BCI Reportwet · 12 labels
15.3%
15.3% balanced accuracyParticipant-mean balanced accuracy
95% interval 13.7%–17.1%Calibration budget · the same session and the next one
How much calibration data does an EEG decoder need?
On a 12-target wearable protocol, target-only spectral ridge improves gradually but remains low; single-band ensemble TRCA benefits sharply on wet recordings from 24 to 48 labels and only modestly on dry recordings. Across two sessions of the same people, a few labeled trials from the new session raise one motor-imagery baseline on average, though some people decline; the other baseline’s gain is not established.
Measured on: Wearable SSVEP BCI dataset (dry and wet electrodes); OpenBMI motor imagery (Lee et al. 2019) · Methods: CCA; eTRCA
Short answer
It depends on the method, and on how far the test lies from the calibration. Within one session — a 12-target wearable SSVEP task, the same 102 people tested on the same future blocks — going from 24 to 48 labeled target trials lifted single-band eTRCA from 39.8% to 64.0% balanced accuracy on wet recordings but only from 12.4% to 15.1% on dry ones, and no calibrated eTRCA point beat the training-free CCA reference (81.1% wet, 65.1% dry); that eTRCA uses one fixed band, not the original method's filter bank. Across sessions — OpenBMI motor imagery, trained on each person's first session and tested on their second — 40 labeled second-session trials raised a log-covariance decoder by +4.6 pp on average across 51 people (interval +2.3 to +6.9 pp), yet 13 of them still declined; a relative-PSD decoder gained +1.7 pp, but its interval includes zero, so that gain is not established, and 16 people declined.
CCA · 0 labelswet recording · training-free reference
81.1% (77.2%–84.8%)
Spectral ridge · 12 labelswet recording · target-only
15.3% (13.7%–17.1%)
Spectral ridge · 24 labelswet recording · target-only
18.2% (15.9%–20.7%)
Spectral ridge · 48 labelswet recording · target-only
21.3% (18.3%–24.5%)
Single-band eTRCA · 24 labelswet recording · target-only
39.8% (34.1%–45.8%)
Single-band eTRCA · 48 labelswet recording · target-only
64.0% (57.1%–70.7%)
CCA · 0 labelsdry recording · training-free reference
65.1% (60.0%–70.0%)
Spectral ridge · 12 labelsdry recording · target-only
15.0% (13.6%–16.5%)
Spectral ridge · 24 labelsdry recording · target-only
18.3% (16.3%–20.7%)
Spectral ridge · 48 labelsdry recording · target-only
21.8% (19.3%–24.5%)
Single-band eTRCA · 24 labelsdry recording · target-only
12.4% (10.4%–15.0%)
Single-band eTRCA · 48 labelsdry recording · target-only
15.1% (12.6%–18.2%)
Target-only spectral ridge
Twelve, 24 and 48 labeled trials
Each target-person model uses only that person's labeled calibration recordings. All conditions are evaluated on the same future blocks 5–10, across 102 people and 7,344 test trials.
wet · 24 labels
18.2%
18.2% balanced accuracyParticipant-mean balanced accuracy
95% interval 15.9%–20.7%wet · 48 labels
21.3%
21.3% balanced accuracyParticipant-mean balanced accuracy
95% interval 18.3%–24.5%dry · 12 labels
15.0%
15.0% balanced accuracyParticipant-mean balanced accuracy
95% interval 13.6%–16.5%dry · 24 labels
18.3%
18.3% balanced accuracyParticipant-mean balanced accuracy
95% interval 16.3%–20.7%dry · 48 labels
21.8%
21.8% balanced accuracyParticipant-mean balanced accuracy
95% interval 19.3%–24.5%Trial counts are not minutes.
A separate arm
Zero target labels is source-only transfer
The zero-budget spectral-ridge rows use a model trained on other participants from one source sensor.
| Training source | Test on wet | Test on dry |
|---|---|---|
| wet sourceother participants only | 39.2%35.4%–43.0% | 35.4%32.0%–39.0% |
| dry sourceother participants only | 39.0%35.2%–42.9% | 37.2%33.6%–40.9% |
eTRCA and CCA
Single-band eTRCA responds differently
The target-only eTRCA arm uses 24 or 48 calibration trials and the same future test blocks. CCA at zero labels is the analytic reference.
+24.2 ppWet eTRCA: 48 labels minus 24 labels
A larger budget helped wet recordings much more
The paired participant interval is +19.7 to +28.8 pp. Dry eTRCA improved by +2.7 pp, interval +1.3 to +4.2 pp. Neither calibrated point exceeds the analytic CCA reference on the same test blocks.
| Method and labeled target trials | Wet | Dry |
|---|---|---|
| CCA · 0 labelsanalytic target-recording reference | 81.1%77.2%–84.8% | 65.1%60.0%–70.0% |
| Single-band eTRCA · 24 labelstarget-only adaptation | 39.8%34.1%–45.8% | 12.4%10.4%–15.0% |
| Single-band eTRCA · 48 labelstarget-only adaptation | 64.0%57.1%–70.7% | 15.1%12.6%–18.2% |
Next session · OpenBMI motor imagery
The next session: how much do a few labeled trials help?
This result is kept apart from the SSVEP results above: a different data set, task and test. In OpenBMI, people imagined moving the left or the right hand in two sessions. Each person’s decoder is trained on their session 1 — the first 80 trials fit it, the last 20 calibrate its probabilities — then given the first 0, 10, 20 or 40 labeled trials of their session 2, and tested on the final 60 trials of session 2. Every budget is tested on those same trials.
People evaluated
51
54 acquired, minus 1 engineering exclusion and 2 held for input quality.
