Modeling and pattern recognition of sEMG for intelligent bionic artificial limb

There are different kinds of correlations between sEMG and muscle activities, which can represent the activities of neuromuscular in a certain extent. sEMG is a feeble, complex, non-stationary signal, which is susceptible to external interference. According to these characteristics, sEMG mathematics models of two hand movements (letter `C' in ASL and CSL (ASLC), and extension of index finger (EXIF)) are established in this paper, which are used for identification and classification of motion patterns. This method can verify the models' ability to characterize different motions. According to the shortcoming of traditional BP neural network algorithm which is easily trapped into local minimum, an improved one based on existing BP algorithm and simulated annealing algorithm is proposed in this paper. The experimental results indicate that the novel one has better recognition capability comparing with traditional BP algorithm.