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

Modelling and prediction for chaotic fir laser attractor using rational function neural network.

S Cho1

  • 1Intelligent Systems Laboratory, School of Engineering, Cardiff University, UK. ChoS@cf.ac.uk

International Journal of Neural Systems
|April 20, 2001
PubMed
Summary

This study introduces a novel rational function neural network for modeling chaotic Far InfraRed laser systems. The proposed method enhances predictability and reduces complexity compared to traditional neural networks.

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

Search for new phenomena with the <math></math> variable in the all-hadronic final state produced in proton-proton collisions at <math> </math> <math></math>.

The European physical journal. C, Particles and fields·2020
Same author

Measurement of the triple-differential dijet cross section in proton-proton collisions at <math> </math> and constraints on parton distribution functions.

The European physical journal. C, Particles and fields·2020
Same author

Measurements of the associated production of a Z boson and b jets in pp collisions at <math> </math>.

The European physical journal. C, Particles and fields·2020
Same author

Search for dark matter produced in association with heavy-flavor quark pairs in proton-proton collisions at <math> </math>.

The European physical journal. C, Particles and fields·2020
Same author

Extraction and validation of a new set of CMS pythia8 tunes from underlying-event measurements.

The European physical journal. C, Particles and fields·2020
Same author

Searches for physics beyond the standard model with the <math></math> variable in hadronic final states with and without disappearing tracks in proton-proton collisions at <math> </math>.

The European physical journal. C, Particles and fields·2020

Area of Science:

  • Nonlinear Dynamics
  • Chaos Theory
  • Laser Physics

Background:

  • Real-world systems like ECG signals and currency exchange rates exhibit chaotic behavior.
  • Linear system theory is insufficient for modeling high-dimensional, irregular chaotic systems.
  • Predicting and modeling chaotic systems, especially those with unknown underlying equations, remains a challenge.

Purpose of the Study:

  • To propose a novel method for prediction and modeling of a chaotic Far InfraRed (FIR) laser system.
  • To introduce and compare three neural network architectures: Time Delayed Neural Network (TDNN), Radial Basis Function (RBF) network, and Rational Function (RF) network.
  • To demonstrate the superiority of the RF network in modeling chaotic time series.

Main Methods:

  • Development of a prediction and modeling method using a rational function neural network.

Related Experiment Videos

  • Implementation and comparison of TDNN, RBF, and RF network architectures.
  • Evaluation of network performance based on predictability and complexity.

    • Main Results:

    • The Rational Function (RF) network demonstrated superior performance in predicting chaotic FIR laser time series.
    • The RF network achieved better predictability compared to TDNN and RBF networks.
    • The proposed RF network architecture resulted in reduced network complexity.

    Conclusions:

    • The rational function neural network is an effective tool for modeling and predicting chaotic systems, particularly FIR laser systems with unknown dynamics.
    • The RF network offers significant advantages over traditional neural network architectures like TDNN and RBF in terms of predictability and efficiency.
    • This research provides a valuable approach for understanding and controlling complex chaotic phenomena in scientific and engineering applications.