2006 | OriginalPaper | Chapter
Real-Time Identification and Forecasting of Chaotic Time Series Using Hybrid Systems of Computational Intelligence
Authors : Yevgeniy Bodyanskiy, Vitaliy Kolodyazhniy
Published in: Integration of Fuzzy Logic and Chaos Theory
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
In this chapter, the problems of identification, modeling, and forecasting of chaotic signals are discussed. These problems are solved with the use of the conventional techniques of computational intelligence as radial basis neural networks and learning neuro-fuzzy architectures, as well as novel hybrid structures based on the Kolmogorov’s superposition theorem and using the neo-fuzzy neurons as elementary processing units. The need for the solution of the forecasting problem in real time poses higher requirements to the processing speed, so the considered hybrid structures can be trained with the proposed algorithms having high convergence rate and providing a compromise between the smoothing and tracking properties during the processing of nonstationary noisy signals.