A dynamic recurrent neural network for multiple muscles electromyographic mapping to elevation angles of the lower limb in human locomotion.

This paper describes the use of a dynamic recurrent neural network (DRNN) for simulating lower limb coordination in human locomotion. The method is based on mapping between the electromyographic signals (EMG) from six muscles and the elevation angles of the three main lower limb segments (thigh, shank and foot). The DRNN is a fully connected network of 35 hidden units taking into account the temporal relationships history between EMG and lower limb kinematics. Each EMG signal is sent to all 35 units, which converge to three outputs. Each output neurone provides the kinematics of one lower limb segment. The training is supervised, involving learning rule adaptations of synaptic weights and time constant of each unit. Kinematics of the locomotor movements were recorded and analysed using the opto-electronic ELITE system. Comparative analysis of the learning performance with different types of output (position, velocity and acceleration) showed that for common gait mapping velocity data should be used as output, as it is the best compromise between asymptotic error curve, rapid convergence and avoidance of bifurcation. Reproducibility of the identification process and biological plausibility were high, indicating that the DRNN may be used for understanding functional relationships between multiple EMG and locomotion. The DRNN might also be of benefit for prosthetic control.