Pattern Recognition Based on Scale Invariant Discriminant Functions.
Abstract
Some probability models for classifying individuals as belonging to one of two or more populations using scale invariant discriminant functions are considered. The investigation is motivated by practical situations where the observed data on an individual are in the form of ratios of some basic measurements or measurements scaled by an unknown non-negative number. The probability models are obtained by considering a p-vector random variable X with a known distribution and deriving the distribution of the random vector Y = G(X) .1 X, where G(X) is a non-negative measure of size such that G(lambda X) = Lambda G(X) for lambda > 0. Explicit expressions are obtained for the densities of what are called Angular Gaussian, Compositional Gaussian, Type 1 and Compositional Gaussian, Type 2 distributions. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1986
- Accession Number
- ADA170809
Entities
People
- Calyampudi Radhakrishna Rao
- Tarmo M. Pukkila
Organizations
- University of Pittsburgh