# Four-class sleep staging on Oxford Sleep Volunteers

Source: [Four-class sleep staging on Oxford Sleep Volunteers](<https://www.sota2.com/research/sota/four-class-sleep-staging-on-oxford-sleep-volunteers>)

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

Data updated: 2026-02-26T05:47:48.428Z

Evaluation of four-class sleep staging performance using the Oxford Sleep Volunteers dataset, reporting specialized Kappa (mu and T) and Accuracy 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 | four-class sleep staging |
| Dataset (including any stated split) | Oxford Sleep Volunteers |
| Metric | Kappa (mu) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Kappa (mu)](<https://www.sota2.com/research/sota/four-class-sleep-staging-on-oxford-sleep-volunteers.md?metric=Kappa%20(mu)>): Higher is better; unit: PERCENT.

- [Kappa (T)](<https://www.sota2.com/research/sota/four-class-sleep-staging-on-oxford-sleep-volunteers.md?metric=Kappa%20(T)>): Higher is better; unit: PERCENT.

- [Accuracy (mu)](<https://www.sota2.com/research/sota/four-class-sleep-staging-on-oxford-sleep-volunteers.md?metric=Accuracy%20(mu)>): Higher is better; unit: PERCENT.

- [Accuracy (T)](<https://www.sota2.com/research/sota/four-class-sleep-staging-on-oxford-sleep-volunteers.md?metric=Accuracy%20(T)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Kappa (mu) | Result date | Report paper |
| --- | --- | --- | --- |
| SleepVST | 68 | Not recorded | 68fa5f571e209131ce9e913a |
| Carter et al. | 61 | Not recorded | 68fa5f571e209131ce9e913a |

### SleepVST

Kappa (mu): 68. Result ID: 698bc3cc7a967eddb77130a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f571e209131ce9e913a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f571e209131ce9e913a.md>)

Recorded evaluation configuration: {"N":"50","Modalities":"HW+BW+Motion (Cardiac pulse + Respiration + Motion)"}. This record does not assert independent reproduction.

### Carter et al.

Kappa (mu): 61. Result ID: 698bc3cc7a967eddb77130a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f571e209131ce9e913a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa41e209131cea46db3.md>)

Recorded evaluation configuration: {"N":"50","Modalities":"HR+BR+Motion (Heart Rate + Breathing Rate + Motion)"}. This record does not assert independent reproduction.

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