𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Probability densities from distances and discrimination

✍ Scribed by C.M. Cuadras; R.A. Atkinson; J. Fortiana

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
346 KB
Volume
33
Category
Article
ISSN
0167-7152

No coin nor oath required. For personal study only.

✦ Synopsis

Given a population and a random vector X, by using distances between observations of X, we prove that it is, in general, possible to construct probability densities for X. This distance-based approach can present problems, from a multidimensional scaling point of view, for some monotonic density functions, where the construction must be made on the basis of symmetric functions instead of distances. A measure of divergence between the true density and this construction is given. The procedure aims to offer alternative methods for performing discriminant analysis.

πŸ“œ SIMILAR VOLUMES

Correlation functions from probability d
Correlation functions from probability densities
✍ Bernd A. Berg; Alberto Devoto πŸ“‚ Article πŸ“… 1987 πŸ› Elsevier Science 🌐 English βš– 363 KB

Correlation functions are calculated from histograms of probability densities. This method allows to analyse correlations of higher moments from the data. At least for exploratory studies it is by far more practical than direct calculation of the correlations of higher moments during the simulation.

Discriminant feature extraction using em
Discriminant feature extraction using empirical probability density estimation and a local basis library
✍ Naoki Saito; Ronald R. Coifman; Frank B. Geshwind; Fred Warner πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 158 KB

The authors previously developed the so-called local discriminant basis (LDB) method for signal and image classiΓΏcation problems. The original LDB method relies on di erences in the time-frequency energy distribution of each class: it selects the subspaces where these energy distributions are well s