A motion-classification strategy based on sEMG-EEG signal combination for upper-limb amputees.
Xiangxin Li, Oluwarotimi Williams Samuel, Xu Zhang and 3 others
PMID 28061779WHAT IT FOUND
In four above-elbow amputees, combining muscle and brain signals recognized hand and wrist motions better than muscle signals alone, with 91.7% of tested motion attempts correct.
The test was offline, not real-time prosthetic control.
Key findings
01Combining muscle and brain signals recognized motions better than either signal alone.
02The combined method recognized five motions with 91.7% average accuracy, and each motion class was above 89%.
03Optimized combined methods achieved average recognition rates of 87.0% and 84.2%.
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 four male transhumeral amputees took part. The analysis was offline, and performance was judged only by classification accuracy, not by real prosthetic control. The authors state that the EEG cap used would not be feasible outside a controlled laboratory environment. Even the final 20-channel setup may be too many for practical prosthetic applications. One participant, TH4, performed worse, and the authors suggest hair may have increased scalp-electrode impedance.
Declared interests
Funding was provided by the National Key Basic Research Development Program of China, the National Natural Science Foundation of China, the Natural Science Foundation for Distinguished Young Scholars of Guangdong Province, the Special Support Program for Eminent Professionals of Guangdong Province, the Shenzhen High-level Oversea Talent Program (Shenzhen Peacock Plan) Grant, and the Science and Technology Planning Project of Guangdong Province, China. The supplied text gives no competing-interest declaration.
The easy way to misread this
Do not conclude that this method lets an above-elbow amputee control a prosthesis in daily life. The study tested offline recognition of screen-cued motions in four people, not real-time prosthetic use.