# 心算与静息（EEGMAT）

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: Serial subtraction versus resting EEG
- 评测方式: 迁移到新被试
- 数据集: [EEGMAT](https://bci.report/zh/datasets/eegmat/)
- 被试: 36
- 数据量: 2,160 epochs · 5 participant-disjoint folds
- 输入: 19 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。

**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: 56.8% (54.6%–58.9%)
- LaBraM: 64.6% (60.5%–68.6%)
- CBraMod: 62.3% (58.1%–66.5%)
- EEGNet: 67.6% (62.8%–72.5%)

| 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 | 56.8% (54.6%–58.9%) | 0.558 — Mean across held-out participants | 19 | 36 | 0.6 s |
| [LaBraM](https://bci.report/zh/methods/labram/) — 基础模型 | Frozen encoder + ridge head | 64.6% (60.5%–68.6%) | 0.620 — Mean across held-out participants | 19 | 36 | 2.1 s |
| [CBraMod](https://bci.report/zh/methods/cbramod/) — 基础模型 | Frozen encoder + ridge head | 62.3% (58.1%–66.5%) | 0.602 — Mean across held-out participants | 19 | 36 | 6.1 s |
| [EEGNet](https://bci.report/zh/methods/eegnet/) — 轻量模型 | Scratch · 20 epochs | 67.6% (62.8%–72.5%) 仅单个随机种子——为已运行种子中最高的一次（见「稳定性」） | 0.637 — Mean across held-out participants | 19 | 36 | 117.7 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](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/), 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

Thirty nonoverlapping 2-second windows from each of two conditions per person. Published signals were already cleaned with ICA; task performance groups are not evaluated.

### 协议步骤

- 5 participant-disjoint folds. All recordings from a person stay together. Each person contributes to the held-out predictions once.
- First 60 s of each recording; 30 contiguous nonoverlapping 2 s windows; exclude A2-A1 ear-difference and ECG; EDF physical volts converted to microvolts; subtract each channel's window mean; no rejection, filtering, resampling, or learned preprocessing.
- 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: pre-task-rest, mental-arithmetic.
- Uniform-guessing reference: 50.00%. Scores weight participants equally. Intervals describe participant variation; cross-validation training sets overlap.
- The benchmark detects condition (rest versus serial subtraction), not the good/bad count-quality participant grouping.
- Only the first documented 60 seconds is retained even though EDF containers are longer.
- The source README reports prior ICA artifact removal, so these are not untouched acquisition signals.
- Open Data Commons Attribution License v1.0 applies; retain PhysioNet attribution.
- EEGNet three-seed mean 67.52%; sample SD 0.14 percentage points; range 67.36–67.64%. Main table retains the original fixed seed; this is not a confidence interval.

### 稳定性

EEGNet three-seed mean 67.52%; sample SD 0.14 percentage points; range 67.36–67.64%. Main table retains the original fixed seed; this is not a confidence interval.

EEGNet 各随机种子的结果： 67.64% · 67.55% · 67.36%；均值 67.52%

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 67.52%; sample SD 0.14 percentage points; range 67.36–67.64%. 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.
- **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

### EEGMAT

**署名** Igor Zyma, Ivan Seleznov, Anton Popov, Mariia Chernykh, Oleksii Shpenkov · EEG During Mental Arithmetic Tasks 1.0.0, PhysioNet, doi:10.13026/C2JQ1P. Study: Zyma et al. (2019), doi:10.3390/data4010014. PhysioNet platform: Pollard et al. (2026), doi:10.1038/s44360-026-00096-z.

**许可** [Open Data Commons Attribution License 1.0 ↗](https://opendatacommons.org/licenses/by/1-0/)

[数据集记录 ↗](https://physionet.org/content/eegmat/1.0.0/) · [这个数据集上的全部结果 →](https://bci.report/zh/datasets/eegmat/)

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/arithmetic-rest-protocol.json)

**公开数据登记说明** 署名许可与该研究专属的伦理批准、同意书都有记录；可以使用的前提是只输出聚合结果，并排除被试信息字段。 Attribution license and study-specific approval/consent are documented; eligibility assumes aggregate-only output and exclusion of subject-info fields.

**权利审查于** 2026-09-20 · 依据 [physionet.org ↗](https://physionet.org/content/eegmat/1.0.0/) · [www.mdpi.com ↗](https://www.mdpi.com/2306-5729/4/1/14) · [opendatacommons.org ↗](https://opendatacommons.org/licenses/by/1-0/)

## 复现记录

- 协议 ID: `parallel-fixed-subject-folds-v1/physionet-eegmat-1.0.0`
- 数据集版本: PhysioNet EEG During Mental Arithmetic Tasks 1.0.0 · 1.0.0
- 硬件: Apple M5 / MPS
- 评分阶段总耗时: 126.5 s · 可能含加速器等待
- 审计记录 SHA-256: `2d0e4cec78c8d6e5bfc9f5390ba161f4308759e02feffbb8645d6983d9093292`
- 汇总 SHA-256: `ab607e749da1eedcf88441c5b6fd0db55e2ebae0bbd91d6d18e508605eef625b`
- 协议 SHA-256: `5d53ccbd5a00763908162f0b700c0a3236e0d4f9d43b08e42ee31a2ef01aefbf`

## 下载

- [结果 · CSV ↓](https://bci.report/data/arithmetic-rest-results.csv)
- [协议 · JSON ↓](https://bci.report/data/arithmetic-rest-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/)
- [P300 目标 ERP（ds006593）](https://bci.report/zh/protocols/p300-target/)
- [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/arithmetic-rest/ 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）。