Motor imagery: left or right hand across two sessions, and imagery or rest

OpenBMI motor imagery (Lee et al. 2019): EEG decoding results

The OpenBMI dataset (GigaScience Database 100542) holds EEG from 54 healthy participants, each recorded in two sessions on different days in three BCI paradigms — motor imagery, event-related potentials and SSVEP — with 62 electrodes at 1,000 Hz, plus questionnaires, resting-state and artifact recordings. Released by Lee et al. (Korea University) with the OpenBMI toolbox and described in GigaScience (2019). Only the motor-imagery training runs are used here.

Also known as OpenBMI · Lee2019 · Lee2019_MI · GigaDB 100542 · EEG Dataset and OpenBMI Toolbox for Three BCI Paradigms · Lee et al. (2019)

Description sources doi.org · doi.org · api.datacite.org

Where it appears

Published results

Each figure comes from the reviewed download linked in its group. One row is above another only where their 95% intervals do not overlap.

Calibration budget · same person, next session, motor imagery

Source page: How much calibration? · Chance level 50.0% · large-source-update.json

Log-covariance + shrinkage LDA · Session 1 → session 2 · 0 labeled session-2 trials
67.9% (63.6%–72.4%)
Log-covariance + shrinkage LDA · Session 1 → session 2 · 10 labeled session-2 trials
69.1% (64.8%–73.5%)
Log-covariance + shrinkage LDA · Session 1 → session 2 · 20 labeled session-2 trials
69.2% (65.3%–73.4%)
Log-covariance + shrinkage LDA · Session 1 → session 2 · 40 labeled session-2 trials
72.4% (68.9%–76.2%)
Relative PSD + standardized ridge · Session 1 → session 2 · 0 labeled session-2 trials
57.3% (54.4%–60.5%)
Relative PSD + standardized ridge · Session 1 → session 2 · 10 labeled session-2 trials
57.4% (54.5%–60.5%)
Relative PSD + standardized ridge · Session 1 → session 2 · 20 labeled session-2 trials
57.9% (55.2%–60.8%)
Relative PSD + standardized ridge · Session 1 → session 2 · 40 labeled session-2 trials
59.0% (56.0%–62.1%)
Balanced accuracy, 8 configurations. Dot: the estimate; line: 95% interval; dashed line, where drawn: chance level.
MethodConditionMetricValuePeople
Log-covariance + shrinkage LDASession 1 → session 2 · 0 labeled session-2 trialsBalanced accuracy67.9%63.6%–72.4%51
Log-covariance + shrinkage LDASession 1 → session 2 · 10 labeled session-2 trialsBalanced accuracy69.1%64.8%–73.5%51
Log-covariance + shrinkage LDASession 1 → session 2 · 20 labeled session-2 trialsBalanced accuracy69.2%65.3%–73.4%51
Log-covariance + shrinkage LDASession 1 → session 2 · 40 labeled session-2 trialsBalanced accuracy72.4%68.9%–76.2%51
Log-covariance + shrinkage LDA10 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+1.2 pp−0.6 pp–+3.3 pp21 of 51 people declined, 8 by 5 points or more. The interval includes zero: the gain is not established.51
Log-covariance + shrinkage LDA20 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+1.4 pp−0.3 pp–+3.2 pp24 of 51 people declined, 6 by 5 points or more. The interval includes zero: the gain is not established.51
Log-covariance + shrinkage LDA40 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+4.6 pp+2.3 pp–+6.9 pp13 of 51 people declined, 6 by 5 points or more.51
Relative PSD + standardized ridgeSession 1 → session 2 · 0 labeled session-2 trialsBalanced accuracy57.3%54.4%–60.5%51
Relative PSD + standardized ridgeSession 1 → session 2 · 10 labeled session-2 trialsBalanced accuracy57.4%54.5%–60.5%51
Relative PSD + standardized ridgeSession 1 → session 2 · 20 labeled session-2 trialsBalanced accuracy57.9%55.2%–60.8%51
Relative PSD + standardized ridgeSession 1 → session 2 · 40 labeled session-2 trialsBalanced accuracy59.0%56.0%–62.1%51
Relative PSD + standardized ridge10 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+0.1 pp−1.1 pp–+1.2 pp25 of 51 people declined, 6 by 5 points or more. The interval includes zero: the gain is not established.51
Relative PSD + standardized ridge20 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+0.6 pp−0.9 pp–+2.0 pp19 of 51 people declined, 10 by 5 points or more. The interval includes zero: the gain is not established.51
Relative PSD + standardized ridge40 minus 0 labeled session-2 trials, the same people and test trialsPaired difference+1.7 pp−0.1 pp–+3.5 pp16 of 51 people declined, 6 by 5 points or more. The interval includes zero: the gain is not established.51

