Abstract
A419 at controlling prosthesis with surface electromyogram (sEMG), a classifier which combined Learning Vector Quantization (LVQ) artificial neural network and Back Propagation (BP) artificial neural network was proposed. Surface EMG signals under six different forearm actions were recorded and analyzed with PowerLab Biological signal acquisition system. Eigenvalues were extracted, BP neural network, LVQ neural network and the designed neural network which combined BP neural network and LVQ neural network was used to classify the signals under six forearm actions recorded before. Then pattern recognition rates of the three methods were compared. Result showed that the newly designed neural network had the highest pattern recognition rate of the three methods and thus performed better than both BP neural network and LVQ neural network.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call