Metraipolis › archive › dc_e24e6102acfe
Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget — arXiv:2609.20296
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20296
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:02:36.232Z
- SHA-256 of the archived text
1da676ec0624b57d2879b04d9978117f17903cc945b07675b68ce1fe88f08446- Stable URL of this page
https://metraipolis.com/documento/dc_e24e6102acfe
How to cite
Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget — arXiv:2609.20296 — arXiv (en), https://arxiv.org/abs/2609.20296 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e24e6102acfe (Metraipolis archive dc_e24e6102acfe, sha256 1da676ec0624b57d2879b04d9978117f17903cc945b07675b68ce1fe88f08446)
BibTeX
@misc{dce24e6102acfe,
title = {Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget — arXiv:2609.20296},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20296},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e24e6102acfe; sha256 1da676ec0624b57d2879b04d9978117f17903cc945b07675b68ce1fe88f08446},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20296. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A myoelectric interface needs calibration from the user before it will function. Earlier work has treated calibration as a quantity, but has not asked the question of what a device should do with the calibration repetitions once they have been collected. This paper views personalizing the cross-user encoder as a design decision with a cost. Four alternative approaches to using exactly the same labeled repetitions were tested from a single cross-user encoder per held-out subject. Prototypical adaptation, linear probes, scaled fine-tuning and full fine-tuning were tested at every budget up to the maximum each database allows, five repetitions on DB1 and four on DB2 and DB5. Comparing four ways to spend a small calibration budget across 77 subjects, full fine-tuning is the most accurate at every budget, consistently enough that there is no exception among subsets of subjects. The result which impacts how one might make an engineering decision however is that a gradient free prototypical rule recovers 52 to 78 per cent of its benefit with no optimiser and no per-user copy of the weights, which makes personalisation something a worn device can do at donning time. The widespread intuition that a good representation only needs a fresh classifier is incorrect here. How well each method may perform relative to a per-user classifier that would be fitted by a clinic will depend on the specific database. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.HC). Categorie arXiv: Machine Learning (cs.LG) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.20296 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:28:23.650Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).