Paired epochs kept
75.2%
11,674 of 15,52311,674 of 15,523
Montage · two paired comparisons
Fewer electrodes
On the same 10 people and the same 30-second epochs, six scalp electrodes staged sleep better than four in-ear channels — for every one of the 10. That is a paired, descriptive result from one simple model on one cohort. It does not rank headsets, and it does not separate the hardware from electrode position and count. A second, unrelated comparison — four posterior electrodes against all sixteen for telling eyes open from closed — found no consistent difference across 19 people.
+15.4 ppScalp minus in-ear balanced accuracy, same 10 people
Every person scored higher on scalp
10 of 10 people scored higher with six scalp electrodes than with four in-ear channels. The descriptive person-bootstrap interval for the mean difference is +10.6 to +20.3 pp. Both configurations were scored on the identical epochs.
Two configurations, identical epochs
Four in-ear channels against six scalp electrodes
Five-stage sleep, scored in 30-second epochs; chance is 20%. Ten leave-one-person-out folds and one fixed model for both configurations.
| Configuration | Channels | Balanced accuracy | Macro F1 |
|---|---|---|---|
| Four in-ear channelsphysical in-ear channels; not standard scalp positions | RB · RT · LB · LT | 53.6%47.4%–59.7%53.6% balanced accuracy | 47.6% |
| Six scalp electrodesmastoid slots M1 and M2 used only to screen for complete epochs | F3 · C3 · O1 · F4 · C4 · O2 | 69.0%63.4%–74.2%69.0% balanced accuracy | 64.9% |
Usable data
What the scores are conditioned on
An epoch was kept only if both configurations had complete, finite data for it; that rule dropped 3,849 epochs. The scores describe this subset, not how often either device records usable data.
People
10
all retained
Nights
17
17 of 19
Second comparison · eyes open and closed
Four posterior electrodes against all sixteen
A different task on different people: telling eyes open from eyes closed in 6-second windows, where chance is 50%. Both configurations are subsets of the same 16-electrode research recordings, scored with one fixed model over 19 leave-one-person-out folds.
−1.6 ppAll sixteen minus four posterior, same 19 people
No consistent difference
7 of 19 people scored higher with all sixteen electrodes, 7 with the four posterior ones, and 5 tied. The descriptive person-bootstrap interval for the mean difference is −10.0 to +6.8 pp. It spans zero: in this cohort the four posterior electrodes were neither clearly better nor clearly worse than all sixteen. That does not make fewer electrodes better.
| Configuration | Channels | Balanced accuracy | Macro F1 |
|---|---|---|---|
| Four posterior electrodesselected in software from the same recording | Pz · O1 · Oz · O2 | 79.5%72.6%–85.8%79.5% balanced accuracy | 76.6% |
| All sixteen electrodesevery electrode the cap recorded | Fp1 · Fp2 · Fc5 · Fz · Fc6 · T7 · Cz · T8 · P7 · P3 · Pz · P4 · P8 · O1 · Oz · O2 | 77.9%70.5%–85.3%77.9% balanced accuracy | 74.5% |
Methods & limits
What these comparisons can and cannot support
Two paired comparisons on two different cohorts, each with one simple, untuned model. Each narrows one question; neither settles a device choice, and the two do not share a ranking.
Sleep · in-ear and scalp
Six scalp electrodes, not eight
The scalp files also carry two mastoid slots. They were used only in the completeness screen and never entered the model.
Position, count and hardware move together
The in-ear and scalp configurations differ in placement, geometry and number of electrodes. The difference is descriptive, not an estimate of what the ear hardware alone costs.
One simple, untuned model
Five log-bandpower features per channel and an L2 logistic regression with no hyperparameter search. Not a foundation model, and not a ceiling for either configuration.
Not the core sleep protocol
The eight-protocol matrix scores the EESM19 scalp subset with a different cohort and recipe. The two sleep results do not share a ranking.
Eyes open and closed · four and sixteen
Eyes open or closed, not attention
Closing the eyes produces a strong alpha rhythm over the back of the head, which is why four posterior electrodes can carry this task. It is a pipeline check, not concentration, workload or intent detection.
Subsets of one recording, not two headsets
Both configurations are channels selected in software from the same 16-electrode wet-cap recordings. Four channels picked this way do not validate a physical four-channel device.
19 of 20 recordings
The source has 20 recordings. The authors’ own data loader leaves out recording 07, and this comparison keeps that fixed cohort. Our event audit also flagged overlapping events in that recording, but the authors’ reason for leaving it out is not established.
An interval, not a verdict
The interval is a descriptive bootstrap over 19 people, not a population estimate. It shows neither that fewer electrodes are generally better nor that they are generally no worse.
EESM23 · Ear-EEG Sleep Monitoring 2023
Dataset: Yousef Rezaei Tabar, Kaare Mikkelsen, Laura Birch, Nelly Shenton, Simon L. Kappel, Astrid R. Bertelsen, Reza Nikbakht, Hans O. Toft, Chris H. Henriksen, Martin C. Hemmsen, Mike L. Rank, Marit Otto and Preben Kidmose · Ear-EEG Sleep Monitoring 2023 (EESM23), OpenNeuro ds005178 v1.0.0, doi:10.18112/openneuro.ds005178.v1.0.0. Study: Kaare Bjarke Mikkelsen, Yousef Rezai Tabar, Laura Rævsbæk Birch, Simon Lind Kappel, Christian Bech Christensen, Lars Dalskov Mosgaard, Marit Otto, Martin Christian Hemmsen, Mike Lind Rank and Preben Kidmose · Ear-EEG sleep monitoring data sets, Scientific Data 12, 301 (2025), doi:10.1038/s41597-025-04579-8. Processed export: Zachary1150/EESM23-Processed on Hugging Face, which did not create the original cohort.
Consent covered the study; the data were released after the GDPR office of Region Midt judged them fully anonymized. Only cohort aggregates appear here.
OpenNeuro dataset ↗ · Scientific Data paper ↗ · Processed export ↗ · CC0-1.0
EEG Alpha Waves dataset
Grégoire Cattan, Pedro L. C. Rodrigues and Marco Congedo · EEG Alpha Waves dataset, Zenodo, doi:10.5281/zenodo.2605110. Report: Grégoire Cattan, Pedro Luiz Coelho Rodrigues and Marco Congedo · EEG Alpha Waves Dataset, research report, GIPSA-lab, Grenoble, 2018, hal-02086581.
According to the primary report, every participant gave written informed consent covering the experimental process, the data management procedures and the right to withdraw at any moment. The report names no ethics committee. Only cohort aggregates appear here.
Zenodo record ↗ · HAL report ↗ · Authors’ code ↗ · CC-BY-4.0
Data source: reviewed aggregate JSON · schema bci-report-evidence-update-v1 · generated 2026-09-22.