Classifying reaching height through muscle synergies in unconstrained scenarios.

Muscle synergy analysis has been widely adopted in the literature for the analysis of upper limb surface electromyographic signals during reaching tasks and for the prediction of movement direction for myoelectric control purposes. However, previous studies have characterized movements in constrained or semi-constrained scenarios, in which the subjects performing the movement were instructed to reach particular targets or were given some kind of feedback. In this work, the same synergy model has been applied to a completely unconstrained upper limb reaching experiment, with the aim of classifying the height of the target starting from the activity of the synergies. Results show that the synergistic model is able to extract compact features that can identify with good performance three different reaching heights. Moreover, this representation is able to isolate the signals that contain predictive information about the movement direction from the ones that are related to movement timing; this, together with the good performance of the synergy-based classifier supports the proposal of applying this model to the pre-processing of electromyographic signals when dealing with control systems that use signals from multiple muscles to predict movements.