One model, several questions · motor imagery (route 2)

Source page: One model, several questions · Chance level 50.0% · shared-representation-update.json

EEGNet · fixed heads (B-lin) · imagery or rest (MI-A) · trained from scratch, three seeds
73.2% (70.2%–76.2%)
EEGNet · shared hidden layer (B-sh) · imagery or rest (MI-A) · trained from scratch, three seeds
74.3% (71.3%–77.3%)
EEGNet · question-conditioned head (C1) · imagery or rest (MI-A) · trained from scratch, three seeds
74.6% (71.9%–77.5%)
EEGNet · separate model (A) · imagery or rest (MI-A) · trained from scratch, three seeds
74.2% (71.3%–76.9%)
CBraMod · fixed heads (B-lin-fz-sgd) · imagery or rest (MI-A) · heads on frozen features, three seeds
69.2% (67.0%–71.5%)
CBraMod · shared hidden layer (B-sh-fz) · imagery or rest (MI-A) · heads on frozen features, three seeds
70.9% (68.4%–73.4%)
CBraMod · question-conditioned head (C1-fz) · imagery or rest (MI-A) · heads on frozen features, three seeds
70.8% (68.4%–73.2%)
EEGNet · fixed heads (B-lin) · which hand (MI-B) · trained from scratch, three seeds
67.5% (64.6%–70.5%)
EEGNet · shared hidden layer (B-sh) · which hand (MI-B) · trained from scratch, three seeds
67.0% (64.1%–69.9%)
EEGNet · question-conditioned head (C1) · which hand (MI-B) · trained from scratch, three seeds
67.4% (64.4%–70.5%)
EEGNet · separate model (A) · which hand (MI-B) · trained from scratch, three seeds
69.0% (65.9%–72.0%)
CBraMod · fixed heads (B-lin-fz-sgd) · which hand (MI-B) · heads on frozen features, three seeds
56.1% (54.8%–57.4%)
CBraMod · shared hidden layer (B-sh-fz) · which hand (MI-B) · heads on frozen features, three seeds
56.7% (55.4%–58.2%)
CBraMod · question-conditioned head (C1-fz) · which hand (MI-B) · heads on frozen features, three seeds
57.2% (55.8%–58.6%)
Balanced accuracy, 14 configurations. Dot: the estimate; line: 95% interval; dashed line, where drawn: chance level.
MethodConditionMetricValuePeople
EEGNetfixed heads (B-lin) · imagery or rest (MI-A) · trained from scratch, three seedsBalanced accuracy73.2%70.2%–76.2%51
EEGNetshared hidden layer (B-sh) · imagery or rest (MI-A) · trained from scratch, three seedsBalanced accuracy74.3%71.3%–77.3%51
EEGNetquestion-conditioned head (C1) · imagery or rest (MI-A) · trained from scratch, three seedsBalanced accuracy74.6%71.9%–77.5%51
EEGNetseparate model (A) · imagery or rest (MI-A) · trained from scratch, three seedsBalanced accuracy74.2%71.3%–76.9%51
EEGNetimagery or rest (MI-A) · conditioned head minus fixed heads (C1 − B-lin)Paired difference, balanced accuracy+1.48 pp+0.09–+2.89 ppC1 higher; 2 pp margin not met; gate passed.51
EEGNetimagery or rest (MI-A) · conditioned head minus the same layer not told the question (C1 − B-sh)Paired difference, balanced accuracy+0.31 pp−0.91–+1.54 ppNo difference shown; equivalent within ±2 pp; gate passed.51
EEGNetimagery or rest (MI-A) · fixed heads on one shared small-CNN trunk minus separate models (B-lin − A(MI-A))Paired difference, balanced accuracy−1.00 pp−2.21–+0.19 ppNo difference shown; 2 pp margin not met: inconclusive at this sample size; gate passed.51
CBraModfixed heads (B-lin-fz-sgd) · imagery or rest (MI-A) · heads on frozen features, three seedsBalanced accuracy69.2%67.0%–71.5%51
CBraModshared hidden layer (B-sh-fz) · imagery or rest (MI-A) · heads on frozen features, three seedsBalanced accuracy70.9%68.4%–73.4%51
CBraModquestion-conditioned head (C1-fz) · imagery or rest (MI-A) · heads on frozen features, three seedsBalanced accuracy70.8%68.4%–73.2%51
CBraModimagery or rest (MI-A) · conditioned head minus fixed heads, on frozen CBraMod features (C1-fz − B-lin-fz-sgd)Paired difference, balanced accuracy+1.54 pp+0.86–+2.30 ppC1-fz higher; 2 pp margin not met; gate passed.51
EEGNetfixed heads (B-lin) · which hand (MI-B) · trained from scratch, three seedsBalanced accuracy67.5%64.6%–70.5%51
EEGNetshared hidden layer (B-sh) · which hand (MI-B) · trained from scratch, three seedsBalanced accuracy67.0%64.1%–69.9%51
EEGNetquestion-conditioned head (C1) · which hand (MI-B) · trained from scratch, three seedsBalanced accuracy67.4%64.4%–70.5%51
EEGNetseparate model (A) · which hand (MI-B) · trained from scratch, three seedsBalanced accuracy69.0%65.9%–72.0%51
EEGNetwhich hand (MI-B) · conditioned head minus fixed heads (C1 − B-lin)Paired difference, balanced accuracy−0.09 pp−1.24–+1.04 ppNo difference shown; equivalent within ±2 pp; gate passed.51
EEGNetwhich hand (MI-B) · conditioned head minus the same layer not told the question (C1 − B-sh)Paired difference, balanced accuracy+0.45 pp−0.60–+1.34 ppNo difference shown; equivalent within ±2 pp; gate passed.51
EEGNetwhich hand (MI-B) · fixed heads on one shared small-CNN trunk minus separate models (B-lin − A(MI-B))Paired difference, balanced accuracy−1.43 pp−2.57–−0.39 ppA(MI-B) higher; 2 pp margin not met; gate passed.51
CBraModfixed heads (B-lin-fz-sgd) · which hand (MI-B) · heads on frozen features, three seedsBalanced accuracy56.1%54.8%–57.4%51
CBraModshared hidden layer (B-sh-fz) · which hand (MI-B) · heads on frozen features, three seedsBalanced accuracy56.7%55.4%–58.2%51
CBraModquestion-conditioned head (C1-fz) · which hand (MI-B) · heads on frozen features, three seedsBalanced accuracy57.2%55.8%–58.6%51
CBraModwhich hand (MI-B) · conditioned head minus fixed heads, on frozen CBraMod features (C1-fz − B-lin-fz-sgd)Paired difference, balanced accuracy+1.09 pp+0.08–+2.12 ppC1-fz higher; 2 pp margin not met (not read: at floor); at floor: reported, not counted.51

