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 Video

Updated: Jun 10, 2026

Data Acquisition and Analysis In Brainstem Evoked Response Audiometry In Mice
08:51

Data Acquisition and Analysis In Brainstem Evoked Response Audiometry In Mice

Published on: May 10, 2019

An adaptive wavelet neural network for spatio-temporal system identification.

H L Wei1, S A Billings, Y F Zhao

  • 1Department of Automatic Control and Systems Engineering, The University of Sheffield, Mappin Street, Sheffield, UK. w.hualiang@sheffield.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|August 17, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

State Space Representation01:27

State Space Representation

The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...

You might also read

Related Articles

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

Sort by
Same author

[Risk factor analysis and prediction model construction for severe <i>Chlamydia pneumoniae</i> pneumonia in children].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2026
Same author

[A case report of end-stage dilated cardiomyopathy caused by neutral lipid storage disease].

Zhonghua xin xue guan bing za zhi·2026
Same author

[Efficacy analysis of hemivertebra bone-disc-bone osteotomy for congenital scoliosis in children younger than 5 years old].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2026
Same author

[The trend of change in insulin resistance among Chinese adults from 2010 to 2018].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Allogeneic hematopoietic stem cell transplantation in a patient with MonoMAC syndrome and hematopoietic dysplasia which was induced by GATA2 deficiency: a case report and literature review].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2024
Same author

[Clinical characteristics and prognostic factors of breast cancer patients with tumor deposits in the ipsilateral axillary region].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2024
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A new adaptive wavelet neural network (AWNN) framework enhances spatio-temporal system identification. This method uses orthogonal projection pursuit and particle swarm optimization for efficient, parsimonious model construction.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Dynamical Systems

Background:

  • Coupled map lattices (CML) provide a foundation for modeling complex spat-temporal dynamics.
  • Adaptive wavelet neural networks (AWNN) offer a powerful tool for system identification.
  • Efficiently constructing parsimonious models for spat-temporal systems remains a challenge.

Purpose of the Study:

  • Introduce a novel family of adaptive wavelet neural networks (AWNN) for spat-temporal system identification.
  • Develop a new two-stage hybrid training scheme for constructing parsimonious AWNN models.
  • Enhance network augmentation using orthogonal projection pursuit (OPP) and particle swarm optimization (PSO).

Main Methods:

  • Combined wavelet representation with a coupled map lattice model.

Related Experiment Videos

Last Updated: Jun 10, 2026

Data Acquisition and Analysis In Brainstem Evoked Response Audiometry In Mice
08:51

Data Acquisition and Analysis In Brainstem Evoked Response Audiometry In Mice

Published on: May 10, 2019

  • Employed a two-stage hybrid training: OPP with PSO for initial training and orthogonal least squares (OLS) for refinement.
  • Adaptive and successive recruitment of significant wavelet neurons.
  • Optimization of wavelet neuron parameters using PSO.

    • Main Results:

    • Successfully developed a parsimonious network model for spat-temporal systems.
    • The two-stage training procedure effectively removes redundant neurons, producing a ranked list of significant wavelet neurons.
    • Demonstrated the framework's performance through two spat-temporal system identification examples.

    Conclusions:

    • The proposed AWNN framework with OPP and PSO provides an effective approach for spat-temporal system identification.
    • The novel two-stage training scheme ensures parsimonious model construction.
    • The method yields a ranked list of neurons, aiding in understanding model structure and importance.