May 8, 2017 Presentation Closed Access

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

Citation Style Language JSON Export

{
  "DOI": "10.5281/zenodo.1209334", 
  "abstract": "<p>BACKGROUND<br>\nIndividuals with upper-limb deficiency who are fitted<br>\nwith a prosthesis are normally trained in the use of<br>\nsuch device. During training pattern-recognition based<br>\ncontrol, the way training improves control skills and<br>\nwhat kind of feedback facilitates skill acquisition is<br>\nstill poorly understood. Moreover no training protocols<br>\nfor pattern-recognition control have been described in<br>\nthe literature that do not require an expert trainer which<br>\nlimits the clinical applicability of pattern-recognition<br>\ncontrolled prosthetics.<br>\nAIM<br>\nThe aim of this study is to investigate how different<br>\nkinds of feedback improve the control skills of patternrecognition<br>\ncontrol.<br>\nMETHOD<br>\nNine able-bodied volunteers participated in an<br>\ninitial experiment in which they either performed<br>\nconventional system training or gamified system<br>\ntraining with no prior user training. Based on the results<br>\nof the initial experiment, a follow-up experiment will<br>\nbe conducted where four different kinds of training<br>\nregimes are investigated namely; conventional training<br>\nwith knowledge of results but without coaching,<br>\nconventional training with knowledge of results and<br>\nknowledge of performance, serious game training or<br>\ntraining with no feedback (control). Each group will<br>\ninclude 15 participants, who train one hour per day for<br>\nfive consecutive days. Offline and online accuracy as<br>\nwell as the repeatability index, separability index and<br>\nmean semi-principal axis [1] will be reported for each<br>\ngroup.<br>\nRESULTS<br>\nIn the initial experiment control performance was<br>\nmeasured using the motion test [2] and a questionnaire<br>\nwas used to measure the participants experience of<br>\nthe system training and evaluation. No significant<br>\ndifferences were found between the groups.<br>\nPreliminary results of the follow-up experiment will<br>\nalso be reported.<br>\nDISCUSSION &amp; CONCLUSION<br>\nThe finding that no differences were found between<br>\nthe groups in the initial experiment could be ascribed<br>\nto the way the game targets were set in the gamified<br>\nsystem training and to an unintuitive mapping<br>\nbetween movement and game control. In the followup<br>\nexperiment that will be performed a fixed mapping<br>\ninspired by Radhakrishnan et. al [3] is used where the<br>\nelectromyogram measured at each electrode located on<br>\nthe forearm is mapped to a direction.<br>\nREFERENCES<br>\n1. Bunderson NE et. al, IEEE T Neur Sys Reh. 2012<br>\n2. Kuiken TA et. al, J Am Med Assoc. 2009<br>\n3. Radhakrisnan S. et. al, J Neurophysiol. 2008</p>", 
  "author": [
    {
      "family": "Kristoffersen, Morten Bak"
    }, 
    {
      "family": "Franzke, Andreas"
    }, 
    {
      "family": "Murgia, Alessio"
    }, 
    {
      "family": "van der Sluis, Corry"
    }, 
    {
      "family": "Bongers, Raoul M."
    }
  ], 
  "id": "1209334", 
  "issued": {
    "date-parts": [
      [
        2017, 
        5, 
        8
      ]
    ]
  }, 
  "publisher": "Zenodo", 
  "title": "User training for pattern-recognition based myoelectric prostheses using a serious game", 
  "type": "speech"
}