Time-frequency characterization of multi-channel dynamic sEMG recordings by neural networks

The main effort of this paper is directed towards the characterization of multi-channel muscle contractions recordings measured by surface electromyography (sEMG) for both research and clinical purposes. In particular, an attempt is made in order to describe the kind of modifications in the spectrum and related frequency content of the sEMG data when the forces produced by muscles are varying. Recent works have proposed time-frequency analysis as a powerful tool to investigate some parameters that relate to the progression of muscle fatigue. A different method of time-frequency characterization by means of unsupervised learning processing is here proposed: the growing neural gas (GNG) algorithm is used. The advantage of the proposed method with respect to traditional methods, that make use of the mean or median frequency, seems the complete description of the frequency content of the signal. The obtained results are in agreement with physiologic studies of muscle activity.