Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning chaotic attractors by neural networks.

R Bakker1, J C Schouten, C L Giles

  • 1DelftChemTech, Delft University of Technology, The Netherlands.

Neural Computation
|October 14, 2000
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Bringing Anatomical Information into Neuronal Network Models.

Advances in experimental medicine and biology·2022
Same author

HPV-negative squamous cell carcinoma of the anal canal is unresponsive to standard treatment and frequently carries disruptive mutations in TP53.

British journal of cancer·2015
Same author

Carbon-coated ceramic membrane reactor for the production of hydrogen by aqueous-phase reforming of sorbitol.

ChemSusChem·2014
Same author

Bridging between professionals in perinatal care: towards shared care in the Netherlands.

Maternal and child health journal·2012
Same author

Dose-response relationship between alcohol consumption before and during pregnancy and the risks of low birthweight, preterm birth and small for gestational age (SGA)-a systematic review and meta-analyses.

BJOG : an international journal of obstetrics and gynaecology·2011
Same author

Poster presentations at medical conferences: an effective way of disseminating research?

Clinical medicine (London, England)·2011

This study introduces a novel algorithm for identifying chaotic dynamics in time series data using neural networks. The method combines short-term prediction with a statistical test to ensure accurate modeling of chaotic systems.

Area of Science:

  • Nonlinear dynamics
  • Time series analysis
  • Machine learning

Background:

  • Identifying chaotic dynamics from time series is crucial for understanding complex systems.
  • Existing methods often struggle with accurate attractor reconstruction and prediction.

Purpose of the Study:

  • To develop and validate a new algorithm for identifying chaotic dynamics from single time series.
  • To improve the accuracy of attractor reconstruction and short-term prediction in chaotic systems.

Main Methods:

  • A neural network is trained to short-term predict time series data.
  • A statistical test (Diks et al., 1996) is used to compare reconstructed attractors.
  • Weighted principal component analysis reduces state space dimension.
  • An adjustable prediction horizon is achieved via error propagation.

Related Experiment Videos

Main Results:

  • The algorithm successfully identified chaotic dynamics in experimental pendulum data, distinguishing subtle attractor differences.
  • Performance was validated even when using incomplete state variable information.
  • A model for Santa Fe laser competition data (Set A) was developed, showing accurate prediction and chaotic characteristic replication.

Conclusions:

  • The developed algorithm effectively identifies chaotic dynamics and reconstructs attractors.
  • It offers improved short-term prediction and robust performance with limited data.
  • This approach provides a valuable tool for analyzing complex, chaotic systems.