Share Email Print

Proceedings Paper

Geometric multi-resolution analysis based classification for high dimensional data
Author(s): Dung N. Tran; Sang Peter Chin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Data sets are often modeled as point clouds lying in a high dimensional space. In practice, they usually reside on or near a much lower dimensional manifold embedded in the ambient space; this feature allows for both a simple representation of the data as well as accurate performance for statistical inference procedures such as estimation, regression and classification. In this paper we propose a framework based on geometric multi-resolution analysis (GMRA) to tackle the problem of classifying data lying around a low-dimensional set M embedded in a high-dimensional space RD. We test our algorithms on real data sets and demonstrate its efficacy in the presence of noise.

Paper Details

Date Published: 18 June 2014
PDF: 8 pages
Proc. SPIE 9097, Cyber Sensing 2014, 90970L (18 June 2014); doi: 10.1117/12.2063316
Show Author Affiliations
Dung N. Tran, Johns Hopkins Univ. (United States)
Sang Peter Chin, Johns Hopkins Univ. (United States)
Draper Lab. (United States)

Published in SPIE Proceedings Vol. 9097:
Cyber Sensing 2014
Igor V. Ternovskiy; Peter Chin, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?