Data and knowledge classification in intelligence informational systems by the evolutionary method

Abstract

This article discusses the promising direction in the field of intelligence informational system such as knowledge bases development. These knowledge bases use ontology systemization as a tool for classification of domain objects. The developed model is able to select essential features of classifiable objects. To solve problems of classification and structuring of data and knowledge, we suggest a new evolutionary approach based on the arranging of knowledge objects with respect to the basic element inside of a multidimensional space of features. The basic element is denoted by the genetic algorithm (GA). This algorithm allows to obtain the effective solution of classification with the use of different types of basic element representation inside of multidimensional space and various classes ordering in sequence of ontology objects. The genetic algorithm is an iterative probabilistic heuristic search algorithm with simultaneous use of a variety of populations from alternative solution space.