OSCR

Oracle Upper Bounds on Clean-EEG Recoverability from Single-Channel Decompositions Under EOG/EMG Contamination.

Code ↔ Paper

6 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 6 matches · 4 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § 2. Methods › 2.1. The Benchmark Dataset and Noise Synthesis ↔ scripts/prepare_workspace_example.m, the whole file · a weak match · score 0.62 · EEGdenoiseNet, Clean EEG, EMG epochs, artifact, 256 Hz, benchmark
  2. [2] § 2. Methods › 2.3. Oracle Reconstruction and Performance Metrics ↔ src/compute_metrics.m, the whole file · a weak match · score 0.54 · Pearson correlation coefficient, Metrics, error, Reconstruction
  3. [3] § 2. Methods › 2.1. The Benchmark Dataset and Noise Synthesis ↔ scripts/prepare_workspace_example.m, the whole file · a weak match · score 0.53 · clean EEG epoch, EMG epoch, optionally, benchmark, EOG
  4. [4] § 2. Methods › 2.3. Oracle Reconstruction and Performance Metrics ↔ src/fit_oracle_weights.m, the whole file · a weak match · score 0.52 · box constraints, lsqlin, squares, component, oracle, Reconstruction
  5. [5] § 3. Results › 3.1. Within-Method Hyperparameter Behaviour and Selections › 3.1.2. SSA ↔ src/ssa_decompose.m, lines 1–38 · score 0.52 · SSA decomposition, window length, SVD, matrix, reconstruction
  6. [6] § 2. Methods › 2.2. Decomposition Methods and Hyperparameter Grids › 2.2.2. Singular Spectrum Analysis (SSA) ↔ src/ssa_decompose.m, lines 1–38 · score 0.51 · window length, SVD, rank, Singular, Spectrum, SSA

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

MATLAB · 27 lines · 1.1 KB · MIT · 2 matches

  1. %% prepare_workspace_example.m
  2. % Example template for preparing the workspace before building the benchmark.
  3. %
  4. % Replace the placeholder loading code below with your own data-loading
  5. % pipeline. The benchmark builder expects the following variables in the
  6. % MATLAB workspace:
  7. %
  8. % EEG_all_epochs : [N_eeg x T_src] clean EEG epochs
  9. % EOG_all_epochs : [N_eog x T_src] ocular artifact epochs
  10. % EMG_all_epochs : [N_emg x T_src] muscle artifact epochs
  11. % fs : source sampling rate in Hz (optional; default = 256)
  12. %
  13. % IMPORTANT:
  14. % This repository does not redistribute EEGdenoiseNet or any third-party
  15. % data. Please obtain the original data separately and adapt this script
  16. % to your local storage format.
  18. clearvars;
  19. clc;
  21. % -------------------------------------------------------------------------
  22. % Example placeholder:
  23. % load('your_epoch_pools.mat', 'EEG_all_epochs', 'EOG_all_epochs', 'EMG_all_epochs', 'fs');
  24. % -------------------------------------------------------------------------
  26. error(['Edit scripts/prepare_workspace_example.m to load your clean EEG, ' ...
  27. 'EOG, and EMG epoch matrices into the workspace before proceeding.']);

