Objective: To solve the problem of large samples and contradictory samples in EMG during high level muscle contraction.
Method: By means of recording EMG during muscle contraction with linearly increasing force instead of constant force, basic MUAP templates were obtained with the combination of information diffusion theory and fuzzy neural network. Samples were compressed and contradictory samples were eliminated.
Result: The method was tested by simulated and real EMG data and the results were satisfactory.
Conclusion: This method is meaningful for decomposing NEMG at high level muscle contraction.