交互式方法探索
在七个协议上探索解码方法如何分化
这里没有单一总分。通过去除整体水平后的二维方法轮廓图、任意双协议散点图、七协议一致性矩阵与两两配对对比器,直接观察方法在不同 EEG 范式间的行为模式与不确定性。
视图一 · 去除整体水平的二维轮廓映射
二维方法轮廓图
先将 7 个准确率协议分别标准化,再减去每个方法自身的七协议均值,从而彻底去除整体高低,只保留方法在不同任务间的相对行为形状。距离越近,表示跨范式的相对强弱模式越相似。
- 完整覆盖方法
- 27 另 9 个部分覆盖
- 二维保留方差
- 69.5% 轴 1:45.1% · 轴 2:24.4%
- 距离相关 r
- 0.92 2D 与真实 7D 轮廓距离
- 3-近邻保留率
- 53.1% 200 次区间重采样
轮廓较平的方法(空心点): 以下方法的跨协议相对波动小于其 95% 区间重采样标准差的 1.5 倍,因此在二维轮廓图上的具体落点参考意义较弱: ERP-FM Base、LaBraM at Scale Molecule-L、LaBraM at Scale Quark-L、REVE Large.
部分覆盖方法(未纳入七协议轮廓图,共 9 个): 本图不做缺失值填补。下列仅在部分协议上评测的方法保留在下方的双协议散点图与两两协议对比器中: BrainOmni Base (5/7)、CSP+LDA (5/7)、FBCCA (2/7)、MDM (2/7)、Standard CCA (2/7)、Temporal ridge (2/7)、TS+LR (2/7)、xDAWN+LDA (2/7)、XDAWNCov+TS+LR (2/7).
查看完整轮廓坐标与七协议原始分数表(27 个完整方法 + 9 个部分覆盖方法)
| 方法 | 类别 | 轴 1 | 轴 2 | 3-近邻保留 | 轮廓状态 | 运动想象 | BETA 8通道 | BETA 4通道 | 心算负荷 | P300 ERP | 语义 ERP | 睡眠分期 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BrainOmni Base | 基础模型 | — | — | — | 5/7 | 58.8%57.0–60.8% | 21.7%18.6–25.0% | 13.0%10.6–15.6% | 61.6%58.4–64.9% | — | — | 67.7%65.8–69.5% |
| CBraMod | 基础模型 | −0.15 | +0.05 | 1/3 | 清晰 | 62.9%59.6–66.5% | 33.7%29.8–37.6% | 27.6%24.1–31.3% | 62.3%58.1–66.5% | 55.0%53.3–56.7% | 55.8%54.2–57.4% | 71.3%68.7–73.7% |
| CodeBrain | 基础模型 | −0.96 | −0.78 | 1/3 | 清晰 | 58.8%54.5–62.6% | 11.9%10.5–13.3% | 11.2%9.8–12.7% | 63.0%59.5–66.5% | 50.8%49.3–52.2% | 54.7%53.0–56.6% | 70.7%68.8–72.7% |
| eeg-fm-masking MAE (r=9 cm, L=2) | 基础模型 | +1.35 | +1.70 | 2/3 | 清晰 | 68.1%64.3–72.3% | 54.8%49.4–60.0% | 47.1%42.1–52.1% | 63.6%59.1–68.1% | 49.5%48.1–51.0% | 54.8%52.7–56.9% | 67.9%65.4–70.4% |
| EEGMamba | 基础模型 | +1.02 | +0.88 | 2/3 | 清晰 | 67.3%63.6–70.6% | 40.2%35.7–44.7% | 32.7%28.9–36.7% | 60.3%57.0–63.4% | 52.5%51.4–53.5% | 54.4%52.5–56.3% | 64.1%61.6–66.4% |
| EEGPT | 基础模型 | −1.54 | −0.45 | 1/3 | 清晰 | 58.3%54.9–61.8% | 20.3%18.2–22.6% | 17.3%15.5–19.2% | 65.7%60.9–70.3% | 54.0%51.5–56.6% | 54.6%53.3–55.9% | 75.5%73.9–77.1% |
| ERP-FM Base | 基础模型 | −1.02 | +0.37 | 1/3 | 较平 | 54.8%51.8–57.8% | 18.4%16.3–20.5% | 20.9%18.4–23.5% | 61.1%57.3–65.1% | 51.2%49.3–53.2% | 53.3%51.7–54.8% | 71.0%69.5–72.6% |
| LaBraM | 基础模型 | −1.49 | −0.25 | 1/3 | 清晰 | 53.5%51.4–55.4% | 10.8%9.5–12.2% | 12.9%11.2–14.6% | 64.6%60.5–68.6% | 49.4%47.7–51.2% | 53.2%51.3–54.9% | 71.1%69.0–73.2% |
| LaBraM at Scale Atom-L | 基础模型 | −1.39 | +0.62 | 2/3 | 清晰 | 56.9%53.3–61.0% | 25.8%22.4–29.4% | 28.0%24.3–31.8% | 67.5%63.7–71.3% | 53.2%51.5–54.9% | 52.8%51.3–54.3% | 72.7%70.6–74.4% |
| LaBraM at Scale Molecule-L | 基础模型 | −0.52 | +0.32 | 1/3 | 较平 | 59.6%57.2–61.4% | 26.6%22.9–30.5% | 28.9%25.1–33.0% | 63.9%59.9–68.0% | 51.4%49.2–53.5% | 54.7%52.9–56.5% | 71.9%70.2–73.4% |
