Fig. 4.

Reconstruction quality of timing and weightings across conditions compared to randomly generated baseline. R² and normalized root mean squared error (NRMSE) of randomly generated weightings and timings for the unpowered (gray) and powered conditions (blue). The randomly generated weightings and timings could not reconstruct the muscle signals (R²≤ 0). However, the randomly generated weightings could produce a poor reconstruction (R²> 0) demonstrating that the variability in timing is harder to reproduce than in weighting