On the Suitability of Integrating Accelerometry Data with Electromyography Signals for Resolving the Effect of Changes in Limb Position during Dynamic Limb Movement

It is shown that, unless the classifier is trained in most of the possible positions, the integration of accelerometry data with EMG data can significantly degrade performance compared with EMg alone, and a dynamic training method that moves the residual limb through the regions of interest is introduced.