Investigation on the Contributions of Different Muscles to the Generated Force based on HD-sEMG and DBN.

In this study, we proposed a multi-muscle contraction force estimation framework and implemented it on the elbow flexion task to explore the contributions of different muscles to integrated force at different force levels. High density surface electromyography (HD-sEMG) signals were collected from four muscle groups and the wrist pulling force was measured synchronously. The deep belief network (DBN) was adopted to establish the relationship between HD-sEMG and force. The representative signals of four primary areas, which were considered as the input signal of the force estimation model, were extracted from HD-sEMG by principle component analysis (PCA) algorithm, then fed separately or in common to the DBN to estimate the generated force. And the contributions of different muscle groups to the generated force was analyzed with an index called mean impact value (MIV). The experimental result demonstrates that in multi-muscle contraction task, not all muscles are suitable for force estimation, the force estimation accuracy obtained using only one muscle approximates even exceeds that obtained using multiple muscles, and the relative contributions of different muscle groups to the force can be obtained according to the ranking of MIVs. This scheme provides an effective method for muscle force estimation in multi-muscle contraction tasks, and can be further applied to biomechanics, sports and rehabilitation medicine.