aiqbench analysis
This research introduces novel zero-shot learning techniques for sEMG-based prosthetic control, enabling systems to recognize complex combined movements without additional training data. By leveraging linear interpolation in embedding spaces, the proposed methods achieve significant accuracy gains over existing approaches while reducing the need for extensive dataset collection. The findings advance practical applications of machine learning in assistive robotics by addressing a critical bottleneck in adapting models to new user-specific movement patterns.
Prototype Adaptation for Zero-Shot sEMG Movement Classification
arXiv:2607.25826v1 Announce Type: new Abstract: Surface electromyography (sEMG) enables the control of prostheses, allowing upper-limb amputees to re-gain some hand function. Most current research focuses on recognizing basic movements for prosthesis control. However, in most daily activities, such as opening a door, combined movements are essential. However, collecting training data for all possible combined movements is time-consuming and requires re-training of the model for any new combination. We propose two novel recognition approaches, Compositional Prototype Interpolation (CPI) and Synthetic Adaptation for Prototypes (SAP), that enable zero-shot learning of combined, novel and unseen movements in Prototype Networks after training only with basic movements. Our methods rest on a linear interpolation assumption in the embedding space, which we study by inspecting the geometry of combined motions in signal and embedding space. In experiments on the NearLab and NinaPro DB3 data sets as well as our newly recorded BasCom dataset, our proposed SAP outperforms prior zero-shot learning methods with accuracy improvements on combined movements of more than 20%. This advantage is maintained in online inference experiments in a user study.
Abstract:Surface electromyography (sEMG) enables the control of prostheses, allowing upper-limb amputees to re-gain some hand function. Most current research focuses on recognizing basic movements for prosthesis control. However, in most daily activities, such as opening a door, combined movements are essential. However, collecting training data for all possible combined movements is time-consuming and requires re-training of the model for any new combination. We propose two novel recognition approaches, Compositional Prototype Interpolation (CPI) and Synthetic Adaptation for Prototypes (SAP), that enable zero-shot learning of combined, novel and unseen movements in Prototype Networks after training only with basic movements. Our methods rest on a linear interpolation assumption in the embedding space, which we study by inspecting the geometry of combined motions in signal and embedding space. In experiments on the NearLab and NinaPro DB3 data sets as well as our newly recorded BasCom dataset, our proposed SAP outperforms prior zero-shot learning methods with accuracy improvements on combined movements of more than 20%. This advantage is maintained in online inference experiments in a user study.
Machine Learning (cs.LG)
arXiv:2607.25826 [cs.LG]
(or arXiv:2607.25826v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.25826 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
arXiv · Jun 5, 2026
Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
arXiv · Oct 6, 2026
BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
arXiv · Sep 22, 2026
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
arXiv · Sep 22, 2026