Limits: The questions are label-backed classification targets from one dataset each, asked by identifier. They are not language prompts and say nothing about unseen questions (route 3). Per-person balanced accuracy averages people equally; it compares arms and is not a deployment error rate. The OpenBMI numbers here use route 2's own 2-s windows, label-free high-pass and person-disjoint folds; they are not comparable with the site's OpenBMI cross-session calibration figures. A contrast shows a difference when its paired 95% interval excludes zero; it is equivalent when the whole interval lies within ±2 pp, the margin fixed before any result, and an arm is non-inferior when the interval rules out its being 2 pp or more behind. No multiplicity correction: across route 2’s 21 primary comparisons and its secondary ones, about one in 20 comparisons with no true difference may show one by chance. Every limitation of route 2 →

Source and licence

OpenBMI motor imagery (Lee et al. 2019)

Credit Min-Ho Lee, O-Yeon Kwon, Yong-Jeong Kim, Hong-Kyung Kim, Young-Eun Lee, John Williamson, Siamac Fazli and Seong-Whan Lee · EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into BCI illiteracy, GigaScience (2019), giz002, doi:10.1093/gigascience/giz002. Data: Supporting data, GigaScience Database, doi:10.5524/100542.

CC0-1.0 ↗ · Dataset record ↗

BCI Report does not redistribute any recording. These are aggregate measurements computed by BCI Report under the licence above; the data remain their creators’.

Row in the open register →

All datasets → · All methods →

Cite this page

BCI Report (2026). OpenBMI motor imagery (Lee et al. 2019): EEG decoding results. https://bci.report/datasets/openbmi/

Figures from releases shared-representation-update-20261007 (2026-10-07), large-source-update-20261003 (2026-10-03). Cite the upstream dataset as well: its credit is on this page.

Every release is archived on Zenodo: doi:10.5281/zenodo.23123296. BibTeX for the site and its releases → · CITATION.cff ↗