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

Employing 3D virtual reality games to develop ANN for device control: a pilot study.

P E Patterson1

  • 1College of Engineering, Iowa State University, Ames, IA 50011, USA.

Biomedical Sciences Instrumentation
|May 12, 2001
PubMed
Summary

Virtual reality games help collect EMG data for biceps and triceps. Optimized artificial neural network (ANN) algorithms show promise for training prosthetic limb control.

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

Biomechanical waveform analysis in the frequency domain.

IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society·2009
Same author

A systematic approach for introducing innovative product design in courses with engineering and nonengineering students.

Biomedical sciences instrumentation·2007
Same author

Supporting undergraduate biomedical entrepreneurship.

Biomedical sciences instrumentation·2004
Same author

Development of a learning module using a virtual environment to demonstrate EMG and telerobotic control principles.

Biomedical sciences instrumentation·2002
Same author

The use of self organizing maps to evaluate myoelectric signals.

Biomedical sciences instrumentation·2001
Same author

Gender differences in navigating virtual worlds.

Biomedical sciences instrumentation·2001

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Rehabilitation Technology

Background:

  • Electromyography (EMG) signal analysis is crucial for myoelectric control.
  • Current training methods for prosthetic devices can be challenging for users.
  • Virtual reality (VR) offers immersive environments for skill acquisition.

Purpose of the Study:

  • To develop non-immersive VR game scenarios for collecting EMG data.
  • To optimize artificial neural network (ANN) configurations for classifying muscle contractions.
  • To evaluate VR as a training tool for prosthetic limb control.

Main Methods:

  • Designed VR game scenarios for sequenced upper limb tasks.
  • Collected EMG data from biceps and triceps during gameplay.
  • Determined optimal ANN configurations (layers, transfer functions) per subject.
  • Utilized optimized ANNs to classify contraction sequences and function types.

Main Results:

  • Individualized ANN configurations were necessary for accurate classification.
  • A wide variability in optimal ANN configurations was observed among subjects.
  • VR gameplay provided a viable method for acquiring EMG data.

Conclusions:

  • A single, universal algorithm is insufficient for training diverse myoelectric device users.
  • VR-based games demonstrate significant potential as an effective training modality.
  • This approach could enhance the development of control for prosthetic limbs.

Related Experiment Videos