Investigation of feature dimension reduction schemes for classification applications
Loading...
Authors
Fargues, Monique P.
Subjects
Feature dimension
classification
Computer software.
kernel-based scheme
classification
Computer software.
kernel-based scheme
Advisors
Date of Issue
2001-06
Date
2001-06
Publisher
Monterey, California. Naval Postgraduate School
Language
Abstract
Extracting relevant features that allow for class discrimination is the first critical step in classification applications. However, this step often leads to high-dimensional feature spaces, which requires large datasets to create viable classification schemes. As a result, there is a strong incentive to reduce the feature space dimension. Two classical types of approaches to reduce feature dimension exist Principal Component Analysis (PCA)-based or discriminant-based approaches. The main difference between the two types lies in the criterion selected; PCA-based schemes seek a projection direction which bests represents the data in a norm sense, while discriminant-based schemes seek a projection that best separates the class data. This study presents a comparison of three discriminant-based feature dimension reduction schemes: the Mean Separator Neural Network (MSNN), the Mahalanobis-based Dimension Reduction scheme (MBDR), and the kernel-based Generalized Discriminant Analysis (GDA) approach. PCA is included for comparison purposes as it is also widely used in classification applications. All four feature dimension reduction schemes are implemented and evaluated by applying the transformed features to a basic minimum distance classifier. Three classification datasets commonly used in statistics for benchmarking purposes are selected to compare the schemes and results discussed Results show the kernel-based generalized discriminant analysis approach to lead to consistently higher classification performances than the other schemes considered in the study for the data investigated.
Type
Technical Report
Description
Series/Report No
Identifiers
NPS Report Number
NPS-EC-01-005
Sponsors
This report was sponsored by the Naval Postgraduate School Center for
Reconnaissance Research.
Funding
MIPR#A448195
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.