Paper
18 September 1998 First look at a test statistic for dimensionality reduction
Bradley C. Wallet, Firooz A. Sadjadi
Author Affiliations +
Abstract
Previous work by the authors has studied the problem of searching for projections to low dimensional spaces which are optimal for classification based upon some training data set. In our earlier work, we relied upon using separate training and test data to attempt to estimate and correct the problem of overfitting. In this paper, we examine the problems introduced by using separate training and test data. We then propose a new approach based upon searching projections based upon maximizing the Mann-Whitney test statistic. We discuss efforts made towards calculating the exact distribution of the supremum of this statistic over the Grassmannian manifold of projections to R1.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bradley C. Wallet and Firooz A. Sadjadi "First look at a test statistic for dimensionality reduction", Proc. SPIE 3371, Automatic Target Recognition VIII, (18 September 1998); https://doi.org/10.1117/12.323828
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Automatic target recognition

Distance measurement

Statistical analysis

Warfare

Astatine

Data centers

Ferroelectric LCDs

RELATED CONTENT

Templates with lower mean square error for ATR
Proceedings of SPIE (July 28 1997)
Syntactic pattern recognition for HRR signatures
Proceedings of SPIE (August 24 2000)
Automatic recognition of targets from hyperspectra images
Proceedings of SPIE (December 04 1998)
Millimeter-wave ATR: a study on feature robustness
Proceedings of SPIE (September 21 2004)
High dimensional data computational demand minimization
Proceedings of SPIE (September 18 1998)

Back to Top