# 3-class EEG Classification on ADFTD EEG-3 (Cross-subject)

Source: [3-class EEG Classification on ADFTD EEG-3 (Cross-subject)](<https://www.sota2.com/research/sota/3-class-eeg-classification-on-adftd-eeg-3-cross-subject>)

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

Data updated: 2026-05-22T09:06:37.337Z

Evaluation of 3-class EEG classification performance on the cross-subject split of the ADFTD EEG-3 dataset, reporting Accuracy, F1 Score, and AUR.

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 | 3-class EEG classification |
| Dataset (including any stated split) | ADFTD EEG-3 (Cross-subject) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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/3-class-eeg-classification-on-adftd-eeg-3-cross-subject.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/3-class-eeg-classification-on-adftd-eeg-3-cross-subject.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [AUR](<https://www.sota2.com/research/sota/3-class-eeg-classification-on-adftd-eeg-3-cross-subject.md?metric=AUR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BioFormer | 56.73 | Not recorded | 6a0fe30cf984739ed6739d93 |
| SoftShape | 54.6 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Medformer | 53.27 | Not recorded | 6a0fe30cf984739ed6739d93 |
| iTransformer | 52.6 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Reformer | 50.78 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Transformer | 50.47 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Crossformer | 50.45 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Nonformer | 49.95 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Informer | 48.45 | Not recorded | 6a0fe30cf984739ed6739d93 |
| FEDformer | 46.3 | Not recorded | 6a0fe30cf984739ed6739d93 |
| MTST | 45.6 | Not recorded | 6a0fe30cf984739ed6739d93 |
| Autoformer | 45.25 | Not recorded | 6a0fe30cf984739ed6739d93 |
| PatchTST | 44.37 | Not recorded | 6a0fe30cf984739ed6739d93 |

### BioFormer

Accuracy: 56.73. Result ID: 6a101b77fbc373592c0947cd.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

Recorded evaluation configuration: {"A.Rank":"1.47","Win":"4","Reproduced":"true"}. This record does not assert independent reproduction.

### SoftShape

Accuracy: 54.6. Result ID: 6a101b77fbc373592c0947cc.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79161e209131cea7c0e5.md>)

Recorded evaluation configuration: {"A.Rank":"3.61","Win":"1","Reproduced":"true"}. This record does not assert independent reproduction.

### Medformer

Accuracy: 53.27. Result ID: 6a101b77fbc373592c0947cb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75521e209131cea6727f.md>)

Recorded evaluation configuration: {"A.Rank":"4.94","Win":"0"}. This record does not assert independent reproduction.

### iTransformer

Accuracy: 52.6. Result ID: 6a101b77fbc373592c0947c9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72851e209131cea56f9c.md>)

Recorded evaluation configuration: {"A.Rank":"7.94","Win":"0"}. This record does not assert independent reproduction.

### Reformer

Accuracy: 50.78. Result ID: 6a101b77fbc373592c0947c2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea143ed.md>)

[Implementation](<https://github.com/google/trax/tree/master/trax/models/reformer>)

Recorded evaluation configuration: {"A.Rank":"5.25","Win":"0"}. This record does not assert independent reproduction.

### Transformer

Accuracy: 50.47. Result ID: 6a101b77fbc373592c0947c1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"A.Rank":"7.29","Win":"0"}. This record does not assert independent reproduction.

### Crossformer

Accuracy: 50.45. Result ID: 6a101b77fbc373592c0947c8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

Recorded evaluation configuration: {"A.Rank":"6.47","Win":"0"}. This record does not assert independent reproduction.

### Nonformer

Accuracy: 49.95. Result ID: 6a101b77fbc373592c0947c6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713e1e209131cea50092.md>)

[Implementation](<https://github.com/thuml/Nonstationary_Transformers>)

Recorded evaluation configuration: {"A.Rank":"7.12","Win":"0"}. This record does not assert independent reproduction.

### Informer

Accuracy: 48.45. Result ID: 6a101b77fbc373592c0947c3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699f1e209131cea23263.md>)

[Implementation](<https://github.com/zhouhaoyi/Informer2020>)

Recorded evaluation configuration: {"A.Rank":"7.42","Win":"0"}. This record does not assert independent reproduction.

### FEDformer

Accuracy: 46.3. Result ID: 6a101b77fbc373592c0947c5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c29.md>)

Recorded evaluation configuration: {"A.Rank":"10.67","Win":"0"}. This record does not assert independent reproduction.

### MTST

Accuracy: 45.6. Result ID: 6a101b77fbc373592c0947ca.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729f1e209131cea5799b.md>)

Recorded evaluation configuration: {"A.Rank":"8.33","Win":"0"}. This record does not assert independent reproduction.

### Autoformer

Accuracy: 45.25. Result ID: 6a101b77fbc373592c0947c4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b9a1e209131cea2f3a3.md>)

[Implementation](<https://github.com/thuml/Autoformer>)

Recorded evaluation configuration: {"A.Rank":"12.25","Win":"0"}. This record does not assert independent reproduction.

### PatchTST

Accuracy: 44.37. Result ID: 6a101b77fbc373592c0947c7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe30cf984739ed6739d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb21e209131cea4181f.md>)

Recorded evaluation configuration: {"A.Rank":"8.17","Win":"1"}. This record does not assert independent reproduction.

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