Fixed and resampled permutations are distinct controls in connectivity-augmented EEG decoding

英文摘要

Fixed and independently resampled uniform permutations share an ex-ante one-presentation law but differ across repeated presentations. For a P-coordinate vector with coordinate variance sᵥ², expected squared displacement between two presentations of the same trial is zero under a fixed permutation and 2Psᵥ² under independent resampling. We test their practical consequences in connectivity-augmented EEG decoding using a protocol-locked rerun on four previously inspected evaluation partitions. Ten paired training replicates yield resampled-minus-fixed accuracy differences of +13.28, +0.26, +11.32, and +30.08 percentage points for BCI 2a, BCI 2b, Lee2019, and HGD. Removing auxiliary normalization reduces the matched five-replicate gaps on Lee2019 and HGD from 11.15 to 0.72 and from 29.62 to 2.75 points. An HGD finite-bank null approximately preserving node strengths retains a 17.20-point gap. A graph-convolutional extension shows small, uncertain schedule contrasts, restricting architecture-level generalization. Inference resampling and global relabeling meet a specified ±1-point mean-accuracy equivalence criterion. Large accuracy effects characterize the evaluated late-fusion procedure. Controls require explicit schedules, normalization, and evaluation rules.

看似相同的兩種對照

打亂連結性數值，是檢驗解碼模型是否真正利用資料結構的常見方法。排列可以在每筆試驗上固定一次，也可以在訓練中每次讀到該試驗時重新抽取。只看單次呈現，兩種做法在訓練開始前沒有差別；但同一筆試驗被反覆讀到時，模型收到的輸入序列就不一樣了。

本文先推導這兩種排列排程的精確性質，再於一個加入連結性特徵的腦電圖（EEG）解碼流程中檢驗其實際影響。該流程以相位鎖定值（PLV）為輔助特徵，採用 EEGNet 後期融合模型，並使用四個公開資料集：BCI Competition IV 2a 與 2b、Lee2019/OpenBMI，以及 High-Gamma Dataset。

在不同資料集中，重新抽取與固定排列之間的準確率差距從接近零到約三十個百分點不等，並且高度取決於輔助特徵的正規化方式。延伸到圖卷積架構時，差異小且不確定，因此結果描述的是本文所評估的流程，而非所有模型架構。實務上的結論很簡單：沒寫清楚排列排程、正規化和評估規則，這個對照組就還沒定義完整。