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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Prediction of Performance in Standardised Assessments from Computer-Based Formative Assessment Data.

Technology, knowledge and learning·2026
Same author

Dynamics of postnatal upper airway bacteria colonization in preterm infants <1000g and bronchopulmonary dysplasia.

Scientific reports·2025
Same author

Updating descriptive sensory evaluation of chicken: proposing new protocols and statistical analysis.

Poultry science·2025
Same author

Exploring the structure of the school curriculum with graph neural networks.

Journal of computational social science·2025
Same author

Multilab Direct Replication of Flavell, Beach, and Chinsky (1966): Spontaneous Verbal Rehearsal in a Memory Task as a Function of Age.

Advances in methods and practices in psychological science·2025
Same author

Functional Data Analysis: An Introduction and Recent Developments.

Biometrical journal. Biometrische Zeitschrift·2024

Related Experiment Video

Updated: Sep 22, 2025

Measuring the Kinematics of Daily Living Movements with Motion Capture Systems in Virtual Reality
08:45

Measuring the Kinematics of Daily Living Movements with Motion Capture Systems in Virtual Reality

Published on: April 5, 2018

7.7K

Supervised learning for analysing movement patterns in a virtual reality experiment.

Frederike Vogel1, Nils M Vahle2, Jan Gertheiss1

  • 1Department of Mathematics and Statistics, School of Economics and Social Sciences, Helmut Schmidt University, Hamburg, Germany.

Royal Society Open Science
|May 23, 2022
PubMed
Summary
This summary is machine-generated.

Embodying a virtual older avatar reduced young students' physical activity and agility in upper body exercises. Machine learning effectively distinguished movement patterns between young and old avatars.

Keywords:
ageingdata augmentationdeep learningembodimentresampling

More Related Videos

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

720
Controlled Rotation of Human Observers in a Virtual Reality Environment
09:11

Controlled Rotation of Human Observers in a Virtual Reality Environment

Published on: April 21, 2022

2.7K

Related Experiment Videos

Last Updated: Sep 22, 2025

Measuring the Kinematics of Daily Living Movements with Motion Capture Systems in Virtual Reality
08:45

Measuring the Kinematics of Daily Living Movements with Motion Capture Systems in Virtual Reality

Published on: April 5, 2018

7.7K
Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

720
Controlled Rotation of Human Observers in a Virtual Reality Environment
09:11

Controlled Rotation of Human Observers in a Virtual Reality Environment

Published on: April 21, 2022

2.7K

Area of Science:

  • Virtual Reality (VR) and Human-Computer Interaction
  • Kinesiology and Biomechanics
  • Machine Learning and Pattern Recognition

Background:

  • Embodying virtual avatars can alter user behavior and attitudes, influenced by avatar characteristics and stereotypes.
  • The experience of embodiment, including illusory body ownership, can lead to transformations in self-perception and subsequent actions.

Purpose of the Study:

  • To investigate the impact of embodying an older avatar on the physical activity and movement patterns of young students.
  • To explore the utility of supervised learning algorithms for differentiating behavioral changes associated with avatar embodiment.

Main Methods:

  • Participants were randomly assigned to embody either a young or an older virtual avatar.
  • Upper body movements were tracked during exercises, and supervised learning (Support Vector Machines, Convolutional Neural Networks) was used to classify movement patterns.
  • Time sub-sequences were randomly extracted and repeatedly inserted for robust classification of avatar-induced behavioral differences.

Main Results:

  • Machine learning models, particularly Support Vector Machines with a linear kernel and Convolutional Neural Networks, achieved high classification accuracy in distinguishing movement patterns.
  • The young avatar group exhibited movements characterized by higher local, vertical positions, indicating greater agility compared to the older avatar group.
  • These agility differences were observed in both guided and achievement-oriented exercises, highlighting consistent behavioral changes.

Conclusions:

  • Embodying an older avatar significantly impacts young students' physical activity, leading to reduced agility and altered movement patterns.
  • Supervised learning offers a powerful alternative to traditional methods for detecting subtle behavioral differences induced by avatar embodiment.
  • Findings underscore the profound influence of virtual embodiment on motor behavior and self-perception, with implications for VR applications.