Nonparametric System for Automatic Classification of Large-Scale Statistical Data

The structure of a nonparametric system for automatic classification of large-scale statistical data is proposed and substantiated. The structure of the system under consideration is made up of a technique for compressing the initial information, algorithms for automatic classification of the transformed data, and a procedure for aggregating the results obtained. To implement the functions of the system under study, new methods are used for testing hypotheses about the distributions of random variables and discretizing the range of their values. The effectiveness of the system is illustrated by the results of its application in assessing the state of forests damaged by the four-eyed fir bark beetle, according to remote sensing data.