核心矩阵协议 · 迁移到新被试

SSVEP · 4 通道（BETA）

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: 40 visual targets · 4 posterior electrodes
评测方式: 迁移到新被试
数据集: BETA
被试: 70
数据量: 11,200 trials · 7 participant-disjoint folds
输入: 4 channels selected from a 64-channel recording · 2-second windows
随机水平: 2.5%
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。

Standard CCA

57.6% (51.8%–63.5%)

Spectral ridge

48.2% (43.1%–53.3%)

LaBraM

12.9% (11.2%–14.6%)

CBraMod

27.6% (24.1%–31.3%)

EEGNet

44.1% (38.6%–49.6%)

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
Standard CCA经典方法	Known-frequency reference · no fitting	57.6%51.8%–63.5%	0.567Mean across held-out participants	4	70	1.1 s
Spectral ridge经典方法	Supervised fit	48.2%43.1%–53.3%	0.467Mean across held-out participants	4	70	0.7 s
LaBraM基础模型	Frozen encoder + ridge head	12.9%11.2%–14.6%	0.110Mean across held-out participants	4	70	2.5 s
CBraMod基础模型	Frozen encoder + ridge head	27.6%24.1%–31.3%	0.257Mean across held-out participants	4	70	3.0 s
EEGNet轻量模型	Scratch · 20 epochs	44.1%38.6%–49.6%	0.421Mean across held-out participants	4	70	146.7 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, 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

Near-floor scores are not ordered reliably between the 8- and 4-electrode subsets. Electrode subsets from laboratory recordings do not validate a physical low-channel cap. Prompted SSVEP does not measure idle false activations. Single-seed results; pretraining overlap unknown.

协议步骤

Seven participant-disjoint folds: train on 60 people, test on ten. All four blocks stay with their participant.
Two seconds from stimulus onset; no visual-latency shift. Source data were already zero-phase filtered. Additional 6–80 Hz filtering applies to each selected window separately.
Microvolt units are inferred from an independently documented loader, not explicitly stated in the author MAT description. Inconsistent phase metadata are unused by all methods.
Standard CCA uses known frequencies and three harmonics without training labels. Frozen encoders use training-only standardized ridge heads (alpha 100). EEGNet trains from scratch for 20 epochs with one seed (20260912).
Electrodes: POZ, O1, OZ, O2.
Uniform-guessing reference: 2.5%. Descriptive 95% intervals resample participants; training sets overlap across folds.
No cross-task overall ranking, model fine-tuning optimum or hardware benchmark is claimed.

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

Standard CCA：Trained from scratch / deterministic reference; no third-party pretrained weights. Braindecode BSD-3-Clause; MNE/scikit-learn BSD where used.
Spectral 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

BETA

署名 Bingchuan Liu et al. · BETA: A Large Benchmark Database Toward SSVEP-BCI Application (2020), doi:10.3389/fnins.2020.00627. Figshare 12264401 v3; mirror Bingchuan/BETA.

许可 CC BY 4.0 ↗

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 仅在本站声明的个人、以研究为主、非商业的运营方式下可以使用。任何广告、赞助、收费或以商业利益为目的的使用，都需要重新审查或取得许可。Eligible only under the stated personal, research-led, noncommercial operation. Any ads, sponsorship, fees, or use directed toward commercial advantage requires fresh review or permission.

权利审查于 2026-09-20 · 依据 figshare.com ↗ · doi.org ↗

复现记录

协议 ID: beta-ssvep-2s-posterior4and8-subject7fold-v1/posterior4
数据集版本: Hugging Face mirror of BETA database, Figshare record 12264401 v3 · mirror d4290c0200db8a104e0f557349dc49f90ba79506 · upstream Figshare version 3, 2022-06-15
硬件: Apple M5 / MPS and CPU
评分阶段总耗时: 153.9 s · 可能含加速器等待
审计记录 SHA-256: ccddf911864b8471f488e46cae45a3651369dae1134afcdeaede68bdfcc31950
汇总 SHA-256: 547a35763f7bca10a65c7b44c2f8c46af290159c692d237e92cd682fc21127a6
协议 SHA-256: dcd1d2bf4dbb46b7db8c4562623448633cde4641fa372c90f25ba9d84012c2f0

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 →