| LaBraM at Scale Quark-B | 基础模型 | −0.31 | −0.02 | 1/3 | 清晰 | 61.9%59.1–64.4% | 27.4%23.6–31.5% | 27.8%24.0–31.9% | 66.0%62.0–70.0% | 49.6%48.5–50.6% | 55.4%53.1–57.8% | 72.1%70.3–74.0% |
| LaBraM at Scale Quark-G | 基础模型 | −0.21 | +1.24 | 1/3 | 清晰 | 58.7%57.3–60.1% | 25.0%21.3–28.8% | 26.8%22.8–31.1% | 59.4%56.9–61.7% | 50.3%48.5–52.1% | 51.8%50.1–53.4% | 67.3%65.6–68.9% |
| LaBraM at Scale Quark-H | 基础模型 | −1.06 | +0.81 | 2/3 | 清晰 | 60.2%57.4–62.9% | 23.7%20.2–27.3% | 26.2%22.3–30.3% | 64.5%60.6–68.3% | 52.6%51.1–54.1% | 52.2%50.3–53.9% | 72.9%71.5–74.2% |
| LaBraM at Scale Quark-L | 基础模型 | −0.37 | +0.25 | 2/3 | 较平 | 59.6%56.3–62.9% | 27.1%23.3–31.0% | 28.0%24.0–32.2% | 63.8%59.8–67.8% | 51.0%49.4–52.6% | 54.8%53.0–56.6% | 70.3%68.0–72.5% |
| LUNA Base | 基础模型 | −0.69 | −1.14 | 2/3 | 清晰 | 52.6%50.2–54.9% | 8.6%7.7–9.5% | 9.0%8.1–10.1% | 60.7%56.9–64.4% | 48.7%46.3–51.1% | 56.2%54.2–58.2% | 67.5%65.3–69.5% |
| LUNA Large | 基础模型 | −0.86 | −0.97 | 3/3 | 清晰 | 49.9%46.6–53.5% | 10.0%8.9–11.1% | 11.2%9.8–12.6% | 57.4%54.3–60.6% | 48.8%46.9–50.8% | 57.1%55.3–58.9% | 72.4%70.4–74.0% |
| REVE Base | 基础模型 | −0.54 | +0.43 | 1/3 | 清晰 | 66.2%61.8–70.6% | 37.5%33.3–41.9% | 25.5%22.4–28.8% | 68.8%64.1–73.2% | 50.5%48.5–52.3% | 53.7%51.8–55.4% | 74.6%72.9–76.4% |
| REVE Large | 基础模型 | +0.55 | −0.05 | 1/3 | 较平 | 70.2%64.0–76.1% | 52.7%47.7–57.8% | 46.4%41.7–51.2% | 69.0%63.3–74.7% | 54.6%52.7–56.5% | 59.7%57.5–61.8% | 76.6%75.2–78.0% |
| REVE Small | 基础模型 | +0.39 | +0.12 | 2/3 | 清晰 | 61.5%58.3–64.8% | 39.3%35.2–43.6% | 35.9%32.0–40.0% | 65.2%60.5–70.0% | 54.3%52.9–55.9% | 56.7%54.5–59.0% | 64.5%62.5–66.6% |
| SingLEM | 基础模型 | +4.15 | −1.14 | 2/3 | 清晰 | 72.0%66.6–76.6% | 26.6%23.7–29.5% | 20.5%17.8–23.3% | 51.5%49.2–53.8% | 51.2%49.2–53.1% | 58.5%56.1–61.1% | 35.3%33.7–37.0% |
| ST-EEGFormer Base | 基础模型 | −1.58 | −0.44 | 2/3 | 清晰 | 58.1%53.7–63.3% | 17.1%15.5–18.8% | 17.5%15.8–19.3% | 64.5%59.0–70.0% | 53.6%52.3–54.8% | 54.6%52.9–56.4% | 77.3%75.6–78.8% |
| ST-EEGFormer Large | 基础模型 | −0.81 | −0.91 | 2/3 | 清晰 | 62.4%57.4–67.8% | 22.6%20.1–25.3% | 22.4%19.9–25.0% | 63.4%57.8–69.0% | 52.7%51.3–54.2% | 57.8%56.0–59.6% | 79.6%78.2–81.0% |
| ZUNA 1.1 | 基础模型 | −0.17 | −0.17 | 1/3 | 清晰 | 50.7%49.2–52.1% | 11.9%10.8–13.0% | 8.4%7.5–9.4% | 53.3%49.5–57.1% | 51.6%50.3–53.0% | 53.9%52.2–55.6% | 60.1%57.8–62.3% |
| Deep4Net | 轻量神经网络 | +3.20 | +0.35 | 2/3 | 清晰 | 68.6%63.3–74.0% | 52.8%47.3–58.2% | 38.7%33.7–43.8% | 61.3%57.5–65.2% | 50.8%50.0–51.6% | 57.4%55.4–59.5% | 45.2%42.7–47.7% |
| EEGNet | 轻量神经网络 | +2.50 | −0.78 | 1/3 | 清晰 | 71.0%65.0–76.3% | 55.8%50.1–61.3% | 44.1%38.6–49.6% | 67.6%62.8–72.5% | 53.3%51.7–54.9% | 61.4%58.9–64.0% | 56.5%54.9–58.3% |
