|
Article information
2025 , Volume 30, ¹ 5, p.32-49
Okhtilev M.Y., Musayev A.A.
Sequential detection algorithms for the systematic component of non-stationary random processes
The problem of sequential filtering of chaotic random processes is addressed within the broader context of managing the state of a dynamic object in an unstable immersion environment. Under conditions of unstable dynamics, traditional schemes for sequential processing of observations either do not ensure the required level of smoothing for the realization of the process or lead to significant lagging bias in the estimated conditional mean. This work conducts a numerical analysis of the effectiveness of algorithms for identifying the systematic component of chaotic processes based on terminal indicators of management performance. A series of filtering algorithms with improved characteristics regarding the criteria for smoothing quality and control quality indicators, based on the systematic component extracted from noisy observations, are proposed.
Keywords: stochastic chaos, sequential filtering, terminal performance indicator, trading, control strategy
Author(s):
Okhtilev Michail Yurjevich
Dr.
Position: General Scientist
Office: St Petersburg Federal Research Center of the Russian Academy of Sciences
Address: 199178, Russia, St-Petersburg, 14 line, 39
E-mail: oxt@mail.ru
SPIN-code: 1782-1556Musayev Andrey Alexandrovich
PhD.
Position: Associate Professor
Address: 197101, Russia, St-Petersburg, Kronverksky pr., 49, lit. A
E-mail: amusayev1990@gmail.com
Bibliography link:
Okhtilev M.Y., Musayev A.A. Sequential detection algorithms for the systematic component of non-stationary random processes // Computational technologies. 2025. V. 30. ¹ 5. P. 32-49
|