Held-out trials
3,060
60 per person, the final trials of session 2.
Prediction jobs
408
Every person × two baselines × four budgets; none failed.
| Labeled session-2 trials | Log-covariance + shrinkage LDA | Relative PSD + standardized ridge |
|---|---|---|
| None · session 1 only | 67.9%95% interval 63.6%–72.4% | 57.3%95% interval 54.4%–60.5% |
| 10 trials | 69.1%95% interval 64.8%–73.5% | 57.4%95% interval 54.5%–60.5% |
| 20 trials | 69.2%95% interval 65.3%–73.4% | 57.9%95% interval 55.2%–60.8% |
| 40 trials | 72.4%95% interval 68.9%–76.2% | 59.0%95% interval 56.0%–62.1% |
+4.6 ppLog-covariance LDA: 40 labeled session-2 trials minus none, the same 51 people
Better on average — and still worse for some people
Paired interval +2.3 to +6.9 pp, above zero. Yet 13 of 51 people scored lower with the trials than without them, 6 of them by 5 points or more. For the relative-PSD baseline the mean change was +1.7 pp (−0.1 to +3.5 pp): the interval includes zero, so that gain is not established; 16 of 51 people declined, 6 by 5 points or more.
| Comparison | Log-covariance + shrinkage LDA | Relative PSD + standardized ridge |
|---|---|---|
| 10 trials minus none | +1.2 pp95% interval −0.6 to +3.3 pp21 of 51 declined · 8 by 5 points or moreThe interval includes zero: not established. | +0.1 pp95% interval −1.1 to +1.2 pp25 of 51 declined · 6 by 5 points or moreThe interval includes zero: not established. |
| 20 trials minus none | +1.4 pp95% interval −0.3 to +3.2 pp24 of 51 declined · 6 by 5 points or moreThe interval includes zero: not established. | +0.6 pp95% interval −0.9 to +2.0 pp19 of 51 declined · 10 by 5 points or moreThe interval includes zero: not established. |
| 40 trials minus none | +4.6 pp95% interval +2.3 to +6.9 pp13 of 51 declined · 6 by 5 points or more | +1.7 pp95% interval −0.1 to +3.5 pp16 of 51 declined · 6 by 5 points or moreThe interval includes zero: not established. |
An expanded cohort under the same fixed method, not an independent replication: the original 40 people, their results unchanged, plus all 11 people who became eligible later. An earlier snapshot of the original people was prepared but never published here.
Limits of the next-session result
One dataset, offline
Online closed-loop control, clinical efficacy, consumer headsets and reduced montages are outside this test.
Same person
Every model is fitted to the person it is tested on.
Two fixed CPU baselines
No parameter search, score-driven retry or trial dropping, and no foundation model or fine-tuning (LoRA/PEFT). They are a reference, not a ceiling.
Noisy per person
Each person’s change rests on 60 test trials, which the four budgets reuse, so one person’s decline can be noise.
Units unresolved
The recordings’ physical amplitude unit is not resolved, so only dimensionless inputs are used: each trial filtered 8–30 Hz, covariances divided by their trace, band powers as shares.
Pointwise intervals
Whole-participant bootstrap, 10,000 draws shared by every baseline and budget, not adjusted for multiple comparisons.
OpenBMI motor imagery (Lee et al. 2019)
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.
The paper’s Ethical Approval section states approval by the Korea University Institutional Review Board (1040548-KUIRB-16-159-A-2) and written informed consent from all participants before the experiments. Only cohort means, paired changes and how many people declined appear here — never who.
Data source: large-source-update.json · schema bci-report-large-source-update-v1.
LaBraM adaptation has its own page
The LaBraM results on new people, same task, zero labels from the test person — head only, last block or LoRA — moved to their own page: New people, next day: which part of a pretrained model should you update?
The next-day experiment has moved to the model-adaptation page
The next-day status — run, independently replayed and held, with no figure published — is on the same page: New people, next day: which part of a pretrained model should you update?
Methods & limits
Limits of the SSVEP budget curves
Prespecified single band
eTRCA uses the fixed 6–80 Hz prepared band, not the filter bank of the original method (five sub-bands in the paper and in the reference code’s tutorials), so low scores do not establish an optimized TRCA ceiling.
Descriptive intervals
Bootstrap intervals summarize participants under this protocol, without retraining uncertainty.
An Open Dataset for Wearable SSVEP-Based Brain-Computer Interfaces
Zhu, F., Jiang, L., Dong, G., Gao, X., & Wang, Y. (2021). An Open Dataset for Wearable SSVEP-Based Brain-Computer Interfaces (Version 4) [Data set]. Figshare. https://doi.org/10.6084/m9.figshare.13560281.v4
Zhu, F., Jiang, L., Dong, G., Gao, X., & Wang, Y. (2021). An Open Dataset for Wearable SSVEP-Based Brain-Computer Interfaces. Sensors, 21(4), 1256. https://doi.org/10.3390/s21041256
Official Tsinghua author mirror snapshot acquired 2026-09-20 · CC BY 4.0. Aggregate results only.
Data source: reviewed aggregate JSON · schema bci-report-public-deployment-topics-v1.
Cite this page
BCI Report (2026). How much calibration data does an EEG decoder need? https://bci.report/topics/calibration-budget/
Figures from releases large-source-update-20261003 (2026-10-03), deployment-topics-20260920-v1 (2026-09-20). Cite the upstream datasets as well: their credits are on this page.
Every release is archived on Zenodo: doi:10.5281/zenodo.23123296. BibTeX for the site and its releases → · CITATION.cff ↗