BCI Reportds006593
署名 OpenNeuro ds006593 contributors · version 1.0.0, doi:10.18112/openneuro.ds006593.v1.0.0; original author credits retained at the linked source.
许可 CC0-1.0 ↗
BCI Report 不转发任何记录。这些是 BCI Report 在上述许可下计算的聚合测量；数据归属于署名中的作者。
核心矩阵协议 · 迁移到新被试
P300 目标 ERP（ds006593）
下面这些分数是怎么来的——队列、数据划分、电极、时间窗、每种方法允许学什么、随机猜测能得多少分——都按已发布的协议文件给出。只在本协议内部比较分数。
协议步骤、局限说明、方法备注与数据集署名来自发布数据本身，保持英文原文——它们随数据一起被审核，翻译会让网页与可下载文件不再一致。
协议概览
- 任务
- Visual target versus nontarget events
- 评测方式
- 迁移到新被试
- 数据集
- ds006593
- 被试
- 21
- 数据量
- 2,520 epochs · 5 participant-disjoint folds
- 输入
- 19 channels · 1-second windows
- 随机水平
- 50.0%
- 指标
- 平衡准确率（主指标）· 宏平均 F1（次指标）
结果
在本协议下运行过的每一种方法，以及已发布结果文件中记录的分数。只在这张表内纵向比较：其他协议在队列、电极、时间窗或随机水平上有所不同。
Spectral ridge
51.0% (49.6%–52.4%)
Temporal ridge
53.8% (51.9%–55.6%)
LaBraM
49.4% (47.7%–51.2%)
CBraMod
55.0% (53.3%–56.7%)
EEGNet
53.3% (51.7%–54.9%)
| 方法 | 训练方式 | 平衡准确率 | 宏平均 F1 | 通道 | 被试 | 评分耗时 |
|---|---|---|---|---|---|---|
| Spectral ridge经典方法 | Supervised fit | 51.0%49.6%–52.4%区间触及随机水平 | 0.505Mean across held-out participants | 19 | 21 | 0.4 s |
| Temporal ridge经典方法 | Supervised fit | 53.8%51.9%–55.6% | 0.520Mean across held-out participants | 19 | 21 | 0.5 s |
| LaBraM基础模型 | Frozen encoder + ridge head | 49.4%47.7%–51.2%不高于随机水平 | 0.486Mean across held-out participants | 19 | 21 | 10.6 s |
| CBraMod基础模型 | Frozen encoder + ridge head | 55.0%53.3%–56.7% | 0.529Mean across held-out participants | 19 | 21 | 4.8 s |
| EEGNet轻量模型 | Scratch · 20 epochs | 53.3%51.7%–54.9% | 0.500Mean across held-out participants | 19 | 21 | 45.6 s |
评分耗时包括拟合与预测，可能含加速器等待时间，不含数据准备。它只对该配置有效，不是硬件基准。
未在本协议下运行： CSP+LDA, ShallowFBCSPNet, Deep4Net, Standard CCA。这里缺少的方法只是没有在本协议上运行——不是失败。
谨慎解读
Balanced target/nontarget sample changes the source 1:9 prevalence. One-second windows include later flashes at 0.3-second intervals; this is not an online speller estimate.
协议步骤
- 5 participant-disjoint folds. All recordings from a person stay together. Each person contributes to the held-out predictions once.
- units: microvolts; epoch: [stimulus onset, onset + 1.0 s); filtering: none added
- One fixed seed (20260919); no early stopping or test-based tuning. EEGNet trains for 20 epochs per fold. Frozen encoders use training-only standardized ridge heads (alpha 100).
- Labels: nontarget, target.
- Uniform-guessing reference: 50.00%. Scores weight participants equally. Intervals describe participant variation; cross-validation training sets overlap.
- Research subset with fixed deterministic sampling capped at 60 epochs per participant/class.
- The cap balances target and nontarget and therefore changes the original approximately 1:9 class prevalence.
- Stimuli were presented about every 0.3 s, so each 1 s epoch contains responses to later stimuli; this is intrinsic next-stimulus contamination.
稳定性
One fixed seed and training budget; multi-seed sensitivity pending.
是否出现在预训练数据中
Unknown unless explicitly documented; no unseen-pretraining claim.
方法说明
- One fixed configuration. Foundation encoders remain frozen; small networks train from scratch. These scores do not establish optimal fine-tuned performance. No individual predictions or participant-level results are distributed.
模型条款
- Spectral ridge：Trained from scratch / deterministic reference; no third-party pretrained weights. Braindecode BSD-3-Clause; MNE/scikit-learn BSD where used.
- Temporal ridge：Trained from scratch / deterministic reference; no third-party pretrained weights. Braindecode BSD-3-Clause; MNE/scikit-learn BSD where used.
- LaBraM：Code/repository: MIT · Checkpoint: committed in that repository; no separate weight terms
- CBraMod：Code: MIT · Weights: Apache-2.0 (official model card)
- EEGNet：Trained from scratch / deterministic reference; no third-party pretrained weights. Braindecode BSD-3-Clause; MNE/scikit-learn BSD where used.
来源与许可
许可范围 Personal noncommercial research; aggregate results only
隐私 这里只发布队列级聚合结果：不发布任何记录、被试编号或逐人分数。 完整的审查说明在协议 JSON 中 ↓
公开数据登记说明 锁定的 CC0 版本，有该数据集专属的 IRB 批准与同意书证据，元数据暴露相对较少。Pinned CC0 release with dataset-specific IRB and consent evidence and comparatively low metadata exposure.
权利审查于 · 依据 doi.org ↗ · nemar.org ↗
复现记录
- 协议 ID
parallel-fixed-subject-folds-v1/ds006593- 数据集版本
- OpenNeuro snapshot 1.0.0 · b3fa345b310abfcf442dd4e2867f6652336c3fe4
- 硬件
- Local Ubuntu / CUDA
- 评分阶段总耗时
- 61.9 s · 可能含加速器等待
- 审计记录 SHA-256
30762120c57bede9f47d2e96637656e8948fca458016f7f2e3a39f951a357716- 汇总 SHA-256
a63a7ba5bbd6dd7865ae260b707c2db896136646a910d96516fa5c862e1146c0- 协议 SHA-256
bf6796dfe04dffa57bdd08933d2bb743722da71594135f04fa4fc33f3fb7dd46
下载
其他协议
- 运动想象与静息（ds003810）
- 空闲与指令（ds005342）
- SSVEP · 8 通道（BETA）
- SSVEP · 4 通道（BETA）
- 心算与静息（EEGMAT）
- 语义目标 ERP（TMNRED / ds005383）
- 睡眠分期（EESM19 scalp subset）
全部协议 → · 首页上的核心矩阵 → · 全部数据集 → · 全部方法 →