Title page for ETD etd-050406-124140

Document Type	thesis
Author Name	Moraski, Ashley M.
URN	etd-050406-124140
Title	Classification via distance profile nearest neighbors
Degree	MS
Department	Mathematical Sciences
Advisors	Jayson Wilbur, Advisor
Keywords	classification distance profile nearest neighbor
Date of Presentation/Defense	2006-05-04
Availability	unrestricted
Abstract Most classification rules can be expressed in terms of a distance (or dissimilarity) from the point to be classified to each of the candidate classes. For example, linear discriminant analysis classifies points into the class for which the (sample) Mahalanobis distance is smallest. However, dependence among these point-to-group distance measures is generally ignored. The primary goal of this project is to investigate the properties of a general non-parametric classification rule which takes this dependence structure into account. A review of classification procedures and applications is presented. The distance profile nearest-neighbor classification rule is defined. Properties of the rule are then explored via application to both real and simulated data and comparisons to other classification rules are discussed.
Files	Moraski.pdf

Browse by Author | Browse by Department | Search all available ETDs