核心矩阵协议 · 迁移到新被试

运动想象与静息（ds003810）

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: Rest versus right-hand imagery
评测方式: 迁移到新被试
数据集: ds003810
被试: 10
数据量: 1,200 epochs · 5 participant-disjoint folds
输入: 15 channels · 2-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

54.9% (53.2%–56.7%)

CSP+LDA

47.1% (43.8%–50.2%)

LaBraM

53.5% (51.4%–55.4%)

CBraMod

62.9% (59.6%–66.5%)

EEGNet

71.0% (65.0%–76.3%)

平衡准确率，本协议下的每一种方法。 点为估计值，横线为描述性 95% 区间，虚线为随机水平。

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	54.9%53.2%–56.7%	0.544Mean across held-out participants	15	10	0.2 s
CSP+LDA经典方法	Supervised fit	47.1%43.8%–50.2%不高于随机水平	0.406Mean across held-out participants	15	10	8.8 s
LaBraM基础模型	Frozen encoder + ridge head	53.5%51.4%–55.4%	0.509Mean across held-out participants	15	10	2.2 s
CBraMod基础模型	Frozen encoder + ridge head	62.9%59.6%–66.5%	0.617Mean across held-out participants	15	10	5.0 s
EEGNet轻量模型	Scratch · 20 epochs	71.0%65.0%–76.3%仅单个随机种子——为已运行种子中最高的一次（见「稳定性」）	0.680Mean across held-out participants	15	10	55.5 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： ShallowFBCSPNet, Deep4Net, Standard CCA, Temporal ridge。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

Ten-person laboratory task with prompted rest. This is not continuous-idle monitoring or a physical low-channel headset test.

协议步骤

5 participant-disjoint folds. All recordings from a person stay together. Each person contributes to the held-out predictions once.
epoching: two seconds from the class annotation onset; amplitude: converted to microvolts according to source calibration, then per-channel epoch mean removed; resampling: none; native sampling rate retained; selection: natural file/event order; when over the cap, retain 60 evenly spaced event indices per participant/class; source_units: Microv declared by BIDS channels.tsv; EDF physical dimension is absent, so MNE returns the source numeric microvolt values without SI scaling
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: rest, right_hand_imagery.
Uniform-guessing reference: 50.00%. Scores weight participants equally. Intervals describe participant variation; cross-validation training sets overlap.
run 0 is real dominant-hand movement and is excluded; only imagery runs 1-4 contribute
the source reports online 0.5-45 Hz filtering
controlled cue-locked laboratory windows; this does not measure continuous false activations
foundation-model pretraining overlap is unknown
EEGNet three-seed mean 69.47%; sample SD 1.43 percentage points; range 68.17–71.00%. Main table retains the original fixed seed; this is not a confidence interval.

稳定性

EEGNet three-seed mean 69.47%; sample SD 1.43 percentage points; range 68.17–71.00%. Main table retains the original fixed seed; this is not a confidence interval.

EEGNet 各随机种子的结果： 71.00% · 69.25% · 68.17%；均值 69.47%

Same participants, folds, preprocessing and 20-epoch budget. Three seeds measure initialization variability, not population uncertainty. Main table retains its preselected seed; no best-seed selection.

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.
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. EEGNet three-seed mean 69.47%; sample SD 1.43 percentage points; range 68.17–71.00%. Main table retains the original fixed seed; this is not a confidence interval.

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.
CSP+LDA：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

ds003810

署名 Peterson et al. · OpenNeuro ds003810, version 2.0.2. Study: https://pmc.ncbi.nlm.nih.gov/articles/PMC9114495/

数据集作者要求引用： Peterson V, Galván C, Hernández H, Spies R. A feasibility study of a complete low-cost consumer-grade brain-computer interface system. Heliyon 6(3):e03425 (2020). doi ↗ · 数据集记录中的要求 ↗

许可 CC0-1.0 ↗

数据集记录 ↗ · 这个数据集上的全部结果 →

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。

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 CC0 快照明确，另有该数据集专属的伦理批准与签署同意书证据；只发布聚合结果，明显限制了隐私暴露。Clear CC0 snapshot plus dataset-specific ethics and signed-consent evidence; aggregate-only publication materially limits privacy exposure.

权利审查于 2026-09-20 · 依据 doi.org ↗ · pmc.ncbi.nlm.nih.gov ↗

已登记的更正 · 2026-10-01：ds003810 的署名只链接了 2022 年的 Data in Brief 数据描述。OpenNeuro 记录要求引用 Peterson、Galván、Hernández 与 Spies 发表于 Heliyon 6(3):e03425（2020）的论文；数据集页面现在两者都给出。更正登记册 →

复现记录

协议 ID: parallel-fixed-subject-folds-v1/ds003810
数据集版本: OpenNeuro snapshot 2.0.2 · c674303319303b9ffc4ff7e2340b3a4807e8ffb5
硬件: Apple M5 / MPS
评分阶段总耗时: 71.7 s · 可能含加速器等待
审计记录 SHA-256: e762cf7f048bf2df47b9399b9df6171733a93c162ce7800560952df30491a7f2
汇总 SHA-256: 0dd66f4bd4d083fca1d1ab44a2d2951d57f6d19378079b8cb5ff3ee9241f0cda
协议 SHA-256: 57ddb7692e3bb248b95c4e81b6aa02e7c8b19d774ed4a8b799c811b6ef3b65a2

下载

结果 · CSV ↓协议 · JSON ↓核心矩阵 · JSON ↓

其他协议

全部协议 → · 首页上的核心矩阵 → · 全部数据集 → · 全部方法 →