| ShallowFBCSPNet | 轻量神经网络 | +1.08 | −1.45 | 1/3 | 清晰 | 68.8%63.4–73.9% | 23.0%20.3–25.9% | 16.2%14.1–18.6% | 67.9%63.4–72.4% | 49.7%49.0–50.4% | 56.7%54.7–58.8% | 55.0%53.1–56.8% |
| CSP+LDA | 经典方法 | — | — | — | 5/7 | 47.1%43.8–50.2% | — | — | 68.3%62.0–74.3% | 50.0%49.1–50.8% | 52.7%51.4–54.0% | 50.1%46.9–53.1% |
| FBCCA | 经典方法 | — | — | — | 2/7 | — | 79.1%75.1–82.8% | 72.3%67.5–76.9% | — | — | — | — |
| Log band-power ridge | 经典方法 | −0.86 | −1.73 | 2/3 | 清晰 | 57.3%54.4–60.3% | 5.3%4.8–5.8% | 5.3%4.8–5.8% | 65.0%60.2–69.7% | 50.4%49.3–51.6% | 56.1%54.2–58.0% | 66.0%63.0–68.9% |
| MDM | 经典方法 | — | — | — | 2/7 | 53.8%50.8–57.9% | — | — | 71.5%65.5–77.8% | — | — | — |
| Spectral ridge | 经典方法 | +0.12 | +3.34 | 3/3 | 清晰 | 54.9%53.2–56.7% | 50.7%45.6–55.8% | 48.2%43.1–53.3% | 56.8%54.6–58.9% | 51.0%49.6–52.4% | 51.0%49.6–52.5% | 72.2%70.7–73.8% |
| Standard CCA | 经典方法 | — | — | — | 2/7 | — | 63.1%57.2–69.0% | 57.6%51.8–63.5% | — | — | — | — |
| Temporal ridge | 经典方法 | — | — | — | 2/7 | — | — | — | — | 53.8%51.9–55.6% | 56.3%54.4–58.4% | — |
| TS+LR | 经典方法 | — | — | — | 2/7 | 58.9%54.9–63.9% | — | — | 65.5%59.6–71.8% | — | — | — |
| xDAWN+LDA | 经典方法 | — | — | — | 2/7 | — | — | — | — | 60.4%57.7–63.2% | 56.8%55.1–58.6% | — |
| XDAWNCov+TS+LR | 经典方法 | — | — | — | 2/7 | — | — | — | — | 61.9%58.8–65.0% | 60.3%58.2–62.6% | — |
查看 7 维轮廓距离最近与最远的方法对(各 10 对)
| 分组 | 方法 A | 方法 B | 7 维轮廓距离 | 2 维投影距离 |
|---|---|---|---|---|
| 最接近轮廓 | LaBraM at Scale Molecule-L | LaBraM at Scale Quark-L | 0.24 | 0.17 |
| 最接近轮廓 | EEGPT | ST-EEGFormer Base | 0.42 | 0.04 |
| 最接近轮廓 | ERP-FM Base | LaBraM at Scale Molecule-L | 0.68 | 0.50 |
| 最接近轮廓 | ERP-FM Base | LaBraM at Scale Quark-L | 0.90 | 0.66 |
| 最接近轮廓 | LaBraM at Scale Atom-L | LaBraM at Scale Quark-H | 0.90 | 0.38 |
| 最接近轮廓 | CodeBrain | ST-EEGFormer Large | 0.92 | 0.20 |
| 最接近轮廓 | REVE Large | REVE Small | 1.00 | 0.24 |
| 最接近轮廓 | LaBraM at Scale Quark-B | LaBraM at Scale Quark-L | 1.03 | 0.28 |
| 最接近轮廓 | LUNA Base | LUNA Large | 1.08 | 0.24 |
| 最接近轮廓 | CodeBrain | Log band-power ridge | 1.08 | 0.96 |
| 差异最大轮廓 | SingLEM | Spectral ridge | 6.24 | 6.02 |
| 差异最大轮廓 | LaBraM at Scale Atom-L | SingLEM | 6.17 | 5.81 |
| 差异最大轮廓 | LaBraM | SingLEM | 6.15 | 5.71 |
| 差异最大轮廓 | EEGPT | SingLEM | 5.87 | 5.74 |
| 差异最大轮廓 | SingLEM | ST-EEGFormer Base | 5.87 | 5.78 |
| 差异最大轮廓 | LaBraM at Scale Quark-H | SingLEM | 5.75 | 5.56 |
| 差异最大轮廓 | REVE Base | SingLEM | 5.70 | 4.95 |
| 差异最大轮廓 | LUNA Large | SingLEM | 5.59 | 5.01 |
| 差异最大轮廓 | ShallowFBCSPNet | Spectral ridge | 5.53 | 4.88 |
| 差异最大轮廓 | ERP-FM Base | SingLEM | 5.52 | 5.39 |
视图二 · 任意双协议十字误差棒
自由双协议散点图
任选两个准确率协议作为横纵坐标,每个点同时画出横轴与纵轴的 95% 区间以及蓝灰色随机水平参考线。完整覆盖与部分覆盖方法只要在两个协议上都有发布数据,均会显示。
