Imperial College London
Alternate

ProfessorFernandoBello

Faculty of Medicine, Department of Surgery & Cancer

Professor of Surgical Computing and Simulation Science
 
 
 
//

Contact

 

+44 (0)20 3315 8231f.bello Website

 
 
//

Location

 

G3.50Chelsea and Westminster HospitalChelsea and Westminster Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Chappell:2022:10.1109/ICORR55369.2022.9896480,
author = {Chappell, D and Yang, Z and Son, HW and Bello, F and Kormushev, P and Rojas, N},
doi = {10.1109/ICORR55369.2022.9896480},
publisher = {IEEE},
title = {Towards instant calibration in myoelectric prosthetic hands: a highly data-efficient controller based on the Wasserstein distance},
url = {http://dx.doi.org/10.1109/ICORR55369.2022.9896480},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Prosthetic hand control research typically focuses on developing increasingly complex controllers to achieve diminishing returns in pattern recognition of muscle activity signals, making models less suitable for user calibration. Some works have investigated transfer learning to alleviate this, but such approaches increase model size dramatically—thus reducing their suitability for implementation on real prostheses. In this work, we propose a novel, non-parametric controller that uses the Wasserstein distance to compare the distribution of incoming signals to those of a set of reference distributions,with the intended action classified as the closest distribution. This controller requires only a single capture of data per reference distribution, making calibration almost instantaneous. Preliminary experiments building a reference library show that, in theory, users are able to produce up to 9 distinguishable muscle activity patterns. However, in practice, variation whenrepeating actions reduces this. Controller accuracy results show that 10 non-disabled and 1 disabled participant were able to use the controller with a maximum of two recalibrations to perform 6 actions at an average accuracy of 89.9% and 86.7% respectively. Practical experiments show that the controller allows users to complete all tasks of the Jebsen-Taylor HandFunction Test, although the task of picking and placing small common objects required on average more time than the protocol’s maximum time.
AU  - Chappell,D
AU  - Yang,Z
AU  - Son,HW
AU  - Bello,F
AU  - Kormushev,P
AU  - Rojas,N
DO  - 10.1109/ICORR55369.2022.9896480
PB  - IEEE
PY  - 2022///
TI  - Towards instant calibration in myoelectric prosthetic hands: a highly data-efficient controller based on the Wasserstein distance
UR  - http://dx.doi.org/10.1109/ICORR55369.2022.9896480
UR  - http://hdl.handle.net/10044/1/96928
ER  -
Download