Machine learning-based classification of the movements of children with profound or severe intellectual or multiple disabilities using environment data features.

Interesting results revealed a decreasing trend in the accuracy rates (67%, 62.7%, and 50.3%) in decoding three, four, and six task outcomes (or reaching movements from the same limb) respectively, which implies that using 3 classes could be used to control assistive or rehabilitation robotic devices for paralyzed patients [ 25 ].

also in 47,180 other papers