The bioelectric potentials associated with muscle activity constitute the electromyogram (EMG). These EMG signals are low-frequency and lower-magnitude signals. In this paper, it is presented that Jordan/Elman neural network can be effectively used for EMG signal noise removal, which is a typical nonlinear multivariable regression problem, as compared with other types of neural networks. Different neural network (NN) models with varying parameters were considered for the design of adaptive neural-network-based filter which is a typical SISO system. The performance parameters, that is, MSE, correlation coefficient, N/P, and t, are found to be in the expected range of values.
E. A. Clancy, N. Hogan. (1995). Multiple site electromyograph amplitude estimation. IEEE Transactions on Biomedical Engineering.42(2):203-211. DOI: 10.1109/72.548174.
Y. St-Amant, D. Rancourt, E. A. Clancy. (1998). Influence of smoothing window length on electromyogram amplitude estimates. IEEE Transactions on Biomedical Engineering.45(6):795-800. DOI: 10.1109/72.548174.
L. Wang, T. S. Buchanan. (2002). Prediction of joint moments using a neural network model of muscle activations from EMG signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering.10(1):30-37. DOI: 10.1109/72.548174.
A. Hamilton-Wright, D. W. Stashuk. (2005). Physiologically based simulation of clinical EMG signals. IEEE Transactions on Biomedical Engineering.52(2):171-183. DOI: 10.1109/72.548174.
Z. Zhang, Z. Tang, C. Vairappan. (2007). A novel learning method for Elman neural network using local search. Neural Information Processing—Letters and Reviews.11(8):181-188. DOI: 10.1109/72.548174.