4.7 Article

Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2022.3218430

Keywords

Myoelectric control; pattern recognition; transient EMG; hand wrist prosthetics; cross-subject classifier

Ask authors/readers for more resources

The design of prosthetic controllers using neurophysiological signals remains a significant challenge for bioengineers. Existing electromyographic (EMG) continuous pattern recognition controllers rely on assumptions of stable EMG patterns, which we challenge. We propose an algorithm that decodes wrist and hand movements based on transient EMG signals. Our offline evaluations show promising results with non-amputees achieving a median accuracy of around 96%, while amputees achieved a median accuracy of around 89%. Further assessments with domain-adaptation strategies may be needed for amputees. Overall, our results support the hypothesis that decoding transient EMG signals can be a viable pattern recognition strategy for prosthetic controllers.
The design of prosthetic controllers bymeans of neurophysiologicalsignals still poses a crucial challenge to bioengineers. State of the art of electromyographic (EMG) continuous pattern recognition controllers rely on the questionable assumption that repeated muscular contractions produce repeatable patterns of steady-state EMG signals. Conversely, we propose an algorithm that decodes wrist and hand movements by processing the signals that immediately follow the onset of contraction (i.e., the transient EMG). We collected EMG data from the forearms of 14 non-amputee and 5 transradial amputee participants while they performed wrist flexion/extension, pronation/supination, and four hand grasps (power, lateral, bi-digital, open). We firstly identified the combination of wrist and hand movements that yielded the best control performance for the same participant (intra-subject classification). Then, we assessed the ability of our algorithm to classify participant data that were not included in the training set (cross-subject classification). Our controller achieved a median accuracy of similar to 96% with non-amputees, while it achieved heterogeneous outcomes with amputees, with a median accuracy of similar to 89%. Importantly, for each amputee, it produced at least one acceptable combination of wrist- hand movements (i.e., with accuracy > 85%). Regarding the cross-subject classifier, while our algorithm obtainedpromising resultswith non-amputees (accuracyup to similar to 80%), they were not as good with amputees (accuracy up to similar to 35%), possibly suggesting further assessments with domain-adaptation strategies. In general, our offline outcomes, together with a preliminary online assessment, support the hypothesis that the transient EMG decoding could represent a viable pattern recognition strategy, encouraging further online assessments.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available