查看当前散点数据表:运动想象 × 睡眠分期(共 29 个方法)
| 方法 | 类别 | 运动想象与静息 | 头皮睡眠分期 |
|---|---|---|---|
| BrainOmni Base | 基础模型 | 58.8% (57.0–60.8%) | 67.7% (65.8–69.5%) |
| CBraMod | 基础模型 | 62.9% (59.6–66.5%) | 71.3% (68.7–73.7%) |
| CodeBrain | 基础模型 | 58.8% (54.5–62.6%) | 70.7% (68.8–72.7%) |
| eeg-fm-masking MAE (r=9 cm, L=2) | 基础模型 | 68.1% (64.3–72.3%) | 67.9% (65.4–70.4%) |
| EEGMamba | 基础模型 | 67.3% (63.6–70.6%) | 64.1% (61.6–66.4%) |
| EEGPT | 基础模型 | 58.3% (54.9–61.8%) | 75.5% (73.9–77.1%) |
| ERP-FM Base | 基础模型 | 54.8% (51.8–57.8%) | 71.0% (69.5–72.6%) |
| LaBraM | 基础模型 | 53.5% (51.4–55.4%) | 71.1% (69.0–73.2%) |
| LaBraM at Scale Atom-L | 基础模型 | 56.9% (53.3–61.0%) | 72.7% (70.6–74.4%) |
| LaBraM at Scale Molecule-L | 基础模型 | 59.6% (57.2–61.4%) | 71.9% (70.2–73.4%) |
| LaBraM at Scale Quark-B | 基础模型 | 61.9% (59.1–64.4%) | 72.1% (70.3–74.0%) |
| LaBraM at Scale Quark-G | 基础模型 | 58.7% (57.3–60.1%) | 67.3% (65.6–68.9%) |
| LaBraM at Scale Quark-H | 基础模型 | 60.2% (57.4–62.9%) | 72.9% (71.5–74.2%) |
| LaBraM at Scale Quark-L | 基础模型 | 59.6% (56.3–62.9%) | 70.3% (68.0–72.5%) |
| LUNA Base | 基础模型 | 52.6% (50.2–54.9%) | 67.5% (65.3–69.5%) |
| LUNA Large | 基础模型 | 49.9% (46.6–53.5%) | 72.4% (70.4–74.0%) |
| REVE Base | 基础模型 | 66.2% (61.8–70.6%) | 74.6% (72.9–76.4%) |
| REVE Large | 基础模型 | 70.2% (64.0–76.1%) | 76.6% (75.2–78.0%) |
| REVE Small | 基础模型 | 61.5% (58.3–64.8%) | 64.5% (62.5–66.6%) |
| SingLEM | 基础模型 | 72.0% (66.6–76.6%) | 35.3% (33.7–37.0%) |
| ST-EEGFormer Base | 基础模型 | 58.1% (53.7–63.3%) | 77.3% (75.6–78.8%) |
| ST-EEGFormer Large | 基础模型 | 62.4% (57.4–67.8%) | 79.6% (78.2–81.0%) |
| ZUNA 1.1 | 基础模型 | 50.7% (49.2–52.1%) | 60.1% (57.8–62.3%) |
| Deep4Net | 轻量神经网络 | 68.6% (63.3–74.0%) | 45.2% (42.7–47.7%) |
| EEGNet | 轻量神经网络 | 71.0% (65.0–76.3%) | 56.5% (54.9–58.3%) |
| ShallowFBCSPNet | 轻量神经网络 | 68.8% (63.4–73.9%) | 55.0% (53.1–56.8%) |
| CSP+LDA | 经典方法 | 47.1% (43.8–50.2%) | 50.1% (46.9–53.1%) |
| Log band-power ridge | 经典方法 | 57.3% (54.4–60.3%) | 66.0% (63.0–68.9%) |
| Spectral ridge | 经典方法 | 54.9% (53.2–56.7%) | 72.2% (70.7–73.8%) |
视图三 · 为何不设单一综合分
不同协议是否偏好相同的方法?
下表展示每对准确率协议在共同评测方法上的斯皮尔曼相关系数 ρ 与分歧度(1 − ρ)。任意两项不同协议之间的中位相关为 +0.21,范围从 语义 ERP 与 睡眠分期 的 −0.19 到 BETA 8通道 与 BETA 4通道 的 +0.95。点击任意非对角单元格即可在上方散点图中打开对应协议对。
| 协议 | 运动想象 | BETA 8通道 | BETA 4通道 | 心算负荷 | P300 ERP | 语义 ERP | 睡眠分期 |
|---|---|---|---|---|---|---|---|
| 运动想象 | 1.00n=31 | ||||||
| BETA 8通道 | 1.00n=30 | ||||||
| BETA 4通道 | 1.00n=30 | ||||||
| 心算负荷 | 1.00n=31 | ||||||
| P300 ERP | 1.00n=31 | ||||||
| 语义 ERP | 1.00n=31 | ||||||
| 睡眠分期 | 1.00n=29 |
两两协议对比
选择任意两个方法逐协议对比
查看同一协议下两个方法的点估计与 95% 区间;仅当数据已发布配对差值区间时才显示差值检验。下拉菜单按方法族与字母顺序排列,不按分数排序。
