# Motor Imagery Decoding on EEGMMI (Leave-One-Subject-Out)

Source: [Motor Imagery Decoding on EEGMMI (Leave-One-Subject-Out)](<https://www.sota2.com/research/sota/motor-imagery-decoding-on-eegmmi-leave-one-subject-out>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-02T12:22:10.145Z

Evaluation of Motor Imagery Decoding performance on the EEGMMI dataset using the Leave-One-Subject-Out protocol, reporting Accuracy, Macro-F1, and Kappa statistics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Motor Imagery Decoding |
| Dataset (including any stated split) | EEGMMI (Leave-One-Subject-Out) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/motor-imagery-decoding-on-eegmmi-leave-one-subject-out.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro-F1](<https://www.sota2.com/research/sota/motor-imagery-decoding-on-eegmmi-leave-one-subject-out.md?metric=Macro-F1>): Higher is better; unit: PERCENT.

- [Kappa](<https://www.sota2.com/research/sota/motor-imagery-decoding-on-eegmmi-leave-one-subject-out.md?metric=Kappa>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EVA-Net | 72.3 | Not recorded | 6a1e643bdbd7150506f858a6 |
| EEGNet | 63.64 | Not recorded | 6a1e643bdbd7150506f858a6 |
| EEGCCT | 63.34 | Not recorded | 6a1e643bdbd7150506f858a6 |
| EEG Conformer | 62.56 | Not recorded | 6a1e643bdbd7150506f858a6 |
| ShallowConvNet | 60.79 | Not recorded | 6a1e643bdbd7150506f858a6 |
| MSVTNet | 53 | Not recorded | 6a1e643bdbd7150506f858a6 |

### EVA-Net

Accuracy: 72.3. Result ID: 6a1ecae0fbc373592c1a6c8a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

### EEGNet

Accuracy: 63.64. Result ID: 6a1ecae0fbc373592c1a6c85.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5ee01e209131ce9e5f5a.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

### EEGCCT

Accuracy: 63.34. Result ID: 6a1ecae0fbc373592c1a6c87.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

### EEG Conformer

Accuracy: 62.56. Result ID: 6a1ecae0fbc373592c1a6c88.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

### ShallowConvNet

Accuracy: 60.79. Result ID: 6a1ecae0fbc373592c1a6c86.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

### MSVTNet

Accuracy: 53. Result ID: 6a1ecae0fbc373592c1a6c89.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e643bdbd7150506f858a6.md>)

Recorded evaluation configuration: {"Experimental Setup":"Leave-One-Subject-Out"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
