Intelligent Decision-Making Based on Self-Organization

Abstract

The article deals with main terms of decision support systems based on self-organization. Moreover, the maincomponents and algorithms used in these systems have been described. The authors have provided a structure of the decision support system and it input parameters. The input data include a database, a knowledge base, and a model of the base. The article has concerned a statement of the parametric optimization problem. In terms of the computer-aided design systems, the search of optimal solutions is complicated by the incompleteness of a priori mathematical description of objects. The aim of the parametric optimization algorithm is to find a set of parameters in which the objective function takes the minimum value. The self-organization process has been analysed to build in it in the intelligent decision-making system. The authors have considered bioinspired self-organization algorithms based on the behaviour of bats and monkeys in nature. These algorithms have several advantages, such as scalability, fault tolerance, adaptation, modularity, autonomy, and parallelism. It makes them more effective as compared to classical approaches. Thus, the modified monkey search algorithm has been considered in the article. A model of the optimization problem based on bats behaviour is also provided. To estimate the effectiveness of developed algorithms,the computational experiments have been conducted. The use of bioinspired algorithms in intelligent decision-making systems is a promising area, as confirmed by theexperiments.