UDC 519.246.8:681.5.01:681.514
FOUNDATIONS OF BASE MODELS` ADAPTATION TO ANALYZE FINITE FLUCTUATIONS
S. L. Blumin, Dr. Sc.(Phys. and Math.), full professor, LSTU, Lipetsk, Russia;
orcid.org/0000-0002-0852-0444, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
N. Yu. Zhbanova, Ph.D. (Tech.), associate professor, LSTU, Lipetsk, Russia;
orcid.org/0000-0001-7324-9841, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
S. A. Zhbanov, senior lecturer, LSTU, Lipetsk, Russia;
orcid.org/0000-0002-7214-3401, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The article demonstrates well-known and new adaptive models and algorithms allowing to analyze processes in the systems with complex structure, and may be used as base models for analysis of finite fluctuations (AFF). The aim is to describe existing adaptive methods, and to design modification of Boyd method with idempotent metrics. The assessment of input finite fluctuations impact on output finite fluctuations being the basis for AFF is an actual problem related to the modeling of dynamic processes, that characterize complex technological and organizational systems. On the first stage we must design base models for AFF, via the research of considerated dynamic process. The promising way is to complete standard modeling methods of the least squares and least modules with regularization component, which allows including adaptive properties in the models.
Key words: adaptive models, analysis of finite fluctuations, compressed regression, filtering, self-similar processes.