Ulysse Cote Allard1, François Laviolette1, Benoit Gosselin2
10:00 - 17:00 | Mon 29 Oct | Foyer | A1P-G.3
This work performs electromyography-based hand gesture recognition by applying transfer learning on the aggregated data from multiple users while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. The proposed transfer learning scheme outperforms the state-of-the-art, achieving an average accuracy of 98.31% for 7 gestures over 17 participants.