prepare_workspace_example.m at commit 9edfa5e, under MIT · at the source

Overview

Authors: Usman Qamar Shaikh1,2, Anubha Manju Kalra1,2, Andrew Lowe1,3, Imran Khan Niazi4,5
ORCID iDs: Usman Qamar Shaikh, Anubha Manju Kalra, Andrew Lowe, Imran Khan Niazi
  1. Institute of Biomedical Technologies, Auckland University of Technology, Auckland 1010, New Zealand; (A.M.K.); (A.L.)
  2. Department of Electrical and Electronic Engineering, School of Engineering Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand
  3. Department of Mechanical Engineering, School of Engineering Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand
  4. Centre for Chiropractic Research, New Zealand College of Chiropractic, Auckland 1060, New Zealand
  5. Department of Health Science and Technology, Aalborg University, 9200 Aalborg, Denmark
Institutions: Auckland University of Technology (New Zealand); New Zealand College of Chiropractic (New Zealand); Aalborg University (Denmark)
Journal: Sensors (Basel, Switzerland), volume 26, issue 9, article 2581
Dates: received 6 March 2026; accepted 3 April 2026; published online 22 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/s26092581 · PMID 42122304 · PMCID PMC13165893 · OpenAlex W7155214222
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: EEG (modality), other (modality), human (organism)
Methods: Connectivity, Statistics, Preprocessing, Smoothing, state filtering, decompositions, Physiology & signal measures
Keywords: electroencephalography (EEG), artifact suppression, ocular artifacts (EOG), muscle artifacts (EMG), signal decomposition, variational mode decomposition (VMD), CEEMDAN, singular spectrum analysis (SSA), wavelet transform (DWT)
MeSH: Electroencephalography*, Electromyography*, Electrooculography*, Algorithms, Artifacts, Humans, Signal Processing, Computer-Assisted, Signal-To-Noise Ratio, Wavelet Analysis (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: Auckland University of Technology, New Zealand
Citations: not cited yet (Europe PMC); 56 references in the paper

Abstract

Objective: Single-channel EEG artifact suppression often relies on signal decomposition; however, it is not always clear how much clean EEG is recoverable from a given decomposition when component weighting is ideal. We present an oracle-based benchmark that characterises this best-case recoverability across common 1-D decomposition families under controlled EOG, EMG, and mixed contamination. This work does not propose a new denoising algorithm; rather, it isolates representation capacity from component-selection heuristics by computing an upper bound on reconstruction quality. Approach: Using EEGdenoiseNet, we constructed a synthetic benchmark of 4500 single-channel 2 s segments (125 Hz; T = 250) by mixing clean EEG with ocular (EOG) and/or cranial EMG exemplars at noise-to-signal ratios (NSRs) spanning −10 to +10 dB (floor −10 dB denotes an absent modality). We evaluated variational mode decomposition (VMD), singular spectrum analysis (SSA), discrete wavelet transform (DWT), and CEEMDAN by decomposing each mixture and reconstructing the clean EEG using a bounded nonnegative linear combination of components obtained via constrained least squares (the oracle). Main results: Under this oracle benchmark, SSA achieved the lowest reconstruction error in most tested conditions, while DWT tended to rank best in milder ocular regimes; VMD performance improved, with an increased mode count at higher computational cost. CEEMDAN exhibited higher latency dominated by ensemble settings. Significance: These results should be interpreted as decomposition-level upper bounds under controlled mixtures, not field-ready denoising performance. The benchmark provides a tool with which to compare representational recoverability across decompositions and to inform the subsequent design of practical component-selection strategies.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 6 matches between paragraphs and lines of code.

usmanqamarshaikh/oracle-eeg-recoverability-benchmark

License: MIT
State: the link answers, verified on 29 September 2026
Evidence: files inventoried
Commit: 9edfa5e227f558a6a858f0b17da1870643e91ec0, 9 April 2026
Languages: MATLAB (10)
Size: 13 files, 10 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README, license file, CITATION.cff
Not found: environment file, tests, continuous integration, documentation
Tools: Optimization Toolbox (1 file), Wavelet Toolbox (1 file)
Availability: 1 check, the latest on 29 September 2026: the link answers
  • 29 September 2026: the link answers
12 files
At the source: github.com/usmanqamarshaikh/oracle-eeg-recoverability-benchmark

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 10 scripts, each with its path and the digest of its content;
  • 6 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The code supporting the findings of this study is publicly available at GitHub: https://github.com/usmanqamarshaikh/oracle-eeg-recoverability-benchmark (accessed on 26 December 2025).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 9 keywords, 9 MeSH terms, 1 funder, 51 references.

Cite

This paper

Shaikh, U. Q., Kalra, A. M., Lowe, A., & Niazi, I. K. (2026). Oracle Upper Bounds on Clean-EEG Recoverability from Single-Channel Decompositions Under EOG/EMG Contamination. Sensors (Basel, Switzerland), 26(9), 2581. https://doi.org/10.3390/s26092581

BibTeX

@article{shaikh2026oracle,
author = {Shaikh, Usman Qamar and Kalra, Anubha Manju and Lowe, Andrew and Niazi, Imran Khan},
title = {{Oracle Upper Bounds on Clean-EEG Recoverability from Single-Channel Decompositions Under EOG/EMG Contamination}},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = apr,
volume = {26},
number = {9},
pages = {2581},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {1424-8220},
doi = {10.3390/s26092581},
url = {https://doi.org/10.3390/s26092581},
pmid = {42122304},
pmcid = {PMC13165893}
}

RIS

TY - JOUR
AU - Shaikh, Usman Qamar
AU - Kalra, Anubha Manju
AU - Lowe, Andrew
AU - Niazi, Imran Khan
TI - Oracle Upper Bounds on Clean-EEG Recoverability from Single-Channel Decompositions Under EOG/EMG Contamination
T2 - Sensors (Basel, Switzerland)
J2 - Sensors (Basel)
PY - 2026
DA - 2026/04/22
VL - 26
IS - 9
SP - 2581
SN - 1424-8220
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/s26092581
UR - https://doi.org/10.3390/s26092581
LA - en
ER -

CSL-JSON

{
"id": "10.3390/s26092581",
"type": "article-journal",
"title": "Oracle Upper Bounds on Clean-EEG Recoverability from Single-Channel Decompositions Under EOG/EMG Contamination",
"container-title": "Sensors (Basel, Switzerland)",
"author": [
{
"family": "Shaikh",
"given": "Usman Qamar"
},
{
"family": "Kalra",
"given": "Anubha Manju"
},
{
"family": "Lowe",
"given": "Andrew"
},
{
"family": "Niazi",
"given": "Imran Khan"
}
],
"container-title-short": "Sensors (Basel)",
"volume": "26",
"issue": "9",
"page": "2581",
"DOI": "10.3390/s26092581",
"PMID": "42122304",
"PMCID": "PMC13165893",
"ISSN": "1424-8220",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/s26092581",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
22
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/s26134019 [code]
NeuroStat: An Open-Source EEG Connectivity Platform for Randomised Controlled Trials.
Journal: Sensors (Basel, Switzerland)
In common: EEG, author Imran Khan Niazi
[2] doi:10.1038/s41467-026-71458-0 [code]
Early differential impact of MeCP2 mutations on functional networks in Rett syndrome patient-derived human cortical organoids.
Journal: Nature communications
In common: Wavelet Toolbox, Optimization Toolbox
[3] doi:10.1371/journal.pcbi.1014038 [code]
Fast and accessible morphology-free functional fluorescence imaging analysis.
Journal: PLoS computational biology
In common: Wavelet Toolbox, Optimization Toolbox
[4] doi:10.1038/s41598-026-56416-6
EEG blink and gaze control using random forest classification for accessible assistive robotic navigation in real world conditions.
Journal: Scientific reports
In common: EEG, 2 references
[5] doi:10.3390/s26134045
Brain Signal for Secure EEG Biometric Authentication: A Comprehensive Survey.
Journal: Sensors (Basel, Switzerland)
In common: EEG, 2 references
[6] doi:10.3390/s26103274 [code]
An EEG-Based Edge-AI Framework for Alzheimer's and Creutzfeldt-Jakob Disease Classification.
Journal: Sensors (Basel, Switzerland)
In common: EEG, 2 references
[7] doi:10.3390/brainsci16080856 [code]
Alzheimer's Disease Detection Using Combined EEG Source Connectivity and Microstate Features.
Journal: Brain sciences
In common: EEG, 2 references
[8] doi:10.3390/bios16050258 [code]
A Two-Stage EEG Microstate Fusion Framework for Dementia Screening and Alzheimer's Disease/Frontotemporal Dementia Differentiation.
Journal: Biosensors
In common: EEG, 2 references
[9] doi:10.1523/jneurosci.0295-26.2026 [code]
Detection and Removal of Hyper-synchronous Artifacts in Massively Parallel Spike Recordings.
Journal: The Journal of neuroscience : the official journal of the Society for Neuroscience
In common: 2 references
[10] doi:10.1371/journal.pbio.3003938 [code]
Theta oscillations tag episodic memories for sleep-dependent consolidation.
Journal: PLoS biology
In common: Wavelet Toolbox, EEG

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.