Skip to main content

This is the Python implementation of Artifact-reference multivariate backward regression (ARMBR): a novel method for EEG blink artifact removal with minimal data requirements (for full algorithm, see citation below).

ARMBR is a lightweight and easy-to-use method for blink artifact removal from EEG signals using multivariate backward regression. The algorithm detects the times at which eye blinks occur and then estimates their linear scalp projection by regressing a simplified, time-locked reference signal against the multichannel EEG. This projection is used to suppress blink-related components while preserving underlying brain signals. ARMBR requires minimal training data, does not depend on dedicated EOG channels, and operates robustly in both offline and real-time (online) settings, including BCI applications.

This release contains some improvements to the BCI2000 GUI. It allows the user to create batch files to fit and apply ARMBR in BCI2000.

The code is maintained at: https://github.com/S-Shah-Lab/ARMBR

The semi-synthetic data used in the ARMBR paper, along with example codes that allow testing ARMBR of the semi-synthetic data used in the paper, are available on OSF at: https://osf.io/th2g6/

If you use ARMBR in your work, please cite:

Citation:

Alkhoury L, Scanavini G, Louviot S, Radanovic A, Shah SA & Hill NJ (2025). Artifact-Reference Multivariate Backward Regression (ARMBR): A Novel Method for EEG Blink Artifact Removal with Minimal Data Requirements. Journal of Neural Engineering, 22(3). DOI: 10.1088/1741-2552/ade566 PubMed: 40527334

BibTeX:

@article{alkhoury2025armbr,
	author  = {Alkhoury, Ludvik and Scanavini, Giacomo and Louviot, Samuel and Radanovic, Ana and Shah, Sudhin A and Hill, N Jeremy},
	title   = {Artifact-Reference Multivariate Backward Regression ({ARMBR}): A Novel Method for {EEG} Blink Artifact Removal with Minimal Data Requirements},
	journal = {Journal of Neural Engineering},
	volume  = {22},
	number  = {3},
	pages   = {036048},
	year    = {2025},
	date    = {2025-06-25},
	doi     = {10.1088/1741-2552/ade566},
	url     = {https://doi.org/10.1088/1741-2552/ade566},
}			

Metadata

Release files for ARMBR 2.0.12

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ARMBR 2.0.12
File Size Uploaded Provenance Actions
armbr-2.0.12.tar.gz 38.7 kB Without provenance Details for armbr-2.0.12.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ARMBR 2.0.12
File Interpreter ABI Platform Actions
armbr-2.0.12-py3-none-any.whl Python 3 none any Details for armbr-2.0.12-py3-none-any.whl

Total release size: 73.9 kB

Release files / armbr-2.0.12.tar.gz

Download URL armbr-2.0.12.tar.gz
Size 38.7 kB
Tags Source
SHA-256 checksum
How to use checksums
377a6c8bbed6ef9965972a8dbc005e6b7c3182cf24dc1bd8b8f4211410c2fd23
BLAKE2b-256 checksum
How to use checksums
987cf4f664edf72c8025c14cf97d759c7c8a5629e3ee7bb94bac2214bff5f427
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.0

Release files / armbr-2.0.12-py3-none-any.whl

Download URL armbr-2.0.12-py3-none-any.whl
Size 35.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
03f0823586a976fa99116696761b2e3274c829ecbce57068c4786f3d721063b3
BLAKE2b-256 checksum
How to use checksums
0b576c895e1314d2aba08d9886e236da759de2f9031dd507074b163fa5d77036
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.0

Security for ARMBR 2.0.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page