Title :
Supervised Discriminant Nonnegative Matrix Factorization Method
Author :
Pei, XiaoBing ; Xiao, Laiyuan
Author_Institution :
Coll. of Software, Huazhong Univ. of Sci. & Technol., Wuhan, China
fDate :
Nov. 30 2009-Dec. 1 2009
Abstract :
In this paper, a supervised discriminant NMF (SDNMF) model is investigated. The idea is to incorporate the discriminate and the class information preserving constraints into the NMF decomposition in order to extract latent semantic spaces that enforce the discriminate and class information preserving properties. Finally, experimental evaluation is performed on the SECTOR data set.
Keywords :
constraint handling; document handling; matrix decomposition; NMF decomposition; SECTOR data set; class information preserving constraints; discriminate information preserving properties; latent semantic spaces; supervised discriminant nonnegative matrix factorization method; Additives; Biomedical imaging; Data mining; Educational institutions; Knowledge acquisition; Large scale integration; Matrix decomposition; Principal component analysis; Space technology; Sparse matrices; Dimensionality reduction; Nonnegative matrix factorization;
Conference_Titel :
Knowledge Acquisition and Modeling, 2009. KAM '09. Second International Symposium on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3888-4
DOI :
10.1109/KAM.2009.261