对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差
默认展示(运动想象与静息):ShallowFBCSPNet 平衡准确率 68.8%(95% 区间 63.4–73.9%);EEGNet 71.0%(95% 区间 65.0–76.3%);随机水平 50.0%。
查看已发布的配对差值表(共 91 对)
| 协议 | 对比(左减右) | 配对均值差 | 主区间 | 被试数 | 区间口径与说明 |
|---|---|---|---|---|---|
| SSVEP · 8 通道 | FBCCA − Standard CCA | +16.0 pp | [+11.6, +20.5 pp] | 70 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| SSVEP · 8 通道 | FBCCA − EEGNet | +23.3 pp | [+17.6, +29.6 pp] | 70 | 98.75% 区间,按四项对比做 Bonferroni 校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| SSVEP · 4 通道 | FBCCA − Standard CCA | +14.7 pp | [+10.7, +19.1 pp] | 70 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| SSVEP · 4 通道 | FBCCA − EEGNet | +28.2 pp | [+22.8, +33.9 pp] | 70 | 98.75% 区间,按四项对比做 Bonferroni 校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 运动想象与静息 | TS+LR − Spectral ridge | +4.0 pp | [−1.1, +11.5 pp] | 10 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| 运动想象与静息 | TS+LR − EEGNet | −12.1 pp | [−18.1, −5.4 pp] | 10 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 运动想象与静息 | MDM − EEGNet | −17.2 pp | [−23.7, −10.6 pp] | 10 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 运动想象与静息 | MDM − Spectral ridge | −1.1 pp | [−4.7, +3.8 pp] | 10 | 名义 95% 区间 |
| 运动想象与静息 | TS+LR − CSP+LDA | +11.8 pp | [+7.9, +16.8 pp] | 10 | 名义 95% 区间 |
| 运动想象与静息 | MDM − CSP+LDA | +6.8 pp | [+3.3, +10.8 pp] | 10 | 名义 95% 区间 |
| 运动想象与静息 | TS+LR − LaBraM | +5.4 pp | [+0.3, +11.3 pp] | 10 | 名义 95% 区间 |
| 运动想象与静息 | TS+LR − CBraMod | −4.0 pp | [−8.4, +0.9 pp] | 10 | 名义 95% 区间 |
| 运动想象与静息 | TS+LR − MDM | +5.1 pp | [+2.3, +7.8 pp] | 10 | 名义 95% 区间 |
| 心算与静息 | TS+LR − Spectral ridge | +8.8 pp | [+1.6, +16.1 pp] | 36 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| 心算与静息 | TS+LR − EEGNet | −2.1 pp | [−8.0, +3.8 pp] | 36 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 心算与静息 | MDM − EEGNet | +3.8 pp | [−1.3, +9.3 pp] | 36 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 心算与静息 | MDM − Spectral ridge | +14.7 pp | [+8.9, +20.5 pp] | 36 | 名义 95% 区间 |
| 心算与静息 | TS+LR − LaBraM | +0.9 pp | [−4.6, +6.6 pp] | 36 | 名义 95% 区间 |
| 心算与静息 | TS+LR − CBraMod | +3.2 pp | [−1.5, +8.0 pp] | 36 | 名义 95% 区间 |
| 心算与静息 | TS+LR − MDM | −6.0 pp | [−11.6, −0.5 pp] | 36 | 名义 95% 区间 |
| P300 目标 ERP | XDAWNCov+TS+LR − Spectral ridge | +11.0 pp | [+6.8, +15.1 pp] | 21 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| P300 目标 ERP | XDAWNCov+TS+LR − EEGNet | +8.6 pp | [+5.2, +12.0 pp] | 21 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| P300 目标 ERP | xDAWN+LDA − EEGNet | +7.1 pp | [+4.3, +10.0 pp] | 21 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| P300 目标 ERP | xDAWN+LDA − Spectral ridge | +9.5 pp | [+6.5, +12.4 pp] | 21 | 名义 95% 区间 |
