Poster Open Access

Feedback matters – or doesn't it? User training for pattern-recognition controlled prostheses (Abstract title: User training for pattern-recognition based myoelectric prostheses using a serious game)

Kristoffersen, Morten Bak; Franzke, Andreas; Murgia, Alessio; van der Sluis, Corry; Bongers, Raoul


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Serious games</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">User training</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Motor learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Prosthesis</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Myocontrol</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Pattern-recognition</subfield>
  </datafield>
  <controlfield tag="005">20190409133923.0</controlfield>
  <controlfield tag="001">1217832</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">15-08-2017 - 18-08-2017</subfield>
    <subfield code="g">MEC</subfield>
    <subfield code="a">Myoelectric Controls Symposium</subfield>
    <subfield code="c">Fredericton, New Brunswick, Canada</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Groningen, University Medical Center Groningen, Department of Rehabilitation Medicine, Groningen, the Netherlands</subfield>
    <subfield code="a">Franzke, Andreas</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Groningen, University Medical Center Groningen, Center for Human Movement Sciences, Groningen, the Netherlands</subfield>
    <subfield code="a">Murgia, Alessio</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Groningen, University Medical Center Groningen, Department of Rehabilitation Medicine, Groningen, the Netherlands</subfield>
    <subfield code="a">van der Sluis, Corry</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Groningen, University Medical Center Groningen, Center for Human Movement Sciences, Groningen, the Netherlands</subfield>
    <subfield code="a">Bongers, Raoul</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">580611</subfield>
    <subfield code="z">md5:fba02867291e76f35494f287407008dd</subfield>
    <subfield code="u">https://zenodo.org/record/1217832/files/20170808 MEC Poster </subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">http://www.unb.ca/research/institutes/biomedical/mec/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-08-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:1217832</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Groningen, University Medical Center Groningen, Department of Rehabilitation Medicine, Groningen, the Netherlands</subfield>
    <subfield code="0">(orcid)0000-0002-3901-2856</subfield>
    <subfield code="a">Kristoffersen, Morten Bak</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Feedback matters – or doesn't it? User training for pattern-recognition controlled prostheses (Abstract title: User training for pattern-recognition based myoelectric prostheses using a serious game)</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">687795</subfield>
    <subfield code="a">Intuitive Natural Prosthesis UTilization</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Please note there was a problem with the upload. The file is a pdf, but the file ending is missing. Manually opening the file in a pdf reader should work. Otherwise feel free to contact me.&amp;nbsp;&lt;/p&gt;

&lt;p&gt;Abstract&lt;/p&gt;

&lt;p&gt;Individuals with upper-limb deficiency who are fitted&lt;br&gt;
with a prosthesis are normally trained in the use of such&lt;br&gt;
device. This is even true for individuals who are fitted with a&lt;br&gt;
myoelectric prosthesis that uses control algorithms based on&lt;br&gt;
pattern-recognition, despite the intent of pattern-recognition&lt;br&gt;
control of exploiting &amp;ldquo;intuitive&amp;rdquo; phantom movements.&lt;br&gt;
Conventionally, training individuals for pattern-recognition&lt;br&gt;
control usually involves an expert who guides the user to&lt;br&gt;
produce electromyogram (EMG) signals that optimize&lt;br&gt;
pattern recognition. In the training the individual is&lt;br&gt;
stimulated to adapt their EMG signals as to make them more&lt;br&gt;
distinct in terms of the resulting patterns. To achieve this, for&lt;br&gt;
instance, small movements can be added to the basic pattern,&lt;br&gt;
such as flexing the little finger during open hand. Although&lt;br&gt;
training improves online accuracy it still involves&lt;br&gt;
considerable trial and error. Moreover, expert guidance is&lt;br&gt;
currently done based on visual perusal of EMG patterns or&lt;br&gt;
features thereof and not based on specific metrics&lt;br&gt;
characterizing those EMG signal patterns. Rather than using&lt;br&gt;
intuitive phantom movements for control, we instead propose&lt;br&gt;
to use those phantom movements which are most distinct in&lt;br&gt;
terms of EMG. To find the set of phantom movements that&lt;br&gt;
provides the most distinct EMG activation patterns, we&lt;br&gt;
propose to use a serious game. Using a game, we can train&lt;br&gt;
individuals to make EMG patterns distinct while performing&lt;br&gt;
them in a robust manner. This game is controlled using the&lt;br&gt;
EMG captured from 8 electrodes positioned around the&lt;br&gt;
forearm. Inspired by the work of Radhakrishnan et. al and&lt;br&gt;
Pistohl et. al, the EMG from each electrode is mapped to a&lt;br&gt;
direction of the game avatar in the 2D environment. We&lt;br&gt;
hypothesize that this training will make individuals utilize&lt;br&gt;
their EMG activation space to a greater extent and become&lt;br&gt;
better at generating only EMG activity at specific electrode&lt;br&gt;
sites so that patterns are more distinct.&lt;br&gt;
We are currently conducting an experiment in which 4&lt;br&gt;
experimental groups receive different kinds of training.&lt;br&gt;
Group 1 receives conventional training without coaching.&lt;br&gt;
Group 2 receives conventional training with feedback. Group&lt;br&gt;
3 receives training with the proposed serious game and group&lt;br&gt;
4 receives training without any feedback (control). The&lt;br&gt;
learning effects between groups are analysed using the&lt;br&gt;
metrics proposed by Bunderson et al. and the motion test.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1217828</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1217832</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">poster</subfield>
  </datafield>
</record>
67
9
views
downloads
All versions This version
Views 6758
Downloads 93
Data volume 3.7 MB1.7 MB
Unique views 4439
Unique downloads 62

Share

Cite as