A new approach to dimensionality reduction based on locality preserving LDA

Author

Di Zhang ; Jiazhong He

Author_Institution

Sch. of Inf. Eng., Guangdong Med. Coll., Dongguan, China

fYear

2013

fDate

23-25 July 2013

Firstpage

531

Lastpage

535

Abstract

Linear discriminant analysis (LDA) is one of the most popular supervised dimensionality reduction (DR) techniques. However, LDA only captures global geometrical structure information of the data and ignores the geometrical variation of local data points of the same class. In this paper, a new supervised DR algorithm called local intraclass variation preserving LDA (LIPLDA) is proposed. We also show that the proposed algorithm can be extended to non-linear DR scenarios by applying the kernel trick.

Keywords

data reduction; LIPLDA; dimensionality reduction; global geometrical structure information; kernel trick; linear discriminant analysis; local intraclass variation preserving LDA; locality preserving LDA; nonlinear DR scenarios; supervised dimensionality reduction techniques; Algorithm design and analysis; Classification algorithms; Eigenvalues and eigenfunctions; Error analysis; Kernel; Principal component analysis; Training data; dimensionality reduction; linear discriminant analysis; locality preserving projection; pattern classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems and Knowledge Discovery (FSKD), 2013 10th International Conference on

Conference_Location

Shenyang

Type

conf

DOI

10.1109/FSKD.2013.6816254

Filename

6816254