption that data with the same label locate on a sub-manifold and different class data reside in the corresponding sub-manifolds, the proposed algorithm can construct an objective function which aims to project the original data into a subspace with maximum sub-manifold distance and minimum manifold locality. Moreover, instead of setting the weights between any two points directly or obtaining those by a square optimal problem, the optimal weights in this new algorithm can be approached using L1 minimization. The proposed algorithm is efficient, which can be validated by experiments on some benchmark databases. © 2011 Springer-Verlag London Limited. English Abstract: In this paper, a multiple sub-manifold learning method-oriented classification is presented via sparse representation, which is named maximum variance sparse mapping. Based on the assumption that data with the same label locate on a sub-manifold and different class data reside in the corresponding sub-manifolds, the proposed algorithm can construct an objective function which aims to project the original data into a subspace with maximum sub-manifold distance and minimum manifold locality. Moreover, instead of setting the weights between any two points directly or obtaining those by a square optimal problem, the optimal weights in this new algorithm can be approached using L1 minimization. The proposed algorithm is efficient, which can be validated by experiments on some benchmark databases. © 2011 Springer-Verlag London Limited. Language: 英语
Content Type: 期刊论文
URI: http://ir.iscas.ac.cn/handle/311060/15436
Appears in Collections: 软件所图书馆_期刊论文
There are no files associated with this item.
Recommended Citation:
Liu Jin,Li Bo,Zhang Wen-Sheng. feature extraction using maximum variance sparse mapping[J]. Neural Computing and Applications,2012-01-01,21(8):1827-1833.
