| Autor: |
JAVIER PULIDO CEJUDO, CARLOS CUEVAS COVARRUBIAS |
| Jazyk: |
English<br />Spanish; Castilian |
| Rok vydání: |
2017 |
| Předmět: |
|
| Zdroj: |
Revista de Matemática: Teoría y Aplicaciones, Vol 24, Iss 1, Pp 115-127 (2017) |
| Druh dokumentu: |
article |
| ISSN: |
2215-3373 |
| DOI: |
10.15517/rmta.v24i1.27774 |
| Popis: |
We consider the statistical supervised classification problem from adynamical systems approach. We assume that two classes exist and that, for each one, a multivariate normal distribution determines the probability to be in a certain region in then dimensional real vector space. These density functions are the potentials of corresponding gradient vector fields for each class; we construct a “classifying vector field” as a suitable weighted mean ofthem. From data known in the literature, we estimate the population parameters, and the classes are successfully distinguished; we compute and present confusion matrices. A one and two-dimensional analysis is given. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
