# Sleep Staging on ISRUC S3 (leave-one-subject-out cross-validation)

Source: [Sleep Staging on ISRUC S3 (leave-one-subject-out cross-validation)](<https://www.sota2.com/research/sota/sleep-staging-on-isruc-s3-leave-one-subject-out-cross-validation>)

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

Data updated: 2026-04-15T09:22:41.640Z

Evaluation of Sleep Staging performance on the ISRUC S3 dataset using leave-one-subject-out cross-validation, reporting Accuracy and F1 score.

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 | Sleep Staging |
| Dataset (including any stated split) | ISRUC S3 (leave-one-subject-out cross-validation) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/sleep-staging-on-isruc-s3-leave-one-subject-out-cross-validation.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/sleep-staging-on-isruc-s3-leave-one-subject-out-cross-validation.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EEG-MoCE | 78.53 | Not recorded | 69df1bb57d0172140ec7ba64 |
| XSleepFusion | 75.19 | Not recorded | 69df1bb57d0172140ec7ba64 |
| CTMWA | 75.11 | Not recorded | 69df1bb57d0172140ec7ba64 |
| LMF | 75.02 | Not recorded | 69df1bb57d0172140ec7ba64 |
| MMNet | 74.73 | Not recorded | 69df1bb57d0172140ec7ba64 |
| SSNet | 74.56 | Not recorded | 69df1bb57d0172140ec7ba64 |
| CFSNet | 74.3 | Not recorded | 69df1bb57d0172140ec7ba64 |
| MMML | 73.33 | Not recorded | 69df1bb57d0172140ec7ba64 |
| CMST | 66.68 | Not recorded | 69df1bb57d0172140ec7ba64 |

### EEG-MoCE

Accuracy: 78.53. Result ID: 69df584647f34ce924c85d53.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### XSleepFusion

Accuracy: 75.19. Result ID: 69df584647f34ce924c85d52.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### CTMWA

Accuracy: 75.11. Result ID: 69df584647f34ce924c85d51.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### LMF

Accuracy: 75.02. Result ID: 69df584647f34ce924c85d50.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646c1e209131cea049e6.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### MMNet

Accuracy: 74.73. Result ID: 69df584647f34ce924c85d4f.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### SSNet

Accuracy: 74.56. Result ID: 69df584647f34ce924c85d4e.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a041e209131cea25741.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### CFSNet

Accuracy: 74.3. Result ID: 69df584647f34ce924c85d4d.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### MMML

Accuracy: 73.33. Result ID: 69df584647f34ce924c85d4c.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2ac.md>)

[Implementation](<https://github.com/zehuiwu/MMML>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

### CMST

Accuracy: 66.68. Result ID: 69df584647f34ce924c85d4b.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bb57d0172140ec7ba64.md>)

Recorded evaluation configuration: {"validation\_protocol":"leave-one-subject-out cross-validation","n\_subjects":"10"}. This record does not assert independent reproduction.

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