scientific article; zbMATH DE number 3903784

From MaRDI portal
Publication:3681765





[For the entire collection see Zbl 0496.00013.] We begin by reviewing the standard approach to the problem of discriminating between two normal processes with unequal means or covariance functions. The two cases lead separately to linear or quadratic discriminant functions which can be approximated by spectral methods if the covariance function is stationary. The discriminant functions and their performance characteristics are approximated by frequency domain methods, leading to simple and easily computed expressions. A section is included which discusses methods for (1) determining whether the group patterns are better modelled as by differing in the mean values or covariances (spectra), and (2) the estimation of means and spectra from a learning population. Finally an example shows the application of the techniques to the problem of discriminating between short period seismic recordings of earthquakes and explosions.




Cited in
(44)








This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3681765)