EMG subspace alignment and visualization for cross-subject hand gesture classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913191745814528 |
|---|---|
| author | Colot, Martin Simar, Cédric Petieau, Mathieu Alvarez, Ana Maria Cebolla Cheron, Guy Bontempi, Gianluca |
| author_facet | Colot, Martin Simar, Cédric Petieau, Mathieu Alvarez, Ana Maria Cebolla Cheron, Guy Bontempi, Gianluca |
| contents | Electromyograms (EMG)-based hand gesture recognition systems are a promising technology for human/machine interfaces. However, one of their main limitations is the long calibration time that is typically required to handle new users. The paper discusses and analyses the challenge of cross-subject generalization thanks to an original dataset containing the EMG signals of 14 human subjects during hand gestures. The experimental results show that, though an accurate generalization based on pooling multiple subjects is hardly achievable, it is possible to improve the cross-subject estimation by identifying a robust low-dimensional subspace for multiple subjects and aligning it to a target subject. A visualization of the subspace enables us to provide insights for the improvement of cross-subject generalization with EMG signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05386 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | EMG subspace alignment and visualization for cross-subject hand gesture classification Colot, Martin Simar, Cédric Petieau, Mathieu Alvarez, Ana Maria Cebolla Cheron, Guy Bontempi, Gianluca Signal Processing Human-Computer Interaction Machine Learning Electromyograms (EMG)-based hand gesture recognition systems are a promising technology for human/machine interfaces. However, one of their main limitations is the long calibration time that is typically required to handle new users. The paper discusses and analyses the challenge of cross-subject generalization thanks to an original dataset containing the EMG signals of 14 human subjects during hand gestures. The experimental results show that, though an accurate generalization based on pooling multiple subjects is hardly achievable, it is possible to improve the cross-subject estimation by identifying a robust low-dimensional subspace for multiple subjects and aligning it to a target subject. A visualization of the subspace enables us to provide insights for the improvement of cross-subject generalization with EMG signals. |
| title | EMG subspace alignment and visualization for cross-subject hand gesture classification |
| topic | Signal Processing Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2401.05386 |