Analysis of surface electromyogram during gait by modified matching pursuit decomposition

The matching pursuit decomposition (MPD) with a redundant Gabor dictionary (GMPD) is a popular method to identify the time-frequency content of nonstationary biomedical signals. However, it is time-consuming and suffers from the low decomposition efficiency when dealing with a signal with multiple nonlinear time-frequency structures (TFS) such as surface electromyograms (SEMG) recorded during gait. The modified MPD (MMPD) solves these problems by modifying the dictionary using elements with similar TFS as the signal to be decomposed. The reassigned spectrogram is used to obtain the TFS of the signal. This prior knowledge about the TFS of the signal is the key for the successful application of the MMPD. The MMPD combined with the reassigned spectrogram is applied in gait SEMG to compare the decomposition efficiency with GMPD, and to quantify the effects of the epidural spinal cord stimulation (ESCS) on the muscle activities of an incomplete spinal cord injured (ISCI) patient in this study. The results show that the MMPD combined with reassigned spectrogram can decompose SEMG with much higher efficiency than the GMPD. Moreover, the MMPD provides a quantitative measure to compare the difference of the time and frequency content between the gait SEMG with and without stimulation. These differences demonstrate that ESCS changes the timing pattern of SEMG during the gait, but does not significantly alter the centroid of the frequency content of SEMG.