Fig. 2.

The proposed dimensionality reduction model (b) inspired by the physiological model (a). Each motor neuron j in a pool i receives an input α_ij from the central nervous system, which determines the motor unit spike train x_ij. The input to the motor neuron is partly common to the other motor neurons in the pool and is associated to the spike train by the function g_ij(∙). After estimation of the functions g_ij(∙), the synaptic inputs of the motor neurons are used to extract one activation signal $a_i^r$ in the time processing window r that reflects the common input. The final activation is also obtained by combining in its estimation the activation at the previous processing interval r − 1 ($a_i^{r-1}$) to promote smoothness