# EEG Denoising on BCI Competition IV-2b (test)

Source: [EEG Denoising on BCI Competition IV-2b (test)](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test>)

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

Data updated: 2026-06-09T09:03:44.568Z

Evaluation of EEG signal denoising performance using the test split of BCI Competition IV Dataset 2b, measured using Correlation Coefficient (CC), Root Mean Square Error (RMSE), and related error metrics.

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 | EEG Denoising |
| Dataset (including any stated split) | BCI Competition IV-2b (test) |
| Metric | Correlation Coefficient (CC) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Correlation Coefficient (CC)](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test.md?metric=Correlation%20Coefficient%20(CC)>): Higher is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [T-RRMSE](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test.md?metric=T-RRMSE>): Lower is better; unit: SCALAR.

- [S-RRMSE](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test.md?metric=S-RRMSE>): Lower is better; unit: SCALAR.

- [SDR](<https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test.md?metric=SDR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Correlation Coefficient (CC) | Result date | Report paper |
| --- | --- | --- | --- |
| DSConv U-Net (base6) | 0.777 | Not recorded | 6a279e2490966ade919bf7a7 |
| DSConv U-Net (base4) | 0.776 | Not recorded | 6a279e2490966ade919bf7a7 |
| DSConv U-Net (base8) | 0.772 | Not recorded | 6a279e2490966ade919bf7a7 |
| DSConv U-Net (base16) | 0.766 | Not recorded | 6a279e2490966ade919bf7a7 |
| DSConv U-Net (base2) | 0.75 | Not recorded | 6a279e2490966ade919bf7a7 |

### DSConv U-Net (base6)

Correlation Coefficient (CC): 0.777. Result ID: 6a27d6d9fbc373592c24c3fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

Recorded evaluation configuration: {"Base":"6","Params":"6.53K","zero-shot":"true","multi-seed":"true"}. This record does not assert independent reproduction.

### DSConv U-Net (base4)

Correlation Coefficient (CC): 0.776. Result ID: 6a27d6d9fbc373592c24c3fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

Recorded evaluation configuration: {"Base":"4","Params":"3.22K","zero-shot":"true","multi-seed":"true"}. This record does not assert independent reproduction.

### DSConv U-Net (base8)

Correlation Coefficient (CC): 0.772. Result ID: 6a27d6d9fbc373592c24c3fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

Recorded evaluation configuration: {"Base":"8","Params":"10.99K","zero-shot":"true","multi-seed":"true"}. This record does not assert independent reproduction.

### DSConv U-Net (base16)

Correlation Coefficient (CC): 0.766. Result ID: 6a27d6d9fbc373592c24c3fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

Recorded evaluation configuration: {"Base":"16","Params":"40.26K","zero-shot":"true","multi-seed":"true"}. This record does not assert independent reproduction.

### DSConv U-Net (base2)

Correlation Coefficient (CC): 0.75. Result ID: 6a27d6d9fbc373592c24c3fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2490966ade919bf7a7.md>)

Recorded evaluation configuration: {"Base":"2","Params":"1.05K","zero-shot":"true","multi-seed":"true"}. This record does not assert independent reproduction.

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