| P300 目标 ERP | XDAWNCov+TS+LR − Temporal ridge | +8.1 pp | [+5.3, +11.1 pp] | 21 | 名义 95% 区间 |
| P300 目标 ERP | xDAWN+LDA − Temporal ridge | +6.6 pp | [+3.7, +9.8 pp] | 21 | 名义 95% 区间 |
| P300 目标 ERP | XDAWNCov+TS+LR − LaBraM | +12.5 pp | [+8.7, +16.3 pp] | 21 | 名义 95% 区间 |
| P300 目标 ERP | XDAWNCov+TS+LR − CBraMod | +6.9 pp | [+4.4, +9.6 pp] | 21 | 名义 95% 区间 |
| P300 目标 ERP | XDAWNCov+TS+LR − xDAWN+LDA | +1.5 pp | [−0.9, +3.7 pp] | 21 | 名义 95% 区间 |
| 语义目标 ERP | XDAWNCov+TS+LR − Spectral ridge | +9.3 pp | [+6.1, +12.8 pp] | 30 | 98.75% 区间,按四项对比做 Bonferroni 校正 |
| 语义目标 ERP | XDAWNCov+TS+LR − EEGNet | −1.2 pp | [−3.0, +0.6 pp] | 30 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 语义目标 ERP | xDAWN+LDA − EEGNet | −4.6 pp | [−6.5, −2.7 pp] | 30 | 名义 95% 区间对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 语义目标 ERP | xDAWN+LDA − Spectral ridge | +5.8 pp | [+4.0, +7.8 pp] | 30 | 名义 95% 区间 |
| 语义目标 ERP | XDAWNCov+TS+LR − Temporal ridge | +3.9 pp | [+2.0, +5.9 pp] | 30 | 名义 95% 区间 |
| 语义目标 ERP | xDAWN+LDA − Temporal ridge | +0.5 pp | [−1.2, +2.1 pp] | 30 | 名义 95% 区间 |
| 语义目标 ERP | XDAWNCov+TS+LR − LaBraM | +7.1 pp | [+4.8, +9.4 pp] | 30 | 名义 95% 区间 |
| 语义目标 ERP | XDAWNCov+TS+LR − CBraMod | +4.5 pp | [+2.5, +6.4 pp] | 30 | 名义 95% 区间 |
| 语义目标 ERP | XDAWNCov+TS+LR − xDAWN+LDA | +3.5 pp | [+1.8, +5.3 pp] | 30 | 名义 95% 区间 |
| 心算与静息 | CSP+LDA − EEGNet | +0.7 pp | [−4.3, +5.8 pp] | 36 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 心算与静息 | Deep4Net − EEGNet | −6.3 pp | [−10.4, −2.3 pp] | 36 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 心算与静息 | ShallowFBCSPNet − EEGNet | +0.3 pp | [−2.6, +3.3 pp] | 36 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 心算与静息 | ShallowFBCSPNet − Deep4Net | +6.6 pp | [+2.6, +10.6 pp] | 36 | 95% 区间 |
| SSVEP · 4 通道 | Deep4Net − EEGNet | −5.5 pp | [−6.8, −4.1 pp] | 70 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| SSVEP · 4 通道 | ShallowFBCSPNet − EEGNet | −27.9 pp | [−31.9, −23.9 pp] | 70 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| SSVEP · 4 通道 | ShallowFBCSPNet − Deep4Net | −22.4 pp | [−26.1, −18.9 pp] | 70 | 95% 区间 |
| SSVEP · 8 通道 | Deep4Net − EEGNet | −3.0 pp | [−3.9, −2.1 pp] | 70 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| SSVEP · 8 通道 | ShallowFBCSPNet − EEGNet | −32.7 pp | [−37.0, −28.5 pp] | 70 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| SSVEP · 8 通道 | ShallowFBCSPNet − Deep4Net | −29.7 pp | [−33.7, −25.8 pp] | 70 | 95% 区间 |
