Table 6 Effect sizes for various ablation experiments.

From: CTNet: a convolutional transformer network for EEG-based motor imagery classification

Condition

BCI IV-2a (Hedges' g)

BCI IV-2b (Hedges' g)

WA + WT vs. WA + NT

0.179

0.184

NA + WT vs. NA + NT

− 0.063

− 0.002

WT + WA vs. WT + NA

0.758

0.143

NT + WA vs. NT + NA

0.441

− 0.049

WA + WT vs. NA + NT

0.595

0.139

  1. WA represents with augmentation, WT represents with the Transformer module, NA represents no augmentation, and NT represents no Transformer module.
Back to article page