Reducing the number of EMG electrodes during online hand gesture classification with changing wrist positions.
Luis Pelaez Murciego, Mauricio C Henrich, Erika G Spaich and 1 others
PMID 35864513WHAT IT FOUND
In thirteen able-bodied people, individually chosen muscle-signal electrodes let participants control hand gestures more reliably than evenly spaced electrodes when the wrist moved, especially at low force.
Using all electrodes performed similarly to the chosen set.
Key findings
01Wrist position changed the spatial pattern of forearm muscle activity, and combining wrist positions lowered the separability between gesture classes.
02Offline, individually selected channels and evenly spaced channels had similar gesture classification accuracy across wrist positions and contraction levels.
03During real-time control, individually selected channels had a higher completion rate than evenly spaced channels, especially at low contraction, but did not outperform the full electrode set.
STILL TO COME
How it was doneWhat they found
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only thirteen right-handed able-bodied participants were tested, so the results do not show what would happen in people with stroke, amputation, or impaired hand function. The task measured gesture-control success, not clinical hand function, independence, or patient outcomes. The best channel set was chosen for each participant, and many selected channels were unique to one participant, so there is no single electrode layout that can be assumed to work for everyone. The paper notes that offline accuracy did not predict online performance well, and the real-time task included feedback and time pressure. The authors state that the clinical benefit of targeted placement still needs testing in patient populations.
Declared interests
The work was funded by the European Commission. The supplied text does not report author conflicts of interest.
The easy way to misread this
Do not read this as evidence that EMG gesture control helps people with stroke, amputation or hand dysfunction. It was tested only in thirteen able-bodied participants, and the paper says the clinical benefit of targeted electrode placement needs to be tested in patient populations.