| 运动想象与静息 | Deep4Net − EEGNet | −2.4 pp | [−6.8, +2.3 pp] | 10 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 运动想象与静息 | ShallowFBCSPNet − EEGNet | −2.2 pp | [−8.0, +3.4 pp] | 10 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 运动想象与静息 | ShallowFBCSPNet − Deep4Net | +0.3 pp | [−6.8, +7.7 pp] | 10 | 95% 区间 |
| P300 目标 ERP | CSP+LDA − EEGNet | −3.3 pp | [−5.4, −1.6 pp] | 21 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| P300 目标 ERP | Deep4Net − EEGNet | −2.5 pp | [−4.2, −0.9 pp] | 21 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| P300 目标 ERP | ShallowFBCSPNet − EEGNet | −3.6 pp | [−5.4, −1.9 pp] | 21 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| P300 目标 ERP | ShallowFBCSPNet − Deep4Net | −1.1 pp | [−2.1, −0.2 pp] | 21 | 95% 区间 |
| 语义目标 ERP | CSP+LDA − EEGNet | −8.8 pp | [−11.1, −6.4 pp] | 30 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 语义目标 ERP | Deep4Net − EEGNet | −4.0 pp | [−5.8, −2.1 pp] | 30 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 语义目标 ERP | ShallowFBCSPNet − EEGNet | −4.7 pp | [−7.2, −2.2 pp] | 30 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 语义目标 ERP | ShallowFBCSPNet − Deep4Net | −0.7 pp | [−3.0, +1.5 pp] | 30 | 95% 区间 |
| 头皮睡眠分期 | CSP+LDA − EEGNet | −6.4 pp | [−9.3, −3.3 pp] | 20 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 头皮睡眠分期 | Deep4Net − EEGNet | −11.3 pp | [−13.6, −9.0 pp] | 20 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 头皮睡眠分期 | ShallowFBCSPNet − EEGNet | −1.6 pp | [−3.4, +0.4 pp] | 20 | 95% 区间,未校正对照为矩阵中单种子的 EEGNet 单元格;未包含训练方差 |
| 头皮睡眠分期 | ShallowFBCSPNet − Deep4Net | +9.7 pp | [+7.0, +12.7 pp] | 20 | 95% 区间 |
| 运动想象与静息 | Log band-power ridge − Spectral ridge | +2.4 pp | [−1.2, +5.8 pp] | 10 | 95% 配对被试自助法区间(未校正) |
| SSVEP · 8 通道 | Log band-power ridge − Spectral ridge | −45.4 pp | [−50.4, −40.6 pp] | 70 | 95% 配对被试自助法区间(未校正) |
| SSVEP · 4 通道 | Log band-power ridge − Spectral ridge | −42.9 pp | [−47.7, −38.1 pp] | 70 | 95% 配对被试自助法区间(未校正) |
| 心算与静息 | Log band-power ridge − Spectral ridge | +8.2 pp | [+4.0, +12.6 pp] | 36 | 95% 配对被试自助法区间(未校正) |
| P300 目标 ERP | Log band-power ridge − Spectral ridge | −0.5 pp | [−2.4, +1.4 pp] | 21 | 95% 配对被试自助法区间(未校正) |
| 语义目标 ERP | Log band-power ridge − Spectral ridge | +5.1 pp | [+3.1, +7.1 pp] | 30 | 95% 配对被试自助法区间(未校正) |
| 头皮睡眠分期 | Log band-power ridge − Spectral ridge | −6.2 pp | [−8.5, −3.9 pp] | 20 | 95% 配对被试自助法区间(未校正) |
| 运动想象与静息 | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | −2.3 pp | [−4.8, −0.3 pp] | 10 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 8 通道 | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | −0.4 pp | [−1.3, +0.6 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 4 通道 | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | +0.1 pp | [−0.9, +1.2 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 