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

Citation Style Language JSON Export

  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.1217832", 
  "title": "Feedback matters \u2013 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)", 
  "issued": {
    "date-parts": [
  "abstract": "<p>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.&nbsp;</p>\n\n<p>Abstract</p>\n\n<p>Individuals with upper-limb deficiency who are fitted<br>\nwith a prosthesis are normally trained in the use of such<br>\ndevice. This is even true for individuals who are fitted with a<br>\nmyoelectric prosthesis that uses control algorithms based on<br>\npattern-recognition, despite the intent of pattern-recognition<br>\ncontrol of exploiting &ldquo;intuitive&rdquo; phantom movements.<br>\nConventionally, training individuals for pattern-recognition<br>\ncontrol usually involves an expert who guides the user to<br>\nproduce electromyogram (EMG) signals that optimize<br>\npattern recognition. In the training the individual is<br>\nstimulated to adapt their EMG signals as to make them more<br>\ndistinct in terms of the resulting patterns. To achieve this, for<br>\ninstance, small movements can be added to the basic pattern,<br>\nsuch as flexing the little finger during open hand. Although<br>\ntraining improves online accuracy it still involves<br>\nconsiderable trial and error. Moreover, expert guidance is<br>\ncurrently done based on visual perusal of EMG patterns or<br>\nfeatures thereof and not based on specific metrics<br>\ncharacterizing those EMG signal patterns. Rather than using<br>\nintuitive phantom movements for control, we instead propose<br>\nto use those phantom movements which are most distinct in<br>\nterms of EMG. To find the set of phantom movements that<br>\nprovides the most distinct EMG activation patterns, we<br>\npropose to use a serious game. Using a game, we can train<br>\nindividuals to make EMG patterns distinct while performing<br>\nthem in a robust manner. This game is controlled using the<br>\nEMG captured from 8 electrodes positioned around the<br>\nforearm. Inspired by the work of Radhakrishnan et. al and<br>\nPistohl et. al, the EMG from each electrode is mapped to a<br>\ndirection of the game avatar in the 2D environment. We<br>\nhypothesize that this training will make individuals utilize<br>\ntheir EMG activation space to a greater extent and become<br>\nbetter at generating only EMG activity at specific electrode<br>\nsites so that patterns are more distinct.<br>\nWe are currently conducting an experiment in which 4<br>\nexperimental groups receive different kinds of training.<br>\nGroup 1 receives conventional training without coaching.<br>\nGroup 2 receives conventional training with feedback. Group<br>\n3 receives training with the proposed serious game and group<br>\n4 receives training without any feedback (control). The<br>\nlearning effects between groups are analysed using the<br>\nmetrics proposed by Bunderson et al. and the motion test.</p>", 
  "author": [
      "family": "Kristoffersen, Morten Bak"
      "family": "Franzke, Andreas"
      "family": "Murgia, Alessio"
      "family": "van der Sluis, Corry"
      "family": "Bongers, Raoul"
  "type": "graphic", 
  "id": "1217832"
All versions This version
Views 12496
Downloads 135
Data volume 5.4 MB2.9 MB
Unique views 10077
Unique downloads 94


Cite as