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

A neural network approach to movement pattern analysis.

Jürgen Perl1

  • 1Institute of Computer Science, FB 17, University of Mainz, Postfach, D-55099 Mainz, Germany. perl@informatik.uni-mainz.de

Human Movement Science
|December 14, 2004
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

The use of neural network technology to model swimming performance.

Journal of sports science & medicine·2013
Same author

Special issue: Network approaches in complex environments.

Human movement science·2012
Same author

Tactical pattern recognition in soccer games by means of special self-organizing maps.

Human movement science·2011
Same author

Analysis and simulation of creativity learning by means of artificial neural networks.

Human movement science·2008
Same author

Game creativity analysis using neural networks.

Journal of sports sciences·2008
Same author

Artificial neural networks in motor control research.

Clinical biomechanics (Bristol, Avon)·2004
Same journal

Dissociating variability from error-based processes in observational learning.

Human movement science·2026
Same journal

Associations between movement behaviors, sleep, and screen time exposure in middle childhood using multivariable modelling.

Human movement science·2026
Same journal

The interaction of biomechanical demands and the speed-accuracy trade-off for the control of multi-directional, three-dimensional targeted reaching movements.

Human movement science·2026
Same journal

Think positive, perform better: The detrimental effect of technical motor imagery before action.

Human movement science·2026
Same journal

Shoulder-elbow coordination in the transverse plane during badminton forehand drive depending on training status using vector coding analysis.

Human movement science·2026
Same journal

Delayed reaction time and altered spatial activation of Fibularis longus in chronic ankle instability: A high-density surface electromyography study.

Human movement science·2026
See all related articles

Neural networks, like the Kohonen Feature Map (KFM) and Dynamically Controlled Network (DyCoN), analyze complex movement patterns by reducing high-dimensional data into 2D trajectories for easier analysis in sports science.

Area of Science:

  • Biomechanics
  • Computational Neuroscience
  • Sports Science

Background:

  • Human movements are complex, time-dependent processes represented by high-dimensional coordinate data.
  • Analyzing these movements traditionally requires extensive data and complex modeling.

Purpose of the Study:

  • To explore the application of neural networks for analyzing movement patterns.
  • To demonstrate dimensionality reduction from high-dimensional configurations to 2D trajectories.

Main Methods:

  • Utilizing the Kohonen Feature Map (KFM), a type of neural network, to cluster movement patterns.
  • Employing the Dynamically Controlled Network (DyCoN), a modified KFM, to reduce training data requirements.
  • Modeling movements as time-series of coordinates, creating high-dimensional configurations.

Related Experiment Videos

Main Results:

  • KFM successfully identifies patterns and clusters them, reducing dimensionality to 2D trajectories.
  • DyCoN significantly reduces the need for extensive experimental training data.
  • The method allows for automatic data transfer for further analysis and visualization.

Conclusions:

  • Neural network-based analysis offers an effective method for movement pattern recognition and dimensionality reduction.
  • DyCoN enhances the practicality of KFM for movement analysis by reducing data dependency.
  • This approach supports, rather than replaces, expert analysis and model development in sports science.