A factorization‐based algorithm to predict EMG data using only kinematics information

EMG analyses have several applications, such as identifying muscle excitation patterns during rehabilitation or training plans, controlling EMG-driven devices. However, experimental measurements can be time consuming difficult to obtain. This study presents a simple algorithm predict signals that applied in real running, given only the instantaneous vector of kinematics. We hypothesize factorization kinematics skeleton together with data calibration subjects could used another subject using kinematic information. The results showed lower-limb muscles predicted accurately less than second this method. Correlation coefficients between and were higher 0.7 10 out 11 for most prediction trials subjects, their overall median value was 0.8. These values confirm method when are measured.