# EEG Classification on PhysioNet-MI 4-Class 9,837 Samples Source: [EEG Classification on PhysioNet-MI 4-Class 9,837 Samples]() Collection index: [llms.txt]() Data updated: 2026-07-07T09:31:44.575Z Evaluation of EEG signal classification performance on the specific 4-class subset of the PhysioNet Motor Imagery dataset (9,837 samples), reporting Balanced Accuracy, Cohen’s Kappa, and Weighted F1. 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 Classification | | Dataset (including any stated split) | PhysioNet-MI 4-Class 9,837 Samples | | Metric | Balanced Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Balanced Accuracy](): Higher is better; unit: PERCENT. - [Cohen’s Kappa](): Higher is better; unit: SCALAR. - [Weighted F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Balanced Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CBraMod | 63.05 | Not recorded | 691aac5c6750be83fe5ce65e | | LaBraM | 61.73 | Not recorded | 691aac5c6750be83fe5ce65e | | STAMP | 60.98 | Not recorded | 691aac5c6750be83fe5ce65e | | EEG Conformer | 60.49 | Not recorded | 691aac5c6750be83fe5ce65e | | ST-Transformer | 60.35 | Not recorded | 691aac5c6750be83fe5ce65e | | NeuroOnline\*\*\* | 49.52 | Not recorded | 6a4c880a85dba69fef8b271c | | off-FT-LIN | 45.38 | Not recorded | 6a4c880a85dba69fef8b271c | | off-FT-MLP | 43.79 | Not recorded | 6a4c880a85dba69fef8b271c | | NeuroOnline.a | 42.82 | Not recorded | 6a4c880a85dba69fef8b271c | | off-LoRA-LIN | 38.56 | Not recorded | 6a4c880a85dba69fef8b271c | | off-LoRA-MLP | 36.88 | Not recorded | 6a4c880a85dba69fef8b271c | ### CBraMod Balanced Accuracy: 63.05. Result ID: 69fc5f6e47f34ce924df80ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"46M"}. This record does not assert independent reproduction. ### LaBraM Balanced Accuracy: 61.73. Result ID: 69fc5f6e47f34ce924df80ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"5.8M"}. This record does not assert independent reproduction. ### STAMP Balanced Accuracy: 60.98. Result ID: 69fc5f6e47f34ce924df80ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"0.78M"}. This record does not assert independent reproduction. ### EEG Conformer Balanced Accuracy: 60.49. Result ID: 69fc5f6e47f34ce924df80eb. [Reporting paper]() Recorded evaluation configuration: {"#Params":"0.55M"}. This record does not assert independent reproduction. ### ST-Transformer Balanced Accuracy: 60.35. Result ID: 69fc5f6e47f34ce924df80ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"3.5M"}. This record does not assert independent reproduction. ### NeuroOnline\*\*\* Balanced Accuracy: 49.52. Result ID: 6a4cc76860b88bb339c99de7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Foundation Model":"BIOT"}. This record does not assert independent reproduction. ### off-FT-LIN Balanced Accuracy: 45.38. Result ID: 6a4cc76860b88bb339c99de4. [Reporting paper]() Recorded evaluation configuration: {"Foundation Model":"BIOT","Adaptation Strategy":"Fine-Tuning","Classifier Head":"LIN"}. This record does not assert independent reproduction. ### off-FT-MLP Balanced Accuracy: 43.79. Result ID: 6a4cc76860b88bb339c99de5. [Reporting paper]() Recorded evaluation configuration: {"Foundation Model":"BIOT","Adaptation Strategy":"Fine-Tuning","Classifier Head":"MLP"}. This record does not assert independent reproduction. ### NeuroOnline.a Balanced Accuracy: 42.82. Result ID: 6a4cc76860b88bb339c99de6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Foundation Model":"BIOT"}. This record does not assert independent reproduction. ### off-LoRA-LIN Balanced Accuracy: 38.56. Result ID: 6a4cc76860b88bb339c99de2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Foundation Model":"BIOT","Adaptation Strategy":"LoRA","Classifier Head":"LIN"}. This record does not assert independent reproduction. ### off-LoRA-MLP Balanced Accuracy: 36.88. Result ID: 6a4cc76860b88bb339c99de3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Foundation Model":"BIOT","Adaptation Strategy":"LoRA","Classifier Head":"MLP"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.