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 comparative analysis of various EMG pattern recognition methods

W J Kang1, C K Cheng, J S Lai

  • 1Department of Electrical Engineering, National Taiwan University, ROC.

Medical Engineering & Physics
|July 1, 1996
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

Progress and Advances in Porous Silica-based Scaffolds for Enhanced Solid-state Hydrogen Storage: A Systematic Literature Review.

Chemistry, an Asian journal·2023
Same author

[Veracity of using a visual chart with a testing distance of 2.5 meters for measurement of distance visual acuity in teenagers].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2021
Same author

Deoxycytidine kinase expression in AML blasts and its relationship to leukemia-free and overall survival: <b>PS101</b>.

Porto biomedical journal·2020
Same author

[Impact of complicated myocardial injury on the clinical outcome of severe or critically ill COVID-19 patients].

Zhonghua xin xue guan bing za zhi·2020
Same author

Correction to Metallic Nanoislands on Graphene for Monitoring Swallowing Activity in Head and Neck Cancer Patients.

ACS nano·2018
Same author

High-quality thulium iron garnet films with tunable perpendicular magnetic anisotropy by off-axis sputtering - correlation between magnetic properties and film strain.

Scientific reports·2018

This study identifies neck and shoulder motions using electromyographic (EMG) signals. The modified maximum likelihood method with cepstral coefficients and separately located electrodes achieved over 97% recognition accuracy.

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Technology
  • Signal Processing

Background:

  • Electromyographic (EMG) signals are crucial for understanding neuromuscular activity.
  • Accurate identification of neck and shoulder motions is vital for clinical diagnostics and assistive technologies.
  • Developing robust methods for EMG-based motion recognition remains a significant challenge.

Purpose of the Study:

  • To investigate the effectiveness of different discrimination methods and feature extraction techniques for identifying neck and shoulder motions from EMG signals.
  • To compare the performance of autoregressive (AR) and cepstral coefficients with closely (C-type) and separately (S-type) located electrode arrangements.
  • To determine the optimal combination of feature sets, classifiers, and electrode configurations for maximizing motion recognition accuracy.

Related Experiment Videos

Main Methods:

  • EMG signals were recorded from sternocleidomastoid and upper trapezius muscles during 10 distinct neck and shoulder motions.
  • Three discrimination methods were employed: Euclidean distance measure (EDM), weighted distance measure (WDM), and modified maximum likelihood method (MMLM).
  • Conventional AR and cepstral coefficients were extracted and compared using both C-type and S-type electrode placements.

Main Results:

  • Cepstral coefficients demonstrated at least a 5% higher recognition rate than AR coefficients for S-type signals.
  • The MMLM classifier yielded the best discrimination performance among the tested methods.
  • S-type electrode arrangements generally resulted in higher recognition rates compared to C-type arrangements.
  • The optimal combination of cepstral coefficients, MMLM, and S-type arrangement achieved superior discrimination efficiency.
  • Selecting a subset of five motions improved the overall recognition rate to over 97%.

Conclusions:

  • The study highlights the superiority of cepstral coefficients and the MMLM classifier for EMG-based neck and shoulder motion identification.
  • S-type electrode arrangements offer better performance than C-type arrangements, suggesting spatial separation is beneficial.
  • Optimizing feature sets, classifiers, and electrode configurations is key to achieving high-accuracy EMG-based motion recognition.
  • The findings have implications for developing advanced prosthetic control and rehabilitation systems.