Announcement

Collapse
No announcement yet.

Public Database for EMG Onset Detection Algorithm Development

Collapse
X
Collapse
 
  • Page of 1
  • Filter
  • Time
  • Show
Clear All
new posts
Previous template Next
  • #1

    Public Database for EMG Onset Detection Algorithm Development

    Dear Colleagues,
    I wanted to make everyone aware that we have made our raw surface and fine wire EMG data, as well as the determined visual onset times, publicly available from our recent publications in PLOS ONE (surface EMG) and Journal of Applied Biomechanics (fine wire EMG).

    The manuscripts are available here so you can review the methods:
    Analysis of statistical and standard algorithms for detecting muscle onset with surface electromyography
    http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0177312
    The timing of muscle activity is a commonly applied analytic method to understand how the nervous system controls movement. This study systematically evaluates six classes of standard and statistical algorithms to determine muscle onset in both experimental surface electromyography (EMG) and simulated EMG with a known onset time. Eighteen participants had EMG collected from the biceps brachii and vastus lateralis while performing a biceps curl or knee extension, respectively. Three established methods and three statistical methods for EMG onset were evaluated. Linear envelope, Teager-Kaiser energy operator + linear envelope and sample entropy were the established methods evaluated while general time series mean/variance, sequential and batch processing of parametric and nonparametric tools, and Bayesian changepoint analysis were the statistical techniques used. Visual EMG onset (experimental data) and objective EMG onset (simulated data) were compared with algorithmic EMG onset via root mean square error and linear regression models for stepwise elimination of inferior algorithms. The top algorithms for both data types were analyzed for their mean agreement with the gold standard onset and evaluation of 95% confidence intervals. The top algorithms were all Bayesian changepoint analysis iterations where the parameter of the prior (p0) was zero. The best performing Bayesian algorithms were p0 = 0 and a posterior probability for onset determination at 60–90%. While existing algorithms performed reasonably, the Bayesian changepoint analysis methodology provides greater reliability and accuracy when determining the singular onset of EMG activity in a time series. Further research is needed to determine if this class of algorithms perform equally well when the time series has multiple bursts of muscle activity.

    Human Verification
    https://journals.humankinetics.com/doi/abs/10.1123/jab.2016-0313


    The PLOS ONE is Open Access and I can be contacted (easiest through ResearchGate) for the JAB manuscript.

    The general repository is located here and the raw data is compressed as .rds files and the visual onset times are .csv files:
    GitHub - TenanATC/EMG: This will be a repo to mine and assess EMG data
    https://github.com/TenanATC/EMG
    This will be a repo to mine and assess EMG data. Contribute to TenanATC/EMG development by creating an account on GitHub.


    For educational purposes, and those not familiar with the R programming language, I have created some demonstration R Markdown files to show how the data can easily be extracted (contained within the GitHub repo). This data is free for use, experimentation, and publication. All I ask is that appropriate citation for the data be utilized. Indeed, I see at least one other research group has already found this data helpful for their benchmarking of new algorithms:
    IEEE Xplore - Unable to Load Page
    https://ieeexplore.ieee.org/abstract/document/8355589/


    Please let me know if there are any questions/concerns.

    Best,
    Matt
    Tags: data, database, emg, emg data, emg onset
Previous template Next
Working...
X