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

ScaleNet--multiscale neural-network architecture for time series prediction.

A B Geva1

  • 1Electrical and Computer Engineering Department, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel.

IEEE Transactions on Neural Networks
|February 8, 2008
PubMed
Summary

A novel multiscale neural-network (NN) architecture effectively predicts nonlinear dynamic systems by analyzing time series data at various frequencies. This approach enhances prediction accuracy compared to single-scale methods.

Related Concept Videos

Introduction to Scalers01:21

Introduction to Scalers

Many familiar physical quantities can be specified completely by giving a single number and the appropriate unit. For example, "a class period lasts 50 min," or "the gas tank in my car holds 65 L," or "the distance between the two posts is 100 m." A physical quantity that can be specified completely in this manner is called a scalar quantity. The word "scalar" is a synonym for "number." Time, mass, distance, length, volume, temperature, and energy are some examples of scalar quantities.
Scalar...

You might also read

Related Articles

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

Sort by
Same author

A novel electroencephalography-based tool for objective assessment of network dynamics activated by nociceptive stimuli.

European journal of pain (London, England)·2015
Same author

Network dynamics predict improvement in working memory performance following donepezil administration in healthy young adults.

NeuroImage·2013
Same author

Introducing a novel approach of network oriented analysis of ERPs, demonstrated on adult attention deficit hyperactivity disorder.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2012
Same author

Nonstationary time series analysis by temporal clustering.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Detection of K-complexes in sleep EEG using CD-HMM.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same author

Forecasting epilepsy from the heart rate signal.

Medical & biological engineering & computing·2005

Area of Science:

  • Computational Science
  • Applied Mathematics
  • Artificial Intelligence

Background:

  • Nonlinear dynamic systems present significant challenges for accurate time series prediction.
  • Traditional methods often struggle to capture complex temporal patterns and trends effectively.

Purpose of the Study:

  • To investigate the effectiveness of a multiscale neural-network (NN) architecture for time series prediction.
  • To improve prediction accuracy for nonlinear dynamic systems by leveraging multiscale analysis.

Main Methods:

  • Decomposition of time series data into different scales using wavelets.
  • Prediction of wavelet coefficients at each scale using separate multilayer perceptron NNs.
  • Integration of predictions from all scales using an expert NN.

Related Experiment Videos

  • Training networks with backpropagation and Levenberg-Marquardt, initialized using a novel clustering algorithm.

    • Main Results:

    • The multiscale NN architecture demonstrated superior prediction accuracy compared to single-scale architectures.
    • The method effectively analyzes both short-term details (high frequencies) and long-term trends (low frequencies).
    • Clustering-based initialization improved prediction results over random initialization.

    Conclusions:

    • The proposed multiscale NN architecture is highly effective for time series prediction of nonlinear dynamic systems.
    • Coordinated analysis across multiple time and frequency scales provides richer information for prediction.
    • Further improvements in prediction accuracy are possible with enhanced learning methods.