Fig. 5From: Learning regularized representations of categorically labelled surface EMG enables simultaneous and proportional myoelectric controlExample of MRL calibration results from a single subject. Each point represents the output \(\widehat{{\varvec{y}}}={\left[{\widehat{y}}_{1}, {\widehat{y}}_{2}\right]}^{T}\) of the calibrated MRL model when fed an 8-channel sEMG sample from the calibration data, coloured according to the movement instruction stimuli with which it cooccurred. Each ‘trail’ connecting the origin to a cluster represents the onset and conclusion of a movement repetitionBack to article page