心算与静息 | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | −2.1 pp | [−5.0, +0.8 pp] | 36 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| P300 目标 ERP | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | +1.4 pp | [−0.3, +3.3 pp] | 21 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 语义目标 ERP | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | −0.6 pp | [−2.8, +1.7 pp] | 30 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 头皮睡眠分期 | LaBraM at Scale Quark-L − LaBraM at Scale Quark-B | −1.8 pp | [−3.3, −0.3 pp] | 20 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 运动想象与静息 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | +0.6 pp | [−3.1, +3.5 pp] | 10 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 8 通道 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | −3.4 pp | [−4.4, −2.4 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 4 通道 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | −1.7 pp | [−2.7, −0.8 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 心算与静息 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | +0.6 pp | [−1.7, +2.8 pp] | 36 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| P300 目标 ERP | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | +1.6 pp | [−0.4, +3.5 pp] | 21 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 语义目标 ERP | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | −2.6 pp | [−5.1, −0.1 pp] | 30 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 头皮睡眠分期 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-L | +2.5 pp | [+1.0, +4.2 pp] | 20 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 运动想象与静息 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | −1.8 pp | [−5.2, +1.0 pp] | 10 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 8 通道 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | −3.8 pp | [−4.8, −2.8 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| SSVEP · 4 通道 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | −1.6 pp | [−2.5, −0.7 pp] | 70 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 心算与静息 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | −1.5 pp | [−4.4, +1.3 pp] | 36 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| P300 目标 ERP | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | +3.0 pp | [+1.3, +4.8 pp] | 21 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 语义目标 ERP | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | −3.3 pp | [−5.5, −0.9 pp] | 30 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |
| 头皮睡眠分期 | LaBraM at Scale Quark-H − LaBraM at Scale Quark-B | +0.7 pp | [−0.9, +2.5 pp] | 20 | 95% 配对被试自助法区间(未校正;共 21 项阶梯对比) |