A Method of Nonlinear Manifold Classification using ISOMAP

Author

Lifang, Wu ; Ning, Wei ; Juanjuan, Wang ; Yue, Guo

Author_Institution

Sch. of Electron. Inf. & Control Eng., Beijing Univ. of Technol.

Volume

1

fYear

2006

fDate

Aug. 30 2006-Sept. 1 2006

Firstpage

22

Lastpage

25

Abstract

In this paper, a new nonlinear classification algorithm is proposed using Isomap (isometric feature mapping). First, nonlinear dimensionality reduction algorithm is implemented using Isomap; then nonlinear mapping matrix is approximated by local linear mapping; next dimensionality reduction for all data sets is implemented by local linear mapping; finally linear classification is implemented. Experimental results confirm the efficiency of proposed algorithm

Keywords

differential geometry; feature extraction; matrix algebra; pattern classification; isometric feature mapping; linear classification; local linear mapping; nonlinear dimensionality reduction algorithm; nonlinear manifold classification algorithm; nonlinear mapping matrix; Classification algorithms; Control engineering; Degradation; Euclidean distance; Feature extraction; Geophysics computing; Linear approximation; Manifolds; Pattern classification; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on

Conference_Location

Beijing

Print_ISBN

0-7695-2616-0

Type

conf

DOI

10.1109/ICICIC.2006.11

Filename

1691732