Abstract

Earlier, a constructive--synthesizing model of a fractal time series was developed by authors. A software application for modeling deterministic and stochastic fractal time series and a single-threaded program for their recovery based on this model was developed. The identified shortcomings, namely rather low time efficiency and the difficulty of scaling the restoration process, led to the need to radically change the system architecture. This work presents the main changes: introduction of the agent-oriented architecture approach and changed fitness function of genetic algorithm chromosomes, which takes into account the discrepancy of several model and reconstructed time series. The last one made it possible to level the stochasticity of time series to some extent

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call