OSCR

Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study.

Overview

Authors: Wenwen Chang1, Hesam Akbari2, Muhammad Tariq Sadiq3, Renjie Lv1, Rab Nawaz3
  1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China; (W.C.); (R.L.)
  2. Department of Information Science, University of North Texas, Denton, TX 76207, USA
  3. School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK
Institutions: Lanzhou Jiaotong University (China); University of North Texas (United States); University of Essex (United Kingdom)
Journal: Brain sciences, volume 16, issue 8, article 873
Dates: received 16 July 2026; accepted 15 August 2026; published online 17 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/brainsci16080873 · PMID 42651181 · PMCID PMC13511235 · OpenAlex W7203655817
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), human (organism), methods / tools (subfield)
Methods: Statistics, Machine learning, Spectral & time-frequency, Connectivity, Preprocessing
Keywords: motor imagery EEG, validation protocol, cross-subject generalisation, subject-independent evaluation, leave-one-subject-out cross-validation, nested cross-validation, data leakage
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: the Gansu Provincial Science and Technology Talent Program Special Fund (No. 26RCKA018); National Natural Science Foundation of China (No. W2421090)
Citations: not cited yet (Europe PMC); 35 references in the paper

Abstract

Background: Performance estimates in motor-imagery electroencephalography (MI-EEG) can depend strongly on how observations are partitioned for training, model selection, and testing. Random sample- or window-level splitting may place data from the same participant in different folds and therefore does not answer the same question as evaluation on previously unseen participants. Methods: We evaluated a previously developed Gramian angular field–phase-locking value (GAF–PLV) classifier on the retained full cohort (N=105) using binary left-versus-right MI and leave-one-subject-out cross-validation (LOSO). Separately, a predefined, outcome-independent subset (N=30) was used for a matched sensitivity analysis of eight classifiers, binary and four-class tasks, and three validation strategies: random five-fold cross-validation, LOSO, and nested LOSO with subject-grouped inner model selection. Results: In the full-cohort GAF–PLV analysis, mean accuracy was 58.07% ± 8.27% and Macro-F1 was 53.48% ± 11.19%, with substantial between-subject variability. In the predefined matched subset, performance estimates and numerical model rankings changed across validation strategies. For example, the numerically highest binary-accuracy model was ShallowConvNet under random five-fold cross-validation, DeepConvNet under LOSO, and ATCNet under nested LOSO. Conclusions: Random within-cohort classification and generalisation to previously unseen subjects are distinct evaluation targets. MI-EEG reports should state the cohort, partition unit, validation design, and model-selection procedure. Rankings in the multi-model analysis are conditional on the predefined 30-subject subset and common 0.4 s input setting and are not presented as definitive full-cohort or architecture-optimal rankings.

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

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data Availability Statement

The EEG Motor Movement/Imagery dataset analysed in this study is publicly available from PhysioNet at https://www.physionet.org/content/eegmmidb/1.0.0/ (accessed on 1 January 2025). No new public dataset was created in this study.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 7 keywords, 2 funders, 33 references.

Cite

This paper

Chang, W., Akbari, H., Sadiq, M. T., Lv, R., & Nawaz, R. (2026). Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study. Brain sciences, 16(8), 873. https://doi.org/10.3390/brainsci16080873

BibTeX

@article{chang2026evaluating,
author = {Chang, Wenwen and Akbari, Hesam and Sadiq, Muhammad Tariq and Lv, Renjie and Nawaz, Rab},
title = {{Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study}},
journal = {Brain sciences},
year = {2026},
month = aug,
volume = {16},
number = {8},
pages = {873},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2076-3425},
doi = {10.3390/brainsci16080873},
url = {https://doi.org/10.3390/brainsci16080873},
pmid = {42651181},
pmcid = {PMC13511235}
}

RIS

TY - JOUR
AU - Chang, Wenwen
AU - Akbari, Hesam
AU - Sadiq, Muhammad Tariq
AU - Lv, Renjie
AU - Nawaz, Rab
TI - Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study
T2 - Brain sciences
J2 - Brain Sci
PY - 2026
DA - 2026/08/17
VL - 16
IS - 8
SP - 873
SN - 2076-3425
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/brainsci16080873
UR - https://doi.org/10.3390/brainsci16080873
LA - en
ER -

CSL-JSON

{
"id": "10.3390/brainsci16080873",
"type": "article-journal",
"title": "Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study",
"container-title": "Brain sciences",
"author": [
{
"family": "Chang",
"given": "Wenwen"
},
{
"family": "Akbari",
"given": "Hesam"
},
{
"family": "Sadiq",
"given": "Muhammad Tariq"
},
{
"family": "Lv",
"given": "Renjie"
},
{
"family": "Nawaz",
"given": "Rab"
}
],
"container-title-short": "Brain Sci",
"volume": "16",
"issue": "8",
"page": "873",
"DOI": "10.3390/brainsci16080873",
"PMID": "42651181",
"PMCID": "PMC13511235",
"ISSN": "2076-3425",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/brainsci16080873",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
17
]
]
}
}

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:10.1007/s12021-025-09733-6 [code]
Estimation of Task-Related Dynamic Brain Connectivity via Data Inflation and Classification Model Explainability.
Journal: Neuroinformatics
In common: DOI 10.13026/c28g6p, physionet.org/content/eegmmidb, EEG, 6 references
[2] doi:10.1155/2021/1160454 [code]
CNN-Based Personal Identification System Using Resting State Electroencephalography.
Journal: Computational intelligence and neuroscience
In common: DOI 10.13026/c28g6p, physionet.org/content/eegmmidb, EEG, 3 references
[3] doi:10.3389/fncom.2022.882290
Deep Residual Convolutional Neural Networks for Brain-Computer Interface to Visualize Neural Processing of Hand Movements in the Human Brain.
Journal: Frontiers in computational neuroscience
In common: DOI 10.13026/c28g6p, EEG, 6 references
[4] doi:10.3390/brainsci14121272
The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems.
Journal: Brain sciences
In common: physionet.org/content/eegmmidb, methods / tools, EEG, 6 references
[5] doi:10.1371/journal.pcbi.1014112 [code]
Opposing cortical forces: Alpha slowing and sensorimotor mu acceleration during motor-related BCI training.
Journal: PLoS computational biology
In common: DOI 10.13026/c28g6p, physionet.org/content/eegmmidb, EEG, 2 references
[6] doi:10.3390/s25113389
Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction.
Journal: Sensors (Basel, Switzerland)
In common: DOI 10.13026/c28g6p, physionet.org/content/eegmmidb, EEG, 2 references
[7] doi:10.3390/brainsci15090977
Predicting Depression Therapy Outcomes Using EEG-Derived Amplitude Polar Maps.
Journal: Brain sciences
In common: EEG, 2 authors
[8] doi:10.1038/s41598-025-32207-3 [code]
Multi-scale EEG feature decoding with Swin Transformers for subject independent motor imagery BCIs.
Journal: Scientific reports
In common: physionet.org/content/eegmmidb, methods / tools, EEG, 5 references
[9] doi:10.3390/s23187908 [code]
Enhancing Cross-Subject Motor Imagery Classification in EEG-Based Brain-Computer Interfaces by Using Multi-Branch CNN.
Journal: Sensors (Basel, Switzerland)
In common: physionet.org/content/eegmmidb, EEG, 5 references
[10] doi:10.3389/fnins.2026.1851006
Domain-aware domain-class adaptation network for motor execution to motor imagery EEG classification.
Journal: Frontiers in neuroscience
In common: physionet.org/content/eegmmidb, EEG, 5 references

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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

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