A package for decomposing multi-channel intramuscular and surface EMG signals into individual motor unit activity based off the blind source algorithm described in Negro et al. (2016).
To generate the proposal and final report locally, ensure that you have R version 4.1.2 or above installed, as well as the RStudio IDE. Then install the necessary dependencies with the following commands:
Rscript -e 'install.packages("rmarkdown")'
Rscript -e 'install.packages("tinytex")'
Rscript -e 'tinytex::install_tinytex()'
Rscript -e 'install.packages("bookdown")'
Our project proposal can be found here.
To generate the proposal locally, run the following command from the root directory after cloning EMGdecomPy:
Rscript -e "rmarkdown::render('docs/proposal/proposal.Rmd')"
Alternatively, if the above doesn't work, install Docker. While Docker is running, run the following command from the root directory after cloning EMGdecomPy:
docker run --platform linux/amd64 --rm -v /$(pwd):/home/emgdecompy danfke/pandoc-r-bookdown Rscript -e "rmarkdown::render('home/emgdecompy/docs/proposal/proposal.Rmd')"
Our final report can be found here.
To generate the final report locally, run the following command from the root directory after cloning EMGdecomPy:
Rscript -e "rmarkdown::render('docs/final-report/final-report.Rmd')"
Alternatively, if the above doesn't work, install Docker. While Docker is running, run the following command from the root directory after cloning EMGdecomPy:
docker run --platform linux/amd64 --rm -v /$(pwd):/home/emgdecompy danfke/pandoc-r-bookdown Rscript -e "rmarkdown::render('home/emgdecompy/docs/final-report/final-report.Rmd')"
EMGdecomPy is compatible with Python versions 3.9 to 3.11.
pip install emgdecompyAfter installing emgdecompy, refer to the EMGdecomPy workflow notebook for an example on how to use the package, from loading in the data to visualizing the decomposition results.
Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.
EMGdecomPy was created by Daniel King, Jasmine Ortega, Rada Rudyak, and Rowan Sivanandam. It is licensed under the terms of the GPLv3 license.
EMGdecomPy was created with cookiecutter and the py-pkgs-cookiecutter template.
The blind source separation algorithm in this package was based off of Negro et al. (2016).
The data used for validation was obtained from Hug et al. (2021).
Guilherme Ricioli was consulted for his work on semg-decomposition.