EMG2MCU

EMG2MCU provides surface-EMG preprocessing, event segmentation, feature extraction, model selection, and deployable C++/Arduino model generation.

Run the example

Install the project and its dependencies in the active Python environment:

python -m pip install -e .

Open EMG2MCU_example.ipynb from the repository root. It generates a deterministic synthetic recording at runtime, so no real participant data is needed or included in the repository. The synthetic signals demonstrate the software pipeline only and are not physiological data. Generated artifacts are written to the ignored output_emg2mcu/ directory.

The main entry point is EMG2MCU.automl. Configuration dataclasses and lower-level processing, plotting, feature, and model utilities are also available from their corresponding package modules.

Documentation

The full API reference, configuration dataclasses, and pipeline examples are published on Read the Docs:

• Stable: https://emg2mcu.readthedocs.io/en/stable/
• Latest: https://emg2mcu.readthedocs.io/en/latest/
• Source for the documentation lives in ./docs; see ./docs/README.md for how to build it locally.

Development

Tests run on every pull request across Python 3.10, 3.11, and 3.12 via .github/workflows/tests.yml. Merging to main triggers the release workflow, which auto-bumps the patch version, publishes to PyPI, builds the Sphinx docs, and opens a GitHub Release whose body is taken from the merged PR's ## Changelog section.