The possibility of applying a new approach to the implementation of Chernoff faces as artificial agents for the analysis of multidimensional systems is considered. The main stages of human perception of a multidimensional system are described. The analysis of the possibilities of the classical method based on the works of domestic and foreign authors is carried out, the application area of the method is described. A method for constructing Chernoff faces using polygons is proposed, which allows significantly expanding the capabilities of the method and describing more complex economic systems, as well as increasing the information content of the resulting images. The parameters that characterize the image point are listed. The main stages of data preparation are described, criteria for comparing data groups and image elements are formulated, and the procedure for constructing Chernoff faces based on the available data is given. A method of normalization of values is proposed, which allows avoiding unnatural image distortions for the correct perception of the information contained in the image by the operator. A method for calculating the coordinates of the points of the image of Chernoff faces based on an array of data is developed. Possible types of Chernoff faces obtained using the new method are given, as well as diagrams of some individual image elements. The possibility of implementing a new method in the form of code with a graphical interface is considered.
Polygonal Chernoff faces as artificial agents for analysis of multidimensional economic systems
XLV ACADEMIC SPACE CONFERENCE, DEDICATED TO THE MEMORY OF ACADEMICIAN S.P. KOROLEV AND OTHER OUTSTANDING NATIONAL SCIENTISTS — PIONEERS OF SPACE EXPLORATION ; 2021 ; Moscow, Russia
AIP Conference Proceedings ; 2549 , 1
20.07.2023
5 pages
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Chernoff product formula for C0-semigroups on L∞
American Institute of Physics | 2012
|A New Mathematical Model for Geometric Tolerances as Applied to Polygonal Faces
Online Contents | 2004
|Extending Kernel Fisher Discriminant Analysis with the Weighted Pairwise Chernoff Criterion
British Library Conference Proceedings | 2006
|