An Adaptive Dynamic Mixing Model for sEMG Real-Time ICA on an Ultra-Low Power Processor

Introduction

Code to reproduce our paper "An Adaptive Dynamic Mixing Model for sEMG Real-Time ICA on an Ultra-Low Power Processor" [1].

Environment setup

The code is compatible with Python 3.7+. To create and activate the Python environment, run the following commands:

python -m venv <ENV_NAME>
source <ENV_NAME>/bin/activate

Then, from within the virtual environment, the required packages can be installed with the following command:

pip install -r requirements.txt

Usage

Run the Jupyter notebook Adaptive Decomposition of sEMG signals.ipynb to perform both the offline calibration and the online adaptation.

Authors

This work was realized mainly at the Energy-Efficient Embedded Systems Laboratory (EEES Lab) of University of Bologna (Italy), by:

• Mattia Orlandi
• Pierangelo Maria Rapa
• Marcello Zanghieri
• Sebastian Frey
• Victor Kartsch
• Luca Benini
• Simone Benatti

Citation

If you would like to reference the project, please cite the following paper:

@INPROCEEDINGS{10388538,
  author={Orlandi, Mattia and Rapa, Pierangelo Maria and Zanghieri, Marcello and Frey, Sebastian and Kartsch, Victor and Benini, Luca and Benatti, Simone},
  booktitle={2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)}, 
  title={An Adaptive Dynamic Mixing Model for sEMG Real-Time ICA on an Ultra-Low Power Processor}, 
  year={2023},
  volume={},
  number={},
  pages={1-5},
  keywords={Human computer interaction;Heuristic algorithms;Human-machine systems;Real-time systems;Blind source separation;Low-power electronics;Usability;Surface EMG;Wearable EMG;BSS;Ultra-Low-Power;Embedded;MCU;PULP},
  doi={10.1109/BioCAS58349.2023.10388538}
}

References

[1] M. Orlandi et al., "An Adaptive Dynamic Mixing Model for sEMG Real-Time ICA on an Ultra-Low Power Processor," 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), Toronto, ON, Canada, 2023, pp. 1-5, doi: 10.1109/BioCAS58349.2023.10388538.

License

All files are released under the Apache-2.0 license (see LICENSE).