# P300 目标 ERP（ds006593）

核心矩阵协议 · 迁移到新被试

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](https://bci.report/zh/datasets/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。

**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。

- 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 | 0.505 — Mean across held-out participants | 19 | 21 | 0.4 s |
| Temporal ridge — 经典方法 | Supervised fit | 53.8% (51.9%–55.6%) | 0.520 — Mean across held-out participants | 19 | 21 | 0.5 s |
| [LaBraM](https://bci.report/zh/methods/labram/) — 基础模型 | Frozen encoder + ridge head | 49.4% (47.7%–51.2%) 不高于随机水平 | 0.486 — Mean across held-out participants | 19 | 21 | 10.6 s |
| [CBraMod](https://bci.report/zh/methods/cbramod/) — 基础模型 | Frozen encoder + ridge head | 55.0% (53.3%–56.7%) | 0.529 — Mean across held-out participants | 19 | 21 | 4.8 s |
| [EEGNet](https://bci.report/zh/methods/eegnet/) — 轻量模型 | Scratch · 20 epochs | 53.3% (51.7%–54.9%) | 0.500 — Mean 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](https://bci.report/zh/methods/csp-lda/), [ShallowFBCSPNet](https://bci.report/zh/methods/shallowfbcspnet/), [Deep4Net](https://bci.report/zh/methods/deep4net/), [Standard CCA](https://bci.report/zh/methods/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

### ds006593

**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 ↗](https://creativecommons.org/publicdomain/zero/1.0/)

[数据集记录 ↗](https://doi.org/10.18112/openneuro.ds006593.v1.0.0) · [这个数据集上的全部结果 →](https://bci.report/zh/datasets/ds006593/)

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 ↓](https://bci.report/data/p300-target-protocol.json)

**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** 2026-09-20 · 依据 [doi.org ↗](https://doi.org/10.18112/openneuro.ds006593.v1.0.0) · [nemar.org ↗](https://nemar.org/dataset/on006593)

## 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

- [结果 · CSV ↓](https://bci.report/data/p300-target-results.csv)
- [协议 · JSON ↓](https://bci.report/data/p300-target-protocol.json)
- [核心矩阵 · JSON ↓](https://bci.report/data/experiments.json)

### 其他协议

- [运动想象与静息（ds003810）](https://bci.report/zh/protocols/mi-rest/)
- [空闲与指令（ds005342）](https://bci.report/zh/protocols/idle/)
- [SSVEP · 8 通道（BETA）](https://bci.report/zh/protocols/beta-8ch/)
- [SSVEP · 4 通道（BETA）](https://bci.report/zh/protocols/beta-4ch/)
- [心算与静息（EEGMAT）](https://bci.report/zh/protocols/arithmetic-rest/)
- [语义目标 ERP（TMNRED / ds005383）](https://bci.report/zh/protocols/semantic-target/)
- [睡眠分期（EESM19 scalp subset）](https://bci.report/zh/protocols/sleep-scalp/)

[全部协议 →](https://bci.report/zh/protocols/) · [首页上的核心矩阵 →](https://bci.report/zh/#overview) · [全部数据集 →](https://bci.report/zh/datasets/) · [全部方法 →](https://bci.report/zh/methods/)

---
本文是 https://bci.report/zh/protocols/p300-target/ 的 Markdown 版本，由已发布的网页生成。数字均为聚合结果；使用条款见 https://bci.report/data-use/（英文）。