Fig. 9
From: Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks
Using one-shot transfer learning (PN) improved the accuracy in comparison to subject-independent NN. Supplementing it with dimensionality reduction (PN+DR), or increased window size (PN+TS), or both (PN+DR+TS) improved the accuracy even further. Results with (*) indicate a significant difference (\(p<0.05\)) between them