A New Method Identification of Interval Discrete Models of Objects with a Randomized Selection of Structural Elements

• Published in: 2023 13th International Conference on Advanced Computer Information Technologies (ACIT) pp. 176 - 181
• Main Authors: Dyvak, Mykola, Melnyk, Andriy, Porplytsya, Natalia, Spivak, Iryna, Bodnar, Olga
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21-09-2023
• Subjects: Adaptation models; behavioral models of artificial bee colony; Behavioral sciences; Carbon monoxide; Chemical elements; Computational modeling; interval model; Object recognition; Probability; structural identification
• DOI: 10.1109/ACIT58437.2023.10275572
• EISSN: 2770-5226

The article deals with the problem of identification of interval discrete models of complex objects. A new method of structural identification of these models based on behavioral models of bee colonies (BMBC) is proposed and substantiated, which includes computational procedures of adaptive setting of the random selection of structural elements for the formation of new structures. These procedures are based on the calculation of probability of the selection after the completion of the corresponding phase of BMBC taking into account the history of success of the formation of applicant models for each element. The peculiarities of the application of the given method have been studied. A comparative analysis of computational complexity of application of existing and proposed methods was made on the example of the construction of interval models of the dynamics of concentration of harmful emissions of carbon monoxide CO in homogenious environment due to the uniform movement of traffic flow with constant power of emissions.