# Motor Imagery Decoding on BCI Competition IV 2a I (cross-subject) Source: [Motor Imagery Decoding on BCI Competition IV 2a I (cross-subject)]() Collection index: [llms.txt]() Data updated: 2026-06-02T12:22:10.198Z Evaluation of Motor Imagery Decoding performance on the BCI Competition IV Dataset 2a, specifically using the cross-subject protocol (Set I), reporting per-class accuracies and Kappa statistics. 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 | Motor Imagery Decoding | | Dataset (including any stated split) | BCI Competition IV 2a I (cross-subject) | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Accuracy Class 1](): Higher is better; unit: PERCENT. - [Accuracy Class 2](): Higher is better; unit: PERCENT. - [Accuracy Class 3](): Higher is better; unit: PERCENT. - [Accuracy Class 4](): Higher is better; unit: PERCENT. - [Accuracy Class 5](): Higher is better; unit: PERCENT. - [Accuracy Class 6](): Higher is better; unit: PERCENT. - [Accuracy Class 7](): Higher is better; unit: PERCENT. - [Accuracy Class 8](): Higher is better; unit: PERCENT. - [Accuracy Class 9](): Higher is better; unit: PERCENT. - [Kappa Statistic](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BFM-MSDA | 86.17 | Not recorded | 68fa7a4b1e209131cea8244a | | DJDAN | 84.18 | Not recorded | 68fa7a4b1e209131cea8244a | | DJP-MMD | 84.11 | Not recorded | 68fa7a4b1e209131cea8244a | | GAT | 83.81 | Not recorded | 68fa7a4b1e209131cea8244a | | JAN | 83.21 | Not recorded | 68fa7a4b1e209131cea8244a | | ASJDA | 83.02 | Not recorded | 68fa7a4b1e209131cea8244a | | Conformer | 80.75 | Not recorded | 68fa7a4b1e209131cea8244a | | ShallowConvNet | 80.15 | Not recorded | 68fa7a4b1e209131cea8244a | | EEGNet | 77.93 | Not recorded | 68fa7a4b1e209131cea8244a | | EVA-Net | 71.25 | Not recorded | 6a1e643bdbd7150506f858a6 | | CBraMod w/ Linear | 67.92 | Not recorded | 68fa7a4b1e209131cea8244a | | EEGCCT | 67.9 | Not recorded | 6a1e643bdbd7150506f858a6 | | LaBraM w/ Linear | 64.77 | Not recorded | 68fa7a4b1e209131cea8244a | | MSVTNet | 64.1 | Not recorded | 6a1e643bdbd7150506f858a6 | | EEGNet | 63.44 | Not recorded | 6a1e643bdbd7150506f858a6 | | EEG Conformer | 60.7 | Not recorded | 6a1e643bdbd7150506f858a6 | | ShallowConvNet | 59.43 | Not recorded | 6a1e643bdbd7150506f858a6 | ### BFM-MSDA Average Accuracy: 86.17. Result ID: 69c54d9247f34ce924af7ac7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### DJDAN Average Accuracy: 84.18. Result ID: 69c54d9247f34ce924af7ac4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### DJP-MMD Average Accuracy: 84.11. Result ID: 69c54d9247f34ce924af7ac1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### GAT Average Accuracy: 83.81. Result ID: 69c54d9247f34ce924af7ac2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### JAN Average Accuracy: 83.21. Result ID: 69c54d9247f34ce924af7ac0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### ASJDA Average Accuracy: 83.02. Result ID: 69c54d9247f34ce924af7ac3. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### Conformer Average Accuracy: 80.75. Result ID: 69c54d9247f34ce924af7abf. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### ShallowConvNet Average Accuracy: 80.15. Result ID: 69c54d9247f34ce924af7abe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### EEGNet Average Accuracy: 77.93. Result ID: 69c54d9247f34ce924af7abd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### EVA-Net Average Accuracy: 71.25. Result ID: 6a1ecae0fbc373592c1a6c95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. ### CBraMod w/ Linear Average Accuracy: 67.92. Result ID: 69c54d9247f34ce924af7ac6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### EEGCCT Average Accuracy: 67.9. Result ID: 6a1ecae0fbc373592c1a6c92. [Reporting paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. ### LaBraM w/ Linear Average Accuracy: 64.77. Result ID: 69c54d9247f34ce924af7ac5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Cross-subject"}. This record does not assert independent reproduction. ### MSVTNet Average Accuracy: 64.1. Result ID: 6a1ecae0fbc373592c1a6c94. [Reporting paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. ### EEGNet Average Accuracy: 63.44. Result ID: 6a1ecae0fbc373592c1a6c90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. ### EEG Conformer Average Accuracy: 60.7. Result ID: 6a1ecae0fbc373592c1a6c93. [Reporting paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. ### ShallowConvNet Average Accuracy: 59.43. Result ID: 6a1ecae0fbc373592c1a6c91. [Reporting paper]() Recorded evaluation configuration: {"Setting":"subject-independent"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.