# EEG Emotion Recognition on MPED (Subject-independent)

Source: [EEG Emotion Recognition on MPED (Subject-independent)](<https://www.sota2.com/research/sota/eeg-emotion-recognition-on-mped-subject-independent>)

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

Data updated: 2026-02-26T05:32:00.265Z

Evaluation of EEG-based emotion recognition performance using the subject-independent split of the MPED dataset.

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 emotion recognition |
| Dataset (including any stated split) | MPED (Subject-independent) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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/eeg-emotion-recognition-on-mped-subject-independent.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy Std Dev](<https://www.sota2.com/research/sota/eeg-emotion-recognition-on-mped-subject-independent.md?metric=Accuracy%20Std%20Dev>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Neuro-HGLN | 28.56 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| PGCN | 28.39 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| TANN | 28.32 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| BiHDM | 28.27 | Not recorded | 68fa5ee81e209131ce9e61fc |
| RGNN | 27.95 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| BiDANN | 25.86 | Not recorded | 68fa5ee81e209131ce9e61fc |
| DGCNN | 25.12 | Not recorded | 68fa5ee81e209131ce9e61fc |
| DGCNN | 25.12 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| A-LSTM | 24.06 | Not recorded | 68fa5ee81e209131ce9e61fc |
| DANN | 22.36 | Not recorded | 68fa5ee81e209131ce9e61fc |
| STM | 20.89 | Not recorded | 68fa5ee81e209131ce9e61fc |
| SA | 20.74 | Not recorded | 68fa5ee81e209131ce9e61fc |
| GFK | 20.27 | Not recorded | 68fa5ee81e209131ce9e61fc |
| SVM | 19.66 | Not recorded | 68fa5ee81e209131ce9e61fc |
| SVM | 19.66 | Not recorded | 6969c618e25ad2fa9d1ec9ad |
| ULSIF | 19.63 | Not recorded | 68fa5ee81e209131ce9e61fc |
| TCA | 19.5 | Not recorded | 68fa5ee81e209131ce9e61fc |
| KLIEP | 18.92 | Not recorded | 68fa5ee81e209131ce9e61fc |

### Neuro-HGLN

Accuracy: 28.56. Result ID: 699899f45698665ec4fc22c6.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":false}. This record does not assert independent reproduction.

### PGCN

Accuracy: 28.39. Result ID: 699899f45698665ec4fc22c3.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7e1e209131cea2e950.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":false}. This record does not assert independent reproduction.

### TANN

Accuracy: 28.32. Result ID: 699899f45698665ec4fc22c5.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68661e209131cea1bd2c.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":true}. This record does not assert independent reproduction.

### BiHDM

Accuracy: 28.27. Result ID: 698bbb0f7a967eddb770ed88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### RGNN

Accuracy: 27.95. Result ID: 699899f45698665ec4fc22c4.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa678f1e209131cea1702f.md>)

[Implementation](<https://github.com/zhongpeixiang/RGNN>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":true}. This record does not assert independent reproduction.

### BiDANN

Accuracy: 25.86. Result ID: 698bbb0f7a967eddb770ed87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### DGCNN

Accuracy: 25.12. Result ID: 698bbb0f7a967eddb770ed86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### DGCNN

Accuracy: 25.12. Result ID: 699899f45698665ec4fc22c2.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":false}. This record does not assert independent reproduction.

### A-LSTM

Accuracy: 24.06. Result ID: 698bbb0f7a967eddb770ed84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### DANN

Accuracy: 22.36. Result ID: 698bbb0f7a967eddb770ed85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627d1e209131ce9f988d.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### STM

Accuracy: 20.89. Result ID: 698bbb0f7a967eddb770ed7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### SA

Accuracy: 20.74. Result ID: 698bbb0f7a967eddb770ed82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)","Training Feature Subsample":3000}. This record does not assert independent reproduction.

### GFK

Accuracy: 20.27. Result ID: 698bbb0f7a967eddb770ed83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)","Training Feature Subsample":3000}. This record does not assert independent reproduction.

### SVM

Accuracy: 19.66. Result ID: 698bbb0f7a967eddb770ed80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### SVM

Accuracy: 19.66. Result ID: 699899f45698665ec4fc22c1.

[Reporting paper](<https://www.sota2.com/research/paper/6969c618e25ad2fa9d1ec9ad.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Subject-independent","Domain Adaptation":false}. This record does not assert independent reproduction.

### ULSIF

Accuracy: 19.63. Result ID: 698bbb0f7a967eddb770ed7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

### TCA

Accuracy: 19.5. Result ID: 698bbb0f7a967eddb770ed81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)","Training Feature Subsample":3000}. This record does not assert independent reproduction.

### KLIEP

Accuracy: 18.92. Result ID: 698bbb0f7a967eddb770ed7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e61fc.md>)

Recorded evaluation configuration: {"Protocol":"Subject-independent","Validation Strategy":"Leave-one-subject-out (LOSO)"}. This record does not assert independent reproduction.

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