Advanced

Using EMG for Real-time Prediction of Joint Angles to Control a Prosthetic Hand Equipped with a Sensory Feedback System

Antfolk, Christian LU ; Cipriani, Christian; Controzzi, Marco; Carrozza, Maria Chiara; Lundborg, Göran LU ; Rosén, Birgitta LU and Sebelius, Fredrik LU (2010) In Journal of Medical and Biological Engineering 30(6). p.399-405
Abstract
All commercially available upper limb prosthesis controllers only allow the hand to be commanded in an open and close fashion without any sensory feedback to the user. Here the evaluation of a multi-degree of freedom hand controlled using a real-time EMG pattern recognition algorithm and incorporating a sensory feedback system is reported. The hand prosthesis, called SmartHand, was controlled in real-time by using 16 myoelectric signals from the residual limb of a 25-year old male transradial amputee in a two day long evaluation session. Initial training of the EMG pattern recognition algorithm was performed with a dataglove fitted to the contralateral hand recording joint angle positions of the fingers and mapping joint angles of the... (More)
All commercially available upper limb prosthesis controllers only allow the hand to be commanded in an open and close fashion without any sensory feedback to the user. Here the evaluation of a multi-degree of freedom hand controlled using a real-time EMG pattern recognition algorithm and incorporating a sensory feedback system is reported. The hand prosthesis, called SmartHand, was controlled in real-time by using 16 myoelectric signals from the residual limb of a 25-year old male transradial amputee in a two day long evaluation session. Initial training of the EMG pattern recognition algorithm was performed with a dataglove fitted to the contralateral hand recording joint angle positions of the fingers and mapping joint angles of the fingers to the EMG data. In the following evaluation sessions, the myoelectric signals were classified using local approximation and lazy learning, producing finger joint angle outputs and consequently controlling the prosthetic hand. Sensory information recorded from force sensors in the artificial hand was relayed to actuators, integrated in the socket of the prosthesis, continuously delivering force sensory feedback stimulations to the stump of the amputee. The participant was able to perform several dextrous movements as well as functional grip tasks after only two hours of training and increased his controllability during the two day session. In the final evaluation session a mean classification accuracy of 86% was achieved. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Prosthetic hand, EMG signal acquisition, Myoelectric control
in
Journal of Medical and Biological Engineering
volume
30
issue
6
pages
399 - 405
publisher
Institute of Biomedical Engineering, National Cheng Kung University
external identifiers
  • wos:000285723100008
  • scopus:78751498290
ISSN
1609-0985
DOI
10.5405/jmbe.767
language
English
LU publication?
yes
id
e2a5692c-4d87-4004-8f06-dbea4ed9b753 (old id 1814798)
date added to LUP
2011-03-02 13:26:02
date last changed
2018-07-08 03:39:49
@article{e2a5692c-4d87-4004-8f06-dbea4ed9b753,
  abstract     = {All commercially available upper limb prosthesis controllers only allow the hand to be commanded in an open and close fashion without any sensory feedback to the user. Here the evaluation of a multi-degree of freedom hand controlled using a real-time EMG pattern recognition algorithm and incorporating a sensory feedback system is reported. The hand prosthesis, called SmartHand, was controlled in real-time by using 16 myoelectric signals from the residual limb of a 25-year old male transradial amputee in a two day long evaluation session. Initial training of the EMG pattern recognition algorithm was performed with a dataglove fitted to the contralateral hand recording joint angle positions of the fingers and mapping joint angles of the fingers to the EMG data. In the following evaluation sessions, the myoelectric signals were classified using local approximation and lazy learning, producing finger joint angle outputs and consequently controlling the prosthetic hand. Sensory information recorded from force sensors in the artificial hand was relayed to actuators, integrated in the socket of the prosthesis, continuously delivering force sensory feedback stimulations to the stump of the amputee. The participant was able to perform several dextrous movements as well as functional grip tasks after only two hours of training and increased his controllability during the two day session. In the final evaluation session a mean classification accuracy of 86% was achieved.},
  author       = {Antfolk, Christian and Cipriani, Christian and Controzzi, Marco and Carrozza, Maria Chiara and Lundborg, Göran and Rosén, Birgitta and Sebelius, Fredrik},
  issn         = {1609-0985},
  keyword      = {Prosthetic hand,EMG signal acquisition,Myoelectric control},
  language     = {eng},
  number       = {6},
  pages        = {399--405},
  publisher    = {Institute of Biomedical Engineering, National Cheng Kung University},
  series       = {Journal of Medical and Biological Engineering},
  title        = {Using EMG for Real-time Prediction of Joint Angles to Control a Prosthetic Hand Equipped with a Sensory Feedback System},
  url          = {http://dx.doi.org/10.5405/jmbe.767},
  volume       = {30},
  year         = {2010},
}