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

Probabilistic inference-based classification applied to myoelectric signal decomposition.

D W Stashuk1, R K Naphan

  • 1Department of Systems Design Engineering, University of Waterloo, Ont., Canada.

IEEE Transactions on Bio-Medical Engineering
|April 1, 1992
PubMed
Summary

A novel inference-based classification (IBC) technique for motor unit action potentials (MUAPs) outperforms template matching algorithms. IBC shows superior performance, especially with noisy or limited training data, for myoelectric signal analysis.

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

Long-Term Endurance and Power Training May Facilitate Motor Unit Size Expansion to Compensate for Declining Motor Unit Numbers in Older Age.

Frontiers in physiology·2019
Same author

Failure to expand the motor unit size to compensate for declining motor unit numbers distinguishes sarcopenic from non-sarcopenic older men.

The Journal of physiology·2018
Same author

The reliability of methods to estimate the number and size of human motor units and their use with large limb muscles.

European journal of applied physiology·2018
Same author

Decomposition of intramuscular EMG signals using a knowledge -based certainty classifier algorithm.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013
Same author

Simulation of electromyographic signals.

Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology·2010
Same author

Decision support for QEMG.

Supplements to Clinical neurophysiology·2010

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Accurate classification of motor unit action potentials (MUAPs) is crucial for analyzing myoelectric signals.
  • Classical template matching algorithms (TBC) have limitations in handling complex or noisy biological data.

Purpose of the Study:

  • To introduce and evaluate a new probabilistic inference-based classification (IBC) technique for MUAPs.
  • To compare the performance of IBC against traditional TBC methods using simulated myoelectric signals.

Main Methods:

  • Developed a probabilistic inference-based classification (IBC) technique to identify statistically significant relationships for rule generation.
  • Applied IBC and TBC algorithms to classify MUAPs extracted from simulated myoelectric signals using 32 time samples as features.

Related Experiment Videos

Main Results:

  • IBC achieved significantly higher peak correct classification performance (83.0 +/- 2.6%) compared to TBC algorithms (78.1 +/- 2.8%, p < 0.005).
  • Both IBC and TBC performance decreased similarly with reduced training set size or increased classification errors.
  • IBC maintained superior performance even with small training sets (<30 MUAPs/unit) or high error rates (>50%).

Conclusions:

  • The IBC technique offers a robust and superior alternative to TBC for MUAP classification.
  • IBC's ability to utilize nominal data suggests potential for incorporating domain knowledge to further enhance performance.
  • This probabilistic approach shows promise for improved analysis of myoelectric signals